diff --git a/.env.template b/.env.template index ddcd41a6c..b91f89540 100644 --- a/.env.template +++ b/.env.template @@ -176,7 +176,14 @@ ENABLE_BACKEND_ACCESS_CONTROL=False # Cognee Cloud API settings for syncing data to/from cloud infrastructure COGNEE_CLOUD_API_URL="http://localhost:8001" -COGNEE_CLOUD_AUTH_TOKEN="your-auth-token" +COGNEE_CLOUD_AUTH_TOKEN="your-api-key" + +################################################################################ +# UI Settings +################################################################################ + +# URL where the frontend is served, defaults to http://localhost:3000 +UI_APP_URL=http://localhost:3000 ################################################################################ # 🛠️ DEV Settings @@ -196,6 +203,16 @@ LITELLM_LOG="ERROR" # DEFAULT_USER_EMAIL="" # DEFAULT_USER_PASSWORD="" +################################################################################ +# 📂 AWS Settings +################################################################################ + +#AWS_REGION="" +#AWS_ENDPOINT_URL="" +#AWS_ACCESS_KEY_ID="" +#AWS_SECRET_ACCESS_KEY="" +#AWS_SESSION_TOKEN="" + ------------------------------- END OF POSSIBLE SETTINGS ------------------------------- diff --git a/.github/actions/cognee_setup/action.yml b/.github/actions/cognee_setup/action.yml index 9ae669b53..e46a42edb 100644 --- a/.github/actions/cognee_setup/action.yml +++ b/.github/actions/cognee_setup/action.yml @@ -24,7 +24,7 @@ runs: uses: astral-sh/setup-uv@v4 with: enable-cache: true - + - name: Rebuild uv lockfile shell: bash run: | diff --git a/.github/workflows/basic_tests.yml b/.github/workflows/basic_tests.yml index e2264da3d..3f3e644a2 100644 --- a/.github/workflows/basic_tests.yml +++ b/.github/workflows/basic_tests.yml @@ -188,6 +188,7 @@ jobs: uses: ./.github/actions/cognee_setup with: python-version: ${{ inputs.python-version }} + extra-dependencies: "baml" - name: Run Simple Examples run: uv run python ./examples/python/simple_example.py diff --git a/.github/workflows/e2e_tests.yml b/.github/workflows/e2e_tests.yml index af3a3ff44..3fe7a7992 100644 --- a/.github/workflows/e2e_tests.yml +++ b/.github/workflows/e2e_tests.yml @@ -166,9 +166,6 @@ jobs: python-version: '3.11.x' extra-dependencies: "aws" - - name: Dependencies already installed - run: echo "Dependencies already installed in setup" - - name: Run S3 Bucket Test env: ENV: 'dev' diff --git a/.github/workflows/test_s3_file_storage.yml b/.github/workflows/test_s3_file_storage.yml index c4866ec2d..a477d8933 100644 --- a/.github/workflows/test_s3_file_storage.yml +++ b/.github/workflows/test_s3_file_storage.yml @@ -18,6 +18,7 @@ jobs: uses: ./.github/actions/cognee_setup with: python-version: '3.11.x' + extra-dependencies: "aws" - name: Run S3 File Storage Test env: diff --git a/cognee-frontend/src/ui/Layout/Header.tsx b/cognee-frontend/src/ui/Layout/Header.tsx index 7a1d2e906..1bc57f699 100644 --- a/cognee-frontend/src/ui/Layout/Header.tsx +++ b/cognee-frontend/src/ui/Layout/Header.tsx @@ -2,10 +2,11 @@ import Link from "next/link"; import Image from "next/image"; -import { useBoolean } from "@/utils"; +import { useEffect } from "react"; +import { useBoolean, fetch } from "@/utils"; import { CloseIcon, CloudIcon, CogneeIcon } from "../Icons"; -import { CTAButton, GhostButton, IconButton, Modal } from "../elements"; +import { CTAButton, GhostButton, IconButton, Modal, StatusDot } from "../elements"; import syncData from "@/modules/cloud/syncData"; interface HeaderProps { @@ -23,6 +24,12 @@ export default function Header({ user }: HeaderProps) { setFalse: closeSyncModal, } = useBoolean(false); + const { + value: isMCPConnected, + setTrue: setMCPConnected, + setFalse: setMCPDisconnected, + } = useBoolean(false); + const handleDataSyncConfirm = () => { syncData() .finally(() => { @@ -30,6 +37,19 @@ export default function Header({ user }: HeaderProps) { }); }; + useEffect(() => { + const checkMCPConnection = () => { + fetch.checkMCPHealth() + .then(() => setMCPConnected()) + .catch(() => setMCPDisconnected()); + }; + + checkMCPConnection(); + const interval = setInterval(checkMCPConnection, 30000); + + return () => clearInterval(interval); + }, [setMCPConnected, setMCPDisconnected]); + return ( <>
@@ -39,6 +59,10 @@ export default function Header({ user }: HeaderProps) {
+ + + { isMCPConnected ? "MCP connected" : "MCP disconnected" } +
Sync
diff --git a/cognee-frontend/src/ui/elements/StatusDot.tsx b/cognee-frontend/src/ui/elements/StatusDot.tsx new file mode 100644 index 000000000..4eb71a6e0 --- /dev/null +++ b/cognee-frontend/src/ui/elements/StatusDot.tsx @@ -0,0 +1,13 @@ +import React from "react"; + +const StatusDot = ({ isActive, className }: { isActive: boolean, className?: string }) => { + return ( + + ); +}; + +export default StatusDot; diff --git a/cognee-frontend/src/ui/elements/index.ts b/cognee-frontend/src/ui/elements/index.ts index 551b06596..0133f56f6 100644 --- a/cognee-frontend/src/ui/elements/index.ts +++ b/cognee-frontend/src/ui/elements/index.ts @@ -8,5 +8,6 @@ export { default as IconButton } from "./IconButton"; export { default as GhostButton } from "./GhostButton"; export { default as NeutralButton } from "./NeutralButton"; export { default as StatusIndicator } from "./StatusIndicator"; +export { default as StatusDot } from "./StatusDot"; export { default as Accordion } from "./Accordion"; export { default as Notebook } from "./Notebook"; diff --git a/cognee-frontend/src/utils/fetch.ts b/cognee-frontend/src/utils/fetch.ts index 246853fb9..e67845d78 100644 --- a/cognee-frontend/src/utils/fetch.ts +++ b/cognee-frontend/src/utils/fetch.ts @@ -9,6 +9,8 @@ const backendApiUrl = process.env.NEXT_PUBLIC_BACKEND_API_URL || "http://localho const cloudApiUrl = process.env.NEXT_PUBLIC_CLOUD_API_URL || "http://localhost:8001"; +const mcpApiUrl = process.env.NEXT_PUBLIC_MCP_API_URL || "http://localhost:8001"; + let apiKey: string | null = process.env.NEXT_PUBLIC_COGWIT_API_KEY || null; let accessToken: string | null = null; @@ -66,6 +68,10 @@ fetch.checkHealth = () => { return global.fetch(`${backendApiUrl.replace("/api", "")}/health`); }; +fetch.checkMCPHealth = () => { + return global.fetch(`${mcpApiUrl.replace("/api", "")}/health`); +}; + fetch.setApiKey = (newApiKey: string) => { apiKey = newApiKey; }; diff --git a/cognee-mcp/entrypoint.sh b/cognee-mcp/entrypoint.sh index 53da83c11..e3ff849e0 100644 --- a/cognee-mcp/entrypoint.sh +++ b/cognee-mcp/entrypoint.sh @@ -48,27 +48,27 @@ if [ "$ENVIRONMENT" = "dev" ] || [ "$ENVIRONMENT" = "local" ]; then if [ "$DEBUG" = "true" ]; then echo "Waiting for the debugger to attach..." if [ "$TRANSPORT_MODE" = "sse" ]; then - exec python -m debugpy --wait-for-client --listen 0.0.0.0:$DEBUG_PORT -m cognee --transport sse --host 0.0.0.0 --port $HTTP_PORT --no-migration + exec python -m debugpy --wait-for-client --listen 0.0.0.0:$DEBUG_PORT -m cognee-mcp --transport sse --host 0.0.0.0 --port $HTTP_PORT --no-migration elif [ "$TRANSPORT_MODE" = "http" ]; then - exec python -m debugpy --wait-for-client --listen 0.0.0.0:$DEBUG_PORT -m cognee --transport http --host 0.0.0.0 --port $HTTP_PORT --no-migration + exec python -m debugpy --wait-for-client --listen 0.0.0.0:$DEBUG_PORT -m cognee-mcp --transport http --host 0.0.0.0 --port $HTTP_PORT --no-migration else - exec python -m debugpy --wait-for-client --listen 0.0.0.0:$DEBUG_PORT -m cognee --transport stdio --no-migration + exec python -m debugpy --wait-for-client --listen 0.0.0.0:$DEBUG_PORT -m cognee-mcp --transport stdio --no-migration fi else if [ "$TRANSPORT_MODE" = "sse" ]; then - exec cognee --transport sse --host 0.0.0.0 --port $HTTP_PORT --no-migration + exec cognee-mcp --transport sse --host 0.0.0.0 --port $HTTP_PORT --no-migration elif [ "$TRANSPORT_MODE" = "http" ]; then - exec cognee --transport http --host 0.0.0.0 --port $HTTP_PORT --no-migration + exec cognee-mcp --transport http --host 0.0.0.0 --port $HTTP_PORT --no-migration else - exec cognee --transport stdio --no-migration + exec cognee-mcp --transport stdio --no-migration fi fi else if [ "$TRANSPORT_MODE" = "sse" ]; then - exec cognee --transport sse --host 0.0.0.0 --port $HTTP_PORT --no-migration + exec cognee-mcp --transport sse --host 0.0.0.0 --port $HTTP_PORT --no-migration elif [ "$TRANSPORT_MODE" = "http" ]; then - exec cognee --transport http --host 0.0.0.0 --port $HTTP_PORT --no-migration + exec cognee-mcp --transport http --host 0.0.0.0 --port $HTTP_PORT --no-migration else - exec cognee --transport stdio --no-migration + exec cognee-mcp --transport stdio --no-migration fi fi diff --git a/cognee-mcp/pyproject.toml b/cognee-mcp/pyproject.toml index a1ee22985..f22396bd4 100644 --- a/cognee-mcp/pyproject.toml +++ b/cognee-mcp/pyproject.toml @@ -36,4 +36,4 @@ dev = [ allow-direct-references = true [project.scripts] -cognee = "src:main" +cognee-mcp = "src:main" diff --git a/cognee-mcp/src/server.py b/cognee-mcp/src/server.py index 9393fe71b..cc6eac09e 100755 --- a/cognee-mcp/src/server.py +++ b/cognee-mcp/src/server.py @@ -19,6 +19,10 @@ from cognee.api.v1.cognify.code_graph_pipeline import run_code_graph_pipeline from cognee.modules.search.types import SearchType from cognee.shared.data_models import KnowledgeGraph from cognee.modules.storage.utils import JSONEncoder +from starlette.responses import JSONResponse +from starlette.middleware import Middleware +from starlette.middleware.cors import CORSMiddleware +import uvicorn try: @@ -38,6 +42,53 @@ mcp = FastMCP("Cognee") logger = get_logger() +async def run_sse_with_cors(): + """Custom SSE transport with CORS middleware.""" + sse_app = mcp.sse_app() + sse_app.add_middleware( + CORSMiddleware, + allow_origins=["http://localhost:3000"], + allow_credentials=True, + allow_methods=["GET"], + allow_headers=["*"], + ) + + config = uvicorn.Config( + sse_app, + host=mcp.settings.host, + port=mcp.settings.port, + log_level=mcp.settings.log_level.lower(), + ) + server = uvicorn.Server(config) + await server.serve() + + +async def run_http_with_cors(): + """Custom HTTP transport with CORS middleware.""" + http_app = mcp.streamable_http_app() + http_app.add_middleware( + CORSMiddleware, + allow_origins=["http://localhost:3000"], + allow_credentials=True, + allow_methods=["GET"], + allow_headers=["*"], + ) + + config = uvicorn.Config( + http_app, + host=mcp.settings.host, + port=mcp.settings.port, + log_level=mcp.settings.log_level.lower(), + ) + server = uvicorn.Server(config) + await server.serve() + + +@mcp.custom_route("/health", methods=["GET"]) +async def health_check(request): + return JSONResponse({"status": "ok"}) + + @mcp.tool() async def cognee_add_developer_rules( base_path: str = ".", graph_model_file: str = None, graph_model_name: str = None @@ -975,12 +1026,12 @@ async def main(): await mcp.run_stdio_async() elif args.transport == "sse": logger.info(f"Running MCP server with SSE transport on {args.host}:{args.port}") - await mcp.run_sse_async() + await run_sse_with_cors() elif args.transport == "http": logger.info( f"Running MCP server with Streamable HTTP transport on {args.host}:{args.port}{args.path}" ) - await mcp.run_streamable_http_async() + await run_http_with_cors() if __name__ == "__main__": diff --git a/cognee/api/client.py b/cognee/api/client.py index 7d5f48672..04c81841f 100644 --- a/cognee/api/client.py +++ b/cognee/api/client.py @@ -3,7 +3,6 @@ import os import uvicorn -import sentry_sdk from traceback import format_exc from contextlib import asynccontextmanager from fastapi import Request @@ -42,11 +41,18 @@ from cognee.modules.users.methods.get_authenticated_user import REQUIRE_AUTHENTI logger = get_logger() if os.getenv("ENV", "prod") == "prod": - sentry_sdk.init( - dsn=os.getenv("SENTRY_REPORTING_URL"), - traces_sample_rate=1.0, - profiles_sample_rate=1.0, - ) + try: + import sentry_sdk + + sentry_sdk.init( + dsn=os.getenv("SENTRY_REPORTING_URL"), + traces_sample_rate=1.0, + profiles_sample_rate=1.0, + ) + except ImportError: + logger.info( + "Sentry SDK not available. Install with 'pip install cognee\"[monitoring]\"' to enable error monitoring." + ) app_environment = os.getenv("ENV", "prod") @@ -81,7 +87,7 @@ if CORS_ALLOWED_ORIGINS: ] else: allowed_origins = [ - "http://localhost:3000", + os.getenv("UI_APP_URL", "http://localhost:3000"), ] # Block all except explicitly set origins app.add_middleware( diff --git a/cognee/api/v1/ui/__init__.py b/cognee/api/v1/ui/__init__.py index f268a2e54..d5708da5a 100644 --- a/cognee/api/v1/ui/__init__.py +++ b/cognee/api/v1/ui/__init__.py @@ -1 +1 @@ -from .ui import start_ui, stop_ui, ui +from .ui import start_ui diff --git a/cognee/api/v1/ui/ui.py b/cognee/api/v1/ui/ui.py index 6faca19e8..7df0b519a 100644 --- a/cognee/api/v1/ui/ui.py +++ b/cognee/api/v1/ui/ui.py @@ -1,5 +1,5 @@ import os -import signal +import socket import subprocess import threading import time @@ -7,7 +7,7 @@ import webbrowser import zipfile import requests from pathlib import Path -from typing import Callable, Optional, Tuple +from typing import Callable, Optional, Tuple, List import tempfile import shutil @@ -17,6 +17,80 @@ from cognee.version import get_cognee_version logger = get_logger() +def _stream_process_output( + process: subprocess.Popen, stream_name: str, prefix: str, color_code: str = "" +) -> threading.Thread: + """ + Stream output from a process with a prefix to identify the source. + + Args: + process: The subprocess to monitor + stream_name: 'stdout' or 'stderr' + prefix: Text prefix for each line (e.g., '[BACKEND]', '[FRONTEND]') + color_code: ANSI color code for the prefix (optional) + + Returns: + Thread that handles the streaming + """ + + def stream_reader(): + stream = getattr(process, stream_name) + if stream is None: + return + + reset_code = "\033[0m" if color_code else "" + + try: + for line in iter(stream.readline, b""): + if line: + line_text = line.decode("utf-8").rstrip() + if line_text: + print(f"{color_code}{prefix}{reset_code} {line_text}", flush=True) + except Exception: + pass + finally: + if stream: + stream.close() + + thread = threading.Thread(target=stream_reader, daemon=True) + thread.start() + return thread + + +def _is_port_available(port: int) -> bool: + """ + Check if a port is available on localhost. + Returns True if the port is available, False otherwise. + """ + try: + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock: + sock.settimeout(1) # 1 second timeout + result = sock.connect_ex(("localhost", port)) + return result != 0 # Port is available if connection fails + except Exception: + return False + + +def _check_required_ports(ports_to_check: List[Tuple[int, str]]) -> Tuple[bool, List[str]]: + """ + Check if all required ports are available on localhost. + + Args: + ports_to_check: List of (port, service_name) tuples + + Returns: + Tuple of (all_available: bool, unavailable_services: List[str]) + """ + unavailable = [] + + for port, service_name in ports_to_check: + if not _is_port_available(port): + unavailable.append(f"{service_name} (port {port})") + logger.error(f"Port {port} is already in use for {service_name}") + + return len(unavailable) == 0, unavailable + + def normalize_version_for_comparison(version: str) -> str: """ Normalize version string for comparison. @@ -327,55 +401,111 @@ def prompt_user_for_download() -> bool: def start_ui( pid_callback: Callable[[int], None], - host: str = "localhost", port: int = 3000, open_browser: bool = True, auto_download: bool = False, start_backend: bool = False, - backend_host: str = "localhost", backend_port: int = 8000, + start_mcp: bool = False, + mcp_port: int = 8001, ) -> Optional[subprocess.Popen]: """ - Start the cognee frontend UI server, optionally with the backend API server. + Start the cognee frontend UI server, optionally with the backend API server and MCP server. This function will: 1. Optionally start the cognee backend API server - 2. Find the cognee-frontend directory (development) or download it (pip install) - 3. Check if Node.js and npm are available (for development mode) - 4. Install dependencies if needed (development mode) - 5. Start the frontend server - 6. Optionally open the browser + 2. Optionally start the cognee MCP server + 3. Find the cognee-frontend directory (development) or download it (pip install) + 4. Check if Node.js and npm are available (for development mode) + 5. Install dependencies if needed (development mode) + 6. Start the frontend server + 7. Optionally open the browser Args: pid_callback: Callback to notify with PID of each spawned process - host: Host to bind the frontend server to (default: localhost) port: Port to run the frontend server on (default: 3000) open_browser: Whether to open the browser automatically (default: True) auto_download: If True, download frontend without prompting (default: False) start_backend: If True, also start the cognee API backend server (default: False) - backend_host: Host to bind the backend server to (default: localhost) backend_port: Port to run the backend server on (default: 8000) + start_mcp: If True, also start the cognee MCP server (default: False) + mcp_port: Port to run the MCP server on (default: 8001) Returns: subprocess.Popen object representing the running frontend server, or None if failed - Note: If backend is started, it runs in a separate process that will be cleaned up - when the frontend process is terminated. + Note: If backend and/or MCP server are started, they run in separate processes + that will be cleaned up when the frontend process is terminated. Example: >>> import cognee + >>> def dummy_callback(pid): pass >>> # Start just the frontend - >>> server = cognee.start_ui() + >>> server = cognee.start_ui(dummy_callback) >>> >>> # Start both frontend and backend - >>> server = cognee.start_ui(start_backend=True) + >>> server = cognee.start_ui(dummy_callback, start_backend=True) >>> # UI will be available at http://localhost:3000 >>> # API will be available at http://localhost:8000 - >>> # To stop both servers later: + >>> + >>> # Start frontend with MCP server + >>> server = cognee.start_ui(dummy_callback, start_mcp=True) + >>> # UI will be available at http://localhost:3000 + >>> # MCP server will be available at http://127.0.0.1:8001/sse + >>> # To stop all servers later: >>> server.terminate() """ logger.info("Starting cognee UI...") + + ports_to_check = [(port, "Frontend UI")] + + if start_backend: + ports_to_check.append((backend_port, "Backend API")) + + if start_mcp: + ports_to_check.append((mcp_port, "MCP Server")) + + logger.info("Checking port availability...") + all_ports_available, unavailable_services = _check_required_ports(ports_to_check) + + if not all_ports_available: + error_msg = f"Cannot start cognee UI: The following services have ports already in use: {', '.join(unavailable_services)}" + logger.error(error_msg) + logger.error("Please stop the conflicting services or change the port configuration.") + return None + + logger.info("✓ All required ports are available") backend_process = None + if start_mcp: + logger.info("Starting Cognee MCP server with Docker...") + cwd = os.getcwd() + env_file = os.path.join(cwd, ".env") + try: + mcp_process = subprocess.Popen( + [ + "docker", + "run", + "-p", + f"{mcp_port}:8000", + "--rm", + "--env-file", + env_file, + "-e", + "TRANSPORT_MODE=sse", + "cognee/cognee-mcp:daulet-dev", + ], + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + preexec_fn=os.setsid if hasattr(os, "setsid") else None, + ) + + _stream_process_output(mcp_process, "stdout", "[MCP]", "\033[34m") # Blue + _stream_process_output(mcp_process, "stderr", "[MCP]", "\033[34m") # Blue + + pid_callback(mcp_process.pid) + logger.info(f"✓ Cognee MCP server starting on http://127.0.0.1:{mcp_port}/sse") + except Exception as e: + logger.error(f"Failed to start MCP server with Docker: {str(e)}") # Start backend server if requested if start_backend: logger.info("Starting cognee backend API server...") @@ -389,16 +519,19 @@ def start_ui( "uvicorn", "cognee.api.client:app", "--host", - backend_host, + "localhost", "--port", str(backend_port), ], - # Inherit stdout/stderr from parent process to show logs - stdout=None, - stderr=None, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, preexec_fn=os.setsid if hasattr(os, "setsid") else None, ) + # Start threads to stream backend output with prefix + _stream_process_output(backend_process, "stdout", "[BACKEND]", "\033[32m") # Green + _stream_process_output(backend_process, "stderr", "[BACKEND]", "\033[32m") # Green + pid_callback(backend_process.pid) # Give the backend a moment to start @@ -408,7 +541,7 @@ def start_ui( logger.error("Backend server failed to start - process exited early") return None - logger.info(f"✓ Backend API started at http://{backend_host}:{backend_port}") + logger.info(f"✓ Backend API started at http://localhost:{backend_port}") except Exception as e: logger.error(f"Failed to start backend server: {str(e)}") @@ -453,11 +586,11 @@ def start_ui( # Prepare environment variables env = os.environ.copy() - env["HOST"] = host + env["HOST"] = "localhost" env["PORT"] = str(port) # Start the development server - logger.info(f"Starting frontend server at http://{host}:{port}") + logger.info(f"Starting frontend server at http://localhost:{port}") logger.info("This may take a moment to compile and start...") try: @@ -468,10 +601,13 @@ def start_ui( env=env, stdout=subprocess.PIPE, stderr=subprocess.PIPE, - text=True, preexec_fn=os.setsid if hasattr(os, "setsid") else None, ) + # Start threads to stream frontend output with prefix + _stream_process_output(process, "stdout", "[FRONTEND]", "\033[33m") # Yellow + _stream_process_output(process, "stderr", "[FRONTEND]", "\033[33m") # Yellow + pid_callback(process.pid) # Give it a moment to start up @@ -479,10 +615,7 @@ def start_ui( # Check if process is still running if process.poll() is not None: - stdout, stderr = process.communicate() - logger.error("Frontend server failed to start:") - logger.error(f"stdout: {stdout}") - logger.error(f"stderr: {stderr}") + logger.error("Frontend server failed to start - check the logs above for details") return None # Open browser if requested @@ -491,7 +624,7 @@ def start_ui( def open_browser_delayed(): time.sleep(5) # Give Next.js time to fully start try: - webbrowser.open(f"http://{host}:{port}") # TODO: use dashboard url? + webbrowser.open(f"http://localhost:{port}") except Exception as e: logger.warning(f"Could not open browser automatically: {e}") @@ -499,13 +632,9 @@ def start_ui( browser_thread.start() logger.info("✓ Cognee UI is starting up...") - logger.info(f"✓ Open your browser to: http://{host}:{port}") + logger.info(f"✓ Open your browser to: http://localhost:{port}") logger.info("✓ The UI will be available once Next.js finishes compiling") - # Store backend process reference in the frontend process for cleanup - if backend_process: - process._cognee_backend_process = backend_process - return process except Exception as e: @@ -523,102 +652,3 @@ def start_ui( except (OSError, ProcessLookupError): pass return None - - -def stop_ui(process: subprocess.Popen) -> bool: - """ - Stop a running UI server process and backend process (if started), along with all their children. - - Args: - process: The subprocess.Popen object returned by start_ui() - - Returns: - bool: True if stopped successfully, False otherwise - """ - if not process: - return False - - success = True - - try: - # First, stop the backend process if it exists - backend_process = getattr(process, "_cognee_backend_process", None) - if backend_process: - logger.info("Stopping backend server...") - try: - backend_process.terminate() - try: - backend_process.wait(timeout=5) - logger.info("Backend server stopped gracefully") - except subprocess.TimeoutExpired: - logger.warning("Backend didn't terminate gracefully, forcing kill") - backend_process.kill() - backend_process.wait() - logger.info("Backend server stopped") - except Exception as e: - logger.error(f"Error stopping backend server: {str(e)}") - success = False - - # Now stop the frontend process - logger.info("Stopping frontend server...") - # Try to terminate the process group (includes child processes like Next.js) - if hasattr(os, "killpg"): - try: - # Kill the entire process group - os.killpg(os.getpgid(process.pid), signal.SIGTERM) - logger.debug("Sent SIGTERM to process group") - except (OSError, ProcessLookupError): - # Fall back to terminating just the main process - process.terminate() - logger.debug("Terminated main process only") - else: - process.terminate() - logger.debug("Terminated main process (Windows)") - - try: - process.wait(timeout=10) - logger.info("Frontend server stopped gracefully") - except subprocess.TimeoutExpired: - logger.warning("Frontend didn't terminate gracefully, forcing kill") - - # Force kill the process group - if hasattr(os, "killpg"): - try: - os.killpg(os.getpgid(process.pid), signal.SIGKILL) - logger.debug("Sent SIGKILL to process group") - except (OSError, ProcessLookupError): - process.kill() - logger.debug("Force killed main process only") - else: - process.kill() - logger.debug("Force killed main process (Windows)") - - process.wait() - - if success: - logger.info("UI servers stopped successfully") - - return success - - except Exception as e: - logger.error(f"Error stopping UI servers: {str(e)}") - return False - - -# Convenience function similar to DuckDB's approach -def ui() -> Optional[subprocess.Popen]: - """ - Convenient alias for start_ui() with default parameters. - Similar to how DuckDB provides simple ui() function. - """ - return start_ui() - - -if __name__ == "__main__": - # Test the UI startup - server = start_ui() - if server: - try: - input("Press Enter to stop the server...") - finally: - stop_ui(server) diff --git a/cognee/cli/_cognee.py b/cognee/cli/_cognee.py index 52915594b..b68e5c80f 100644 --- a/cognee/cli/_cognee.py +++ b/cognee/cli/_cognee.py @@ -204,19 +204,27 @@ def main() -> int: nonlocal spawned_pids spawned_pids.append(pid) + frontend_port = 3000 + start_backend, backend_port = True, 8000 + start_mcp, mcp_port = True, 8001 server_process = start_ui( - host="localhost", - port=3000, - open_browser=True, - start_backend=True, - auto_download=True, pid_callback=pid_callback, + port=frontend_port, + open_browser=True, + auto_download=True, + start_backend=start_backend, + backend_port=backend_port, + start_mcp=start_mcp, + mcp_port=mcp_port, ) if server_process: fmt.success("UI server started successfully!") - fmt.echo("The interface is available at: http://localhost:3000") - fmt.echo("The API backend is available at: http://localhost:8000") + fmt.echo(f"The interface is available at: http://localhost:{frontend_port}") + if start_backend: + fmt.echo(f"The API backend is available at: http://localhost:{backend_port}") + if start_mcp: + fmt.echo(f"The MCP server is available at: http://localhost:{mcp_port}") fmt.note("Press Ctrl+C to stop the server...") try: diff --git a/cognee/eval_framework/modal_eval_dashboard.py b/cognee/eval_framework/modal_eval_dashboard.py index acc0c3aa9..9b1147528 100644 --- a/cognee/eval_framework/modal_eval_dashboard.py +++ b/cognee/eval_framework/modal_eval_dashboard.py @@ -1,6 +1,6 @@ import os import json -import pandas as pd + import subprocess import modal import streamlit as st @@ -78,6 +78,14 @@ def main(): } ) + try: + import pandas as pd + except ImportError: + st.error( + "Pandas is required for the evaluation dashboard. Install with 'pip install cognee\"[evals]\"' to use this feature." + ) + return + df = pd.DataFrame(records) if df.empty: st.warning("No JSON files found in the volume.") diff --git a/cognee/infrastructure/data/utils/extract_keywords.py b/cognee/infrastructure/data/utils/extract_keywords.py deleted file mode 100644 index 8085459c9..000000000 --- a/cognee/infrastructure/data/utils/extract_keywords.py +++ /dev/null @@ -1,48 +0,0 @@ -from sklearn.feature_extraction.text import TfidfVectorizer - -from cognee.infrastructure.data.exceptions.exceptions import KeywordExtractionError -from cognee.shared.utils import extract_pos_tags - - -def extract_keywords(text: str) -> list[str]: - """ - Extract keywords from the provided text string. - - This function raises an KeyWordExtractionError if the input text is empty. It processes the - text to extract parts of speech, focusing on nouns, and uses TF-IDF to identify the most - relevant keywords based on their frequency. The function returns a list of up to 15 - keywords, each having more than 3 characters. - - Parameters: - ----------- - - - text (str): The input text from which to extract keywords. - - Returns: - -------- - - - list[str]: A list of keywords extracted from the text, containing up to 15 nouns - with more than 3 characters. - """ - if len(text) == 0: - raise KeywordExtractionError() - - tags = extract_pos_tags(text) - nouns = [word for (word, tag) in tags if tag == "NN"] - - vectorizer = TfidfVectorizer() - tfidf = vectorizer.fit_transform(nouns) - - top_nouns = sorted( - vectorizer.vocabulary_, key=lambda x: tfidf[0, vectorizer.vocabulary_[x]], reverse=True - ) - - keywords = [] - - for word in top_nouns: - if len(word) > 3: - keywords.append(word) - if len(keywords) >= 15: - break - - return keywords diff --git a/cognee/infrastructure/databases/relational/create_relational_engine.py b/cognee/infrastructure/databases/relational/create_relational_engine.py index a889e1758..deaeaa2da 100644 --- a/cognee/infrastructure/databases/relational/create_relational_engine.py +++ b/cognee/infrastructure/databases/relational/create_relational_engine.py @@ -39,8 +39,16 @@ def create_relational_engine( connection_string = f"sqlite+aiosqlite:///{db_path}/{db_name}" if db_provider == "postgres": - connection_string = ( - f"postgresql+asyncpg://{db_username}:{db_password}@{db_host}:{db_port}/{db_name}" - ) + try: + # Test if asyncpg is available + import asyncpg + + connection_string = ( + f"postgresql+asyncpg://{db_username}:{db_password}@{db_host}:{db_port}/{db_name}" + ) + except ImportError: + raise ImportError( + "PostgreSQL dependencies are not installed. Please install with 'pip install cognee\"[postgres]\"' or 'pip install cognee\"[postgres-binary]\"' to use PostgreSQL functionality." + ) return SQLAlchemyAdapter(connection_string) diff --git a/cognee/infrastructure/databases/vector/create_vector_engine.py b/cognee/infrastructure/databases/vector/create_vector_engine.py index 77bf7d83f..5c4e93359 100644 --- a/cognee/infrastructure/databases/vector/create_vector_engine.py +++ b/cognee/infrastructure/databases/vector/create_vector_engine.py @@ -66,7 +66,12 @@ def create_vector_engine( f"postgresql+asyncpg://{db_username}:{db_password}@{db_host}:{db_port}/{db_name}" ) - from .pgvector.PGVectorAdapter import PGVectorAdapter + try: + from .pgvector.PGVectorAdapter import PGVectorAdapter + except ImportError: + raise ImportError( + "PostgreSQL dependencies are not installed. Please install with 'pip install cognee\"[postgres]\"' or 'pip install cognee\"[postgres-binary]\"' to use PGVector functionality." + ) return PGVectorAdapter( connection_string, diff --git a/cognee/infrastructure/databases/vector/lancedb/LanceDBAdapter.py b/cognee/infrastructure/databases/vector/lancedb/LanceDBAdapter.py index 0184ec3ee..0c93f81e7 100644 --- a/cognee/infrastructure/databases/vector/lancedb/LanceDBAdapter.py +++ b/cognee/infrastructure/databases/vector/lancedb/LanceDBAdapter.py @@ -205,9 +205,12 @@ class LanceDBAdapter(VectorDBInterface): collection = await self.get_collection(collection_name) if len(data_point_ids) == 1: - results = await collection.query().where(f"id = '{data_point_ids[0]}'").to_pandas() + results = await collection.query().where(f"id = '{data_point_ids[0]}'") else: - results = await collection.query().where(f"id IN {tuple(data_point_ids)}").to_pandas() + results = await collection.query().where(f"id IN {tuple(data_point_ids)}") + + # Convert query results to list format + results_list = results.to_list() if hasattr(results, "to_list") else list(results) return [ ScoredResult( @@ -215,7 +218,7 @@ class LanceDBAdapter(VectorDBInterface): payload=result["payload"], score=0, ) - for result in results.to_dict("index").values() + for result in results_list ] async def search( @@ -242,9 +245,7 @@ class LanceDBAdapter(VectorDBInterface): if limit == 0: return [] - results = await collection.vector_search(query_vector).limit(limit).to_pandas() - - result_values = list(results.to_dict("index").values()) + result_values = await collection.vector_search(query_vector).limit(limit).to_list() if not result_values: return [] diff --git a/cognee/infrastructure/databases/vector/pgvector/PGVectorAdapter.py b/cognee/infrastructure/databases/vector/pgvector/PGVectorAdapter.py index 4dfd9792f..d20d7d519 100644 --- a/cognee/infrastructure/databases/vector/pgvector/PGVectorAdapter.py +++ b/cognee/infrastructure/databases/vector/pgvector/PGVectorAdapter.py @@ -9,7 +9,6 @@ from sqlalchemy.exc import ProgrammingError from tenacity import retry, retry_if_exception_type, stop_after_attempt, wait_exponential from asyncpg import DeadlockDetectedError, DuplicateTableError, UniqueViolationError - from cognee.shared.logging_utils import get_logger from cognee.infrastructure.engine import DataPoint from cognee.infrastructure.engine.utils import parse_id diff --git a/cognee/infrastructure/files/storage/S3FileStorage.py b/cognee/infrastructure/files/storage/S3FileStorage.py index ca2a73291..00b67337b 100644 --- a/cognee/infrastructure/files/storage/S3FileStorage.py +++ b/cognee/infrastructure/files/storage/S3FileStorage.py @@ -1,6 +1,5 @@ import os -import s3fs -from typing import BinaryIO, Union +from typing import BinaryIO, Union, TYPE_CHECKING from contextlib import asynccontextmanager from cognee.infrastructure.files.storage.s3_config import get_s3_config @@ -8,23 +7,34 @@ from cognee.infrastructure.utils.run_async import run_async from cognee.infrastructure.files.storage.FileBufferedReader import FileBufferedReader from .storage import Storage +if TYPE_CHECKING: + import s3fs + class S3FileStorage(Storage): """ - Manage local file storage operations such as storing, retrieving, and managing files on - the filesystem. + Manage S3 file storage operations such as storing, retrieving, and managing files on + S3-compatible storage. """ storage_path: str - s3: s3fs.S3FileSystem + s3: "s3fs.S3FileSystem" def __init__(self, storage_path: str): + try: + import s3fs + except ImportError: + raise ImportError( + 's3fs is required for S3FileStorage. Install it with: pip install cognee"[aws]"' + ) + self.storage_path = storage_path s3_config = get_s3_config() if s3_config.aws_access_key_id is not None and s3_config.aws_secret_access_key is not None: self.s3 = s3fs.S3FileSystem( key=s3_config.aws_access_key_id, secret=s3_config.aws_secret_access_key, + token=s3_config.aws_session_token, anon=False, endpoint_url=s3_config.aws_endpoint_url, client_kwargs={"region_name": s3_config.aws_region}, diff --git a/cognee/infrastructure/files/storage/s3_config.py b/cognee/infrastructure/files/storage/s3_config.py index 0b9372b7e..cefe5cd2f 100644 --- a/cognee/infrastructure/files/storage/s3_config.py +++ b/cognee/infrastructure/files/storage/s3_config.py @@ -8,6 +8,7 @@ class S3Config(BaseSettings): aws_endpoint_url: Optional[str] = None aws_access_key_id: Optional[str] = None aws_secret_access_key: Optional[str] = None + aws_session_token: Optional[str] = None model_config = SettingsConfigDict(env_file=".env", extra="allow") diff --git a/cognee/infrastructure/files/utils/open_data_file.py b/cognee/infrastructure/files/utils/open_data_file.py index 171f5deb7..ad8a6b63e 100644 --- a/cognee/infrastructure/files/utils/open_data_file.py +++ b/cognee/infrastructure/files/utils/open_data_file.py @@ -4,7 +4,6 @@ from urllib.parse import urlparse from contextlib import asynccontextmanager from cognee.infrastructure.files.utils.get_data_file_path import get_data_file_path -from cognee.infrastructure.files.storage.S3FileStorage import S3FileStorage from cognee.infrastructure.files.storage.LocalFileStorage import LocalFileStorage @@ -23,23 +22,17 @@ async def open_data_file(file_path: str, mode: str = "rb", encoding: str = None, yield file elif file_path.startswith("s3://"): + try: + from cognee.infrastructure.files.storage.S3FileStorage import S3FileStorage + except ImportError: + raise ImportError( + "S3 dependencies are not installed. Please install with 'pip install cognee\"[aws]\"' to use S3 functionality." + ) + normalized_url = get_data_file_path(file_path) s3_dir_path = os.path.dirname(normalized_url) s3_filename = os.path.basename(normalized_url) - # if "/" in s3_path: - # s3_dir = "/".join(s3_path.split("/")[:-1]) - # s3_filename = s3_path.split("/")[-1] - # else: - # s3_dir = "" - # s3_filename = s3_path - - # Extract filesystem path from S3 URL structure - # file_dir_path = ( - # f"s3://{parsed_url.netloc}/{s3_dir}" if s3_dir else f"s3://{parsed_url.netloc}" - # ) - # file_name = s3_filename - file_storage = S3FileStorage(s3_dir_path) async with file_storage.open(s3_filename, mode=mode, **kwargs) as file: diff --git a/cognee/infrastructure/llm/config.py b/cognee/infrastructure/llm/config.py index 495b583d6..6658a6251 100644 --- a/cognee/infrastructure/llm/config.py +++ b/cognee/infrastructure/llm/config.py @@ -1,9 +1,13 @@ import os -from typing import Optional, ClassVar +from typing import Optional, ClassVar, Any from functools import lru_cache from pydantic_settings import BaseSettings, SettingsConfigDict from pydantic import model_validator -from baml_py import ClientRegistry + +try: + from baml_py import ClientRegistry +except ImportError: + ClientRegistry = None class LLMConfig(BaseSettings): @@ -65,27 +69,36 @@ class LLMConfig(BaseSettings): fallback_endpoint: str = "" fallback_model: str = "" - baml_registry: ClassVar[ClientRegistry] = ClientRegistry() + baml_registry: Optional[Any] = None model_config = SettingsConfigDict(env_file=".env", extra="allow") def model_post_init(self, __context) -> None: """Initialize the BAML registry after the model is created.""" - raw_options = { - "model": self.baml_llm_model, - "temperature": self.baml_llm_temperature, - "api_key": self.baml_llm_api_key, - "base_url": self.baml_llm_endpoint, - "api_version": self.baml_llm_api_version, - } + # Check if BAML is selected as structured output framework but not available + if self.structured_output_framework.lower() == "baml" and ClientRegistry is None: + raise ImportError( + "BAML is selected as structured output framework but not available. " + "Please install with 'pip install cognee\"[baml]\"' to use BAML extraction features." + ) + elif self.structured_output_framework.lower() == "baml" and ClientRegistry is not None: + self.baml_registry = ClientRegistry() - # Note: keep the item only when the value is not None or an empty string (they would override baml default values) - options = {k: v for k, v in raw_options.items() if v not in (None, "")} - self.baml_registry.add_llm_client( - name=self.baml_llm_provider, provider=self.baml_llm_provider, options=options - ) - # Sets the primary client - self.baml_registry.set_primary(self.baml_llm_provider) + raw_options = { + "model": self.baml_llm_model, + "temperature": self.baml_llm_temperature, + "api_key": self.baml_llm_api_key, + "base_url": self.baml_llm_endpoint, + "api_version": self.baml_llm_api_version, + } + + # Note: keep the item only when the value is not None or an empty string (they would override baml default values) + options = {k: v for k, v in raw_options.items() if v not in (None, "")} + self.baml_registry.add_llm_client( + name=self.baml_llm_provider, provider=self.baml_llm_provider, options=options + ) + # Sets the primary client + self.baml_registry.set_primary(self.baml_llm_provider) @model_validator(mode="after") def ensure_env_vars_for_ollama(self) -> "LLMConfig": diff --git a/cognee/infrastructure/llm/structured_output_framework/baml/baml_src/extraction/acreate_structured_output.py b/cognee/infrastructure/llm/structured_output_framework/baml/baml_src/extraction/acreate_structured_output.py index 8efcce23d..6ef27e51d 100644 --- a/cognee/infrastructure/llm/structured_output_framework/baml/baml_src/extraction/acreate_structured_output.py +++ b/cognee/infrastructure/llm/structured_output_framework/baml/baml_src/extraction/acreate_structured_output.py @@ -53,7 +53,8 @@ async def acreate_structured_output( # Transform BAML response to proper pydantic reponse model if response_model is str: - return str(result) + # Note: when a response model is set to string in python, result is stored in text property in the BAML response model + return str(result.text) return response_model.model_validate(result.dict()) diff --git a/cognee/modules/ingestion/data_types/TextData.py b/cognee/modules/ingestion/data_types/TextData.py index 7c2364a5a..90d5335b5 100644 --- a/cognee/modules/ingestion/data_types/TextData.py +++ b/cognee/modules/ingestion/data_types/TextData.py @@ -1,7 +1,6 @@ from typing import BinaryIO from contextlib import asynccontextmanager import hashlib -from cognee.infrastructure.data.utils.extract_keywords import extract_keywords from .IngestionData import IngestionData diff --git a/cognee/modules/retrieval/context_providers/TripletSearchContextProvider.py b/cognee/modules/retrieval/context_providers/TripletSearchContextProvider.py index b539055fa..6cdd57eec 100644 --- a/cognee/modules/retrieval/context_providers/TripletSearchContextProvider.py +++ b/cognee/modules/retrieval/context_providers/TripletSearchContextProvider.py @@ -42,14 +42,12 @@ class TripletSearchContextProvider(BaseContextProvider): self, entities: List[DataPoint], query: str, - user: User, memory_fragment: CogneeGraph, ) -> List: """Creates search tasks for valid entities.""" tasks = [ brute_force_triplet_search( query=f"{entity_text} {query}", - user=user, top_k=self.top_k, collections=self.collections, properties_to_project=self.properties_to_project, @@ -84,9 +82,8 @@ class TripletSearchContextProvider(BaseContextProvider): if not entities: return "No entities provided for context search." - user = await get_default_user() memory_fragment = await get_memory_fragment(self.properties_to_project) - search_tasks = self._get_search_tasks(entities, query, user, memory_fragment) + search_tasks = self._get_search_tasks(entities, query, memory_fragment) if not search_tasks: return "No valid entities found for context search." diff --git a/cognee/modules/retrieval/graph_completion_retriever.py b/cognee/modules/retrieval/graph_completion_retriever.py index cd4944ca9..1772c6300 100644 --- a/cognee/modules/retrieval/graph_completion_retriever.py +++ b/cognee/modules/retrieval/graph_completion_retriever.py @@ -93,11 +93,8 @@ class GraphCompletionRetriever(BaseGraphRetriever): for field_name in index_fields: vector_index_collections.append(f"{subclass.__name__}_{field_name}") - user = await get_default_user() - found_triplets = await brute_force_triplet_search( query, - user=user, top_k=self.top_k, collections=vector_index_collections or None, node_type=self.node_type, diff --git a/cognee/modules/retrieval/utils/brute_force_triplet_search.py b/cognee/modules/retrieval/utils/brute_force_triplet_search.py index aa3233776..8a9bcdeb4 100644 --- a/cognee/modules/retrieval/utils/brute_force_triplet_search.py +++ b/cognee/modules/retrieval/utils/brute_force_triplet_search.py @@ -89,7 +89,6 @@ async def get_memory_fragment( async def brute_force_triplet_search( query: str, - user: User, top_k: int = 5, collections: Optional[List[str]] = None, properties_to_project: Optional[List[str]] = None, @@ -102,7 +101,6 @@ async def brute_force_triplet_search( Args: query (str): The search query. - user (User): The user performing the search. top_k (int): The number of top results to retrieve. collections (Optional[List[str]]): List of collections to query. properties_to_project (Optional[List[str]]): List of properties to project. @@ -139,8 +137,6 @@ async def brute_force_triplet_search( query_vector = (await vector_engine.embedding_engine.embed_text([query]))[0] - send_telemetry("cognee.brute_force_triplet_search EXECUTION STARTED", user.id) - async def search_in_collection(collection_name: str): try: return await vector_engine.search( @@ -176,20 +172,14 @@ async def brute_force_triplet_search( results = await memory_fragment.calculate_top_triplet_importances(k=top_k) - send_telemetry("cognee.brute_force_triplet_search EXECUTION COMPLETED", user.id) - return results except CollectionNotFoundError: return [] except Exception as error: logger.error( - "Error during brute force search for user: %s, query: %s. Error: %s", - user.id, + "Error during brute force search for query: %s. Error: %s", query, error, ) - send_telemetry( - "cognee.brute_force_triplet_search EXECUTION FAILED", user.id, {"error": str(error)} - ) raise error diff --git a/cognee/modules/search/methods/no_access_control_search.py b/cognee/modules/search/methods/no_access_control_search.py index bb3eaba42..a93fce067 100644 --- a/cognee/modules/search/methods/no_access_control_search.py +++ b/cognee/modules/search/methods/no_access_control_search.py @@ -35,7 +35,7 @@ async def no_access_control_search( [get_completion, get_context] = search_tools if only_context: - return await get_context(query_text) + return None, await get_context(query_text), [] context = await get_context(query_text) result = await get_completion(query_text, context) diff --git a/cognee/modules/search/methods/search.py b/cognee/modules/search/methods/search.py index 65efafb4c..8bcef815f 100644 --- a/cognee/modules/search/methods/search.py +++ b/cognee/modules/search/methods/search.py @@ -143,20 +143,35 @@ async def search( context = prepared_search_results["context"] datasets = prepared_search_results["datasets"] - return_value.append( - { - "search_result": [result] if result else None, - "dataset_id": datasets[0].id, - "dataset_name": datasets[0].name, - "graphs": graphs, - } - ) + if only_context: + return_value.append( + { + "search_result": [context] if context else None, + "dataset_id": datasets[0].id, + "dataset_name": datasets[0].name, + "graphs": graphs, + } + ) + else: + return_value.append( + { + "search_result": [result] if result else None, + "dataset_id": datasets[0].id, + "dataset_name": datasets[0].name, + "graphs": graphs, + } + ) return return_value else: return_value = [] - for search_result in search_results: - result, context, datasets = search_result - return_value.append(result) + if only_context: + for search_result in search_results: + prepared_search_results = await prepare_search_result(search_result) + return_value.append(prepared_search_results["context"]) + else: + for search_result in search_results: + result, context, datasets = search_result + return_value.append(result) # For maintaining backwards compatibility if len(return_value) == 1 and isinstance(return_value[0], list): return return_value[0] diff --git a/cognee/modules/visualization/cognee_network_visualization.py b/cognee/modules/visualization/cognee_network_visualization.py index dde2fe98d..c735e70f1 100644 --- a/cognee/modules/visualization/cognee_network_visualization.py +++ b/cognee/modules/visualization/cognee_network_visualization.py @@ -1,6 +1,5 @@ import os import json -import networkx from cognee.shared.logging_utils import get_logger from cognee.infrastructure.files.storage.LocalFileStorage import LocalFileStorage @@ -9,6 +8,8 @@ logger = get_logger() async def cognee_network_visualization(graph_data, destination_file_path: str = None): + import networkx + nodes_data, edges_data = graph_data G = networkx.DiGraph() @@ -22,6 +23,9 @@ async def cognee_network_visualization(graph_data, destination_file_path: str = "TableRow": "#f47710", "TableType": "#6510f4", "ColumnValue": "#13613a", + "SchemaTable": "#f47710", + "DatabaseSchema": "#6510f4", + "SchemaRelationship": "#13613a", "default": "#D3D3D3", } @@ -104,7 +108,7 @@ async def cognee_network_visualization(graph_data, destination_file_path: str = .nodes circle { stroke: white; stroke-width: 0.5px; filter: drop-shadow(0 0 5px rgba(255,255,255,0.3)); } .node-label { font-size: 5px; font-weight: bold; fill: white; text-anchor: middle; dominant-baseline: middle; font-family: 'Inter', sans-serif; pointer-events: none; } .edge-label { font-size: 3px; fill: rgba(255, 255, 255, 0.7); text-anchor: middle; dominant-baseline: middle; font-family: 'Inter', sans-serif; pointer-events: none; } - + .tooltip { position: absolute; text-align: left; @@ -166,7 +170,7 @@ async def cognee_network_visualization(graph_data, destination_file_path: str = // Create tooltip content for edge var content = "Edge Information
"; content += "Relationship: " + d.relation + "
"; - + // Show all weights if (d.all_weights && Object.keys(d.all_weights).length > 0) { content += "Weights:
"; @@ -176,23 +180,23 @@ async def cognee_network_visualization(graph_data, destination_file_path: str = } else if (d.weight !== null && d.weight !== undefined) { content += "Weight: " + d.weight + "
"; } - + if (d.relationship_type) { content += "Type: " + d.relationship_type + "
"; } - + // Add other edge properties if (d.edge_info) { Object.keys(d.edge_info).forEach(function(key) { - if (key !== 'weight' && key !== 'weights' && key !== 'relationship_type' && - key !== 'source_node_id' && key !== 'target_node_id' && - key !== 'relationship_name' && key !== 'updated_at' && + if (key !== 'weight' && key !== 'weights' && key !== 'relationship_type' && + key !== 'source_node_id' && key !== 'target_node_id' && + key !== 'relationship_name' && key !== 'updated_at' && !key.startsWith('weight_')) { content += key + ": " + d.edge_info[key] + "
"; } }); } - + tooltip.html(content) .style("left", (d3.event.pageX + 10) + "px") .style("top", (d3.event.pageY - 10) + "px") diff --git a/cognee/shared/utils.py b/cognee/shared/utils.py index 6ecdbc8f1..90fbb9cd4 100644 --- a/cognee/shared/utils.py +++ b/cognee/shared/utils.py @@ -4,7 +4,6 @@ import os import ssl import requests from datetime import datetime, timezone -import matplotlib.pyplot as plt import http.server import socketserver from threading import Thread @@ -30,37 +29,6 @@ def create_secure_ssl_context() -> ssl.SSLContext: return ssl.create_default_context() -def get_entities(tagged_tokens): - import nltk - - nltk.download("maxent_ne_chunker", quiet=True) - - from nltk.chunk import ne_chunk - - return ne_chunk(tagged_tokens) - - -def extract_pos_tags(sentence): - """Extract Part-of-Speech (POS) tags for words in a sentence.""" - import nltk - - # Ensure that the necessary NLTK resources are downloaded - nltk.download("words", quiet=True) - nltk.download("punkt", quiet=True) - nltk.download("averaged_perceptron_tagger", quiet=True) - - from nltk.tag import pos_tag - from nltk.tokenize import word_tokenize - - # Tokenize the sentence into words - tokens = word_tokenize(sentence) - - # Tag each word with its corresponding POS tag - pos_tags = pos_tag(tokens) - - return pos_tags - - def get_anonymous_id(): """Creates or reads a anonymous user id""" tracking_id = os.getenv("TRACKING_ID", None) diff --git a/cognee/tasks/graph/infer_data_ontology.py b/cognee/tasks/graph/infer_data_ontology.py deleted file mode 100644 index 93b02db9f..000000000 --- a/cognee/tasks/graph/infer_data_ontology.py +++ /dev/null @@ -1,309 +0,0 @@ -# PROPOSED TO BE DEPRECATED - -"""This module contains the OntologyEngine class which is responsible for adding graph ontology from a JSON or CSV file.""" - -import csv -import json -from cognee.shared.logging_utils import get_logger -from datetime import datetime, timezone -from fastapi import status -from typing import Any, Dict, List, Optional, Union, Type - -import aiofiles -import pandas as pd -from pydantic import BaseModel - -from cognee.modules.graph.exceptions import EntityNotFoundError -from cognee.modules.ingestion.exceptions import IngestionError - -from cognee.infrastructure.data.chunking.config import get_chunk_config -from cognee.infrastructure.data.chunking.get_chunking_engine import get_chunk_engine -from cognee.infrastructure.databases.graph.get_graph_engine import get_graph_engine -from cognee.infrastructure.files.utils.extract_text_from_file import extract_text_from_file -from cognee.infrastructure.files.utils.guess_file_type import guess_file_type, FileTypeException -from cognee.modules.data.methods.add_model_class_to_graph import ( - add_model_class_to_graph, -) -from cognee.tasks.graph.models import NodeModel, GraphOntology -from cognee.shared.data_models import KnowledgeGraph -from cognee.modules.engine.utils import generate_node_id, generate_node_name -from cognee.infrastructure.llm.LLMGateway import LLMGateway - -logger = get_logger("task:infer_data_ontology") - - -async def extract_ontology(content: str, response_model: Type[BaseModel]): - """ - Extracts structured ontology from the provided content using a pre-defined LLM client. - - This asynchronous function retrieves a system prompt from a file and utilizes an LLM - client to create a structured output based on the input content and specified response - model. - - Parameters: - ----------- - - - content (str): The content from which to extract the ontology. - - response_model (Type[BaseModel]): The model that defines the structure of the - output ontology. - - Returns: - -------- - - The structured ontology extracted from the content. - """ - - system_prompt = LLMGateway.read_query_prompt("extract_ontology.txt") - - ontology = await LLMGateway.acreate_structured_output(content, system_prompt, response_model) - - return ontology - - -class OntologyEngine: - """ - Manage ontology data and operations for graph structures, providing methods for data - loading, flattening models, and adding ontological relationships to a graph database. - - Public methods: - - - flatten_model - - recursive_flatten - - load_data - - add_graph_ontology - """ - - async def flatten_model( - self, model: NodeModel, parent_id: Optional[str] = None - ) -> Dict[str, Any]: - """ - Flatten the model to a dictionary including optional parent ID and relationship details - if available. - - Parameters: - ----------- - - - model (NodeModel): The NodeModel instance to flatten. - - parent_id (Optional[str]): An optional ID of the parent node for hierarchical - purposes. (default None) - - Returns: - -------- - - - Dict[str, Any]: A dictionary representation of the model with flattened - attributes. - """ - result = model.dict() - result["parent_id"] = parent_id - if model.default_relationship: - result.update( - { - "relationship_type": model.default_relationship.type, - "relationship_source": model.default_relationship.source, - "relationship_target": model.default_relationship.target, - } - ) - return result - - async def recursive_flatten( - self, items: Union[List[Dict[str, Any]], Dict[str, Any]], parent_id: Optional[str] = None - ) -> List[Dict[str, Any]]: - """ - Recursively flatten a hierarchical structure of models into a flat list of dictionaries. - - Parameters: - ----------- - - - items (Union[List[Dict[str, Any]], Dict[str, Any]]): A list or dictionary - containing models to flatten. - - parent_id (Optional[str]): An optional ID of the parent node to maintain hierarchy - during flattening. (default None) - - Returns: - -------- - - - List[Dict[str, Any]]: A flat list of dictionaries representing the hierarchical - model structure. - """ - flat_list = [] - - if isinstance(items, list): - for item in items: - flat_list.extend(await self.recursive_flatten(item, parent_id)) - elif isinstance(items, dict): - model = NodeModel.model_validate(items) - flat_list.append(await self.flatten_model(model, parent_id)) - for child in model.children: - flat_list.extend(await self.recursive_flatten(child, model.node_id)) - return flat_list - - async def load_data(self, file_path: str) -> Union[List[Dict[str, Any]], Dict[str, Any]]: - """ - Load data from a specified JSON or CSV file and return it in a structured format. - - Parameters: - ----------- - - - file_path (str): The path to the file to load data from. - - Returns: - -------- - - - Union[List[Dict[str, Any]], Dict[str, Any]]: Parsed data from the file as either a - list of dictionaries or a single dictionary depending on content type. - """ - try: - if file_path.endswith(".json"): - async with aiofiles.open(file_path, mode="r") as f: - data = await f.read() - return json.loads(data) - elif file_path.endswith(".csv"): - async with aiofiles.open(file_path, mode="r") as f: - content = await f.read() - reader = csv.DictReader(content.splitlines()) - return list(reader) - else: - raise IngestionError(message="Unsupported file format") - except Exception as e: - raise IngestionError( - message=f"Failed to load data from {file_path}: {e}", - status_code=status.HTTP_422_UNPROCESSABLE_ENTITY, - ) - - async def add_graph_ontology(self, file_path: str = None, documents: list = None): - """ - Add graph ontology from a JSON or CSV file, or infer relationships from provided - document content. Raise exceptions for invalid file types or missing entities. - - Parameters: - ----------- - - - file_path (str): Optional path to a file containing data to be loaded. (default - None) - - documents (list): Optional list of document objects for content extraction if no - file path is provided. (default None) - """ - if file_path is None: - initial_chunks_and_ids = [] - - chunk_config = get_chunk_config() - chunk_engine = get_chunk_engine() - chunk_strategy = chunk_config.chunk_strategy - - for base_file in documents: - with open(base_file.raw_data_location, "rb") as file: - try: - file_type = guess_file_type(file) - text = extract_text_from_file(file, file_type) - - subchunks, chunks_with_ids = chunk_engine.chunk_data( - chunk_strategy, - text, - chunk_config.chunk_size, - chunk_config.chunk_overlap, - ) - - if chunks_with_ids[0][0] == 1: - initial_chunks_and_ids.append({base_file.id: chunks_with_ids}) - - except FileTypeException: - logger.warning( - "File (%s) has an unknown file type. We are skipping it.", file["id"] - ) - - ontology = await extract_ontology(str(initial_chunks_and_ids), GraphOntology) - graph_client = await get_graph_engine() - - await graph_client.add_nodes( - [ - ( - node.id, - dict( - uuid=generate_node_id(node.id), - name=generate_node_name(node.name), - type=generate_node_id(node.id), - description=node.description, - updated_at=datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M:%S"), - ), - ) - for node in ontology.nodes - ] - ) - - await graph_client.add_edges( - ( - generate_node_id(edge.source_id), - generate_node_id(edge.target_id), - edge.relationship_type, - dict( - source_node_id=generate_node_id(edge.source_id), - target_node_id=generate_node_id(edge.target_id), - relationship_name=edge.relationship_type, - updated_at=datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M:%S"), - ), - ) - for edge in ontology.edges - ) - - else: - dataset_level_information = documents[0][1] - - # Extract the list of valid IDs from the explanations - valid_ids = {item["id"] for item in dataset_level_information} - try: - data = await self.load_data(file_path) - flt_ontology = await self.recursive_flatten(data) - df = pd.DataFrame(flt_ontology) - graph_client = await get_graph_engine() - - for _, row in df.iterrows(): - node_data = row.to_dict() - node_id = node_data.pop("node_id", None) - if node_id in valid_ids: - await graph_client.add_node(node_id, node_data) - if node_id not in valid_ids: - raise EntityNotFoundError( - message=f"Node ID {node_id} not found in the dataset" - ) - if pd.notna(row.get("relationship_source")) and pd.notna( - row.get("relationship_target") - ): - await graph_client.add_edge( - row["relationship_source"], - row["relationship_target"], - relationship_name=row["relationship_type"], - edge_properties={ - "source_node_id": row["relationship_source"], - "target_node_id": row["relationship_target"], - "relationship_name": row["relationship_type"], - "updated_at": datetime.now(timezone.utc).strftime( - "%Y-%m-%d %H:%M:%S" - ), - }, - ) - - return - except Exception as e: - raise RuntimeError(f"Failed to add graph ontology from {file_path}: {e}") from e - - -async def infer_data_ontology(documents, ontology_model=KnowledgeGraph, root_node_id=None): - """ - Infer data ontology from provided documents and optionally add it to a graph. - - Parameters: - ----------- - - - documents: The documents from which to infer the ontology. - - ontology_model: The ontology model to use for the inference, defaults to - KnowledgeGraph. (default KnowledgeGraph) - - root_node_id: An optional root node identifier for the ontology. (default None) - """ - if ontology_model == KnowledgeGraph: - ontology_engine = OntologyEngine() - root_node_id = await ontology_engine.add_graph_ontology(documents=documents) - else: - graph_engine = await get_graph_engine() - await add_model_class_to_graph(ontology_model, graph_engine) - - yield (documents, root_node_id) diff --git a/cognee/tasks/ingestion/migrate_relational_database.py b/cognee/tasks/ingestion/migrate_relational_database.py index 936ea59e0..53ce176e8 100644 --- a/cognee/tasks/ingestion/migrate_relational_database.py +++ b/cognee/tasks/ingestion/migrate_relational_database.py @@ -4,16 +4,20 @@ from sqlalchemy import text from cognee.infrastructure.databases.relational.get_migration_relational_engine import ( get_migration_relational_engine, ) +from cognee.infrastructure.databases.relational.config import get_migration_config from cognee.tasks.storage.index_data_points import index_data_points from cognee.tasks.storage.index_graph_edges import index_graph_edges +from cognee.tasks.schema.ingest_database_schema import ingest_database_schema from cognee.modules.engine.models import TableRow, TableType, ColumnValue logger = logging.getLogger(__name__) -async def migrate_relational_database(graph_db, schema, migrate_column_data=True): +async def migrate_relational_database( + graph_db, schema, migrate_column_data=True, schema_only=False +): """ Migrates data from a relational database into a graph database. @@ -26,11 +30,133 @@ async def migrate_relational_database(graph_db, schema, migrate_column_data=True Both TableType and TableRow inherit from DataPoint to maintain consistency with Cognee data model. """ + # Create a mapping of node_id to node objects for referencing in edge creation + if schema_only: + node_mapping, edge_mapping = await schema_only_ingestion(schema) + + else: + node_mapping, edge_mapping = await complete_database_ingestion(schema, migrate_column_data) + + def _remove_duplicate_edges(edge_mapping): + seen = set() + unique_original_shape = [] + + for tup in edge_mapping: + # We go through all the tuples in the edge_mapping and we only add unique tuples to the list + # To eliminate duplicate edges. + source_id, target_id, rel_name, rel_dict = tup + # We need to convert the dictionary to a frozenset to be able to compare values for it + rel_dict_hashable = frozenset(sorted(rel_dict.items())) + hashable_tup = (source_id, target_id, rel_name, rel_dict_hashable) + + # We use the seen set to keep track of unique edges + if hashable_tup not in seen: + # A list that has frozensets elements instead of dictionaries is needed to be able to compare values + seen.add(hashable_tup) + # append the original tuple shape (with the dictionary) if it's the first time we see it + unique_original_shape.append(tup) + + return unique_original_shape + + # Add all nodes and edges to the graph + # NOTE: Nodes and edges have to be added in batch for speed optimization, Especially for NetworkX. + # If we'd create nodes and add them to graph in real time the process would take too long. + # Every node and edge added to NetworkX is saved to file which is very slow when not done in batches. + await graph_db.add_nodes(list(node_mapping.values())) + await graph_db.add_edges(_remove_duplicate_edges(edge_mapping)) + + # In these steps we calculate the vector embeddings of our nodes and edges and save them to vector database + # Cognee uses this information to perform searches on the knowledge graph. + await index_data_points(list(node_mapping.values())) + await index_graph_edges() + + logger.info("Data successfully migrated from relational database to desired graph database.") + return await graph_db.get_graph_data() + + +async def schema_only_ingestion(schema): + node_mapping = {} + edge_mapping = [] + + # Calling the ingest_database_schema function to return DataPoint subclasses + result = await ingest_database_schema( + schema=schema, + max_sample_rows=5, + ) + database_schema = result["database_schema"] + schema_tables = result["schema_tables"] + schema_relationships = result["relationships"] + database_node_id = database_schema.id + node_mapping[database_node_id] = database_schema + for table in schema_tables: + table_node_id = table.id + # Add TableSchema Datapoint as a node. + node_mapping[table_node_id] = table + edge_mapping.append( + ( + table_node_id, + database_node_id, + "is_part_of", + dict( + source_node_id=table_node_id, + target_node_id=database_node_id, + relationship_name="is_part_of", + ), + ) + ) + table_name_to_id = {t.name: t.id for t in schema_tables} + for rel in schema_relationships: + source_table_id = table_name_to_id.get(rel.source_table) + target_table_id = table_name_to_id.get(rel.target_table) + + relationship_id = rel.id + + # Add RelationshipTable DataPoint as a node. + node_mapping[relationship_id] = rel + edge_mapping.append( + ( + source_table_id, + relationship_id, + "has_relationship", + dict( + source_node_id=source_table_id, + target_node_id=relationship_id, + relationship_name=rel.relationship_type, + ), + ) + ) + edge_mapping.append( + ( + relationship_id, + target_table_id, + "has_relationship", + dict( + source_node_id=relationship_id, + target_node_id=target_table_id, + relationship_name=rel.relationship_type, + ), + ) + ) + edge_mapping.append( + ( + source_table_id, + target_table_id, + rel.relationship_type, + dict( + source_node_id=source_table_id, + target_node_id=target_table_id, + relationship_name=rel.relationship_type, + ), + ) + ) + return node_mapping, edge_mapping + + +async def complete_database_ingestion(schema, migrate_column_data): engine = get_migration_relational_engine() # Create a mapping of node_id to node objects for referencing in edge creation node_mapping = {} edge_mapping = [] - async with engine.engine.begin() as cursor: # First, create table type nodes for all tables for table_name, details in schema.items(): @@ -38,7 +164,7 @@ async def migrate_relational_database(graph_db, schema, migrate_column_data=True table_node = TableType( id=uuid5(NAMESPACE_OID, name=table_name), name=table_name, - description=f"Table: {table_name}", + description=f'Relational database table with the following name: "{table_name}".', ) # Add TableType node to mapping ( node will be added to the graph later based on this mapping ) @@ -75,7 +201,7 @@ async def migrate_relational_database(graph_db, schema, migrate_column_data=True name=node_id, is_a=table_node, properties=str(row_properties), - description=f"Row in {table_name} with {primary_key_col}={primary_key_value}", + description=f'Row in relational database table from the table with the name: "{table_name}" with the following row data {str(row_properties)} where the dictionary key value is the column name and the value is the column value. This row has the id of: {node_id}', ) # Store the node object in our mapping @@ -113,7 +239,7 @@ async def migrate_relational_database(graph_db, schema, migrate_column_data=True id=uuid5(NAMESPACE_OID, name=column_node_id), name=column_node_id, properties=f"{key} {value} {table_name}", - description=f"Column name={key} and value={value} from column from table={table_name}", + description=f"column from relational database table={table_name}. Column name={key} and value={value}. The value of the column is related to the following row with this id: {row_node.id}. This column has the following ID: {column_node_id}", ) node_mapping[column_node_id] = column_node @@ -180,39 +306,4 @@ async def migrate_relational_database(graph_db, schema, migrate_column_data=True ), ) ) - - def _remove_duplicate_edges(edge_mapping): - seen = set() - unique_original_shape = [] - - for tup in edge_mapping: - # We go through all the tuples in the edge_mapping and we only add unique tuples to the list - # To eliminate duplicate edges. - source_id, target_id, rel_name, rel_dict = tup - # We need to convert the dictionary to a frozenset to be able to compare values for it - rel_dict_hashable = frozenset(sorted(rel_dict.items())) - hashable_tup = (source_id, target_id, rel_name, rel_dict_hashable) - - # We use the seen set to keep track of unique edges - if hashable_tup not in seen: - # A list that has frozensets elements instead of dictionaries is needed to be able to compare values - seen.add(hashable_tup) - # append the original tuple shape (with the dictionary) if it's the first time we see it - unique_original_shape.append(tup) - - return unique_original_shape - - # Add all nodes and edges to the graph - # NOTE: Nodes and edges have to be added in batch for speed optimization, Especially for NetworkX. - # If we'd create nodes and add them to graph in real time the process would take too long. - # Every node and edge added to NetworkX is saved to file which is very slow when not done in batches. - await graph_db.add_nodes(list(node_mapping.values())) - await graph_db.add_edges(_remove_duplicate_edges(edge_mapping)) - - # In these steps we calculate the vector embeddings of our nodes and edges and save them to vector database - # Cognee uses this information to perform searches on the knowledge graph. - await index_data_points(list(node_mapping.values())) - await index_graph_edges() - - logger.info("Data successfully migrated from relational database to desired graph database.") - return await graph_db.get_graph_data() + return node_mapping, edge_mapping diff --git a/cognee/tasks/ingestion/resolve_data_directories.py b/cognee/tasks/ingestion/resolve_data_directories.py index 1d3124a0c..aa2f95303 100644 --- a/cognee/tasks/ingestion/resolve_data_directories.py +++ b/cognee/tasks/ingestion/resolve_data_directories.py @@ -32,7 +32,10 @@ async def resolve_data_directories( import s3fs fs = s3fs.S3FileSystem( - key=s3_config.aws_access_key_id, secret=s3_config.aws_secret_access_key, anon=False + key=s3_config.aws_access_key_id, + secret=s3_config.aws_secret_access_key, + token=s3_config.aws_session_token, + anon=False, ) for item in data: diff --git a/cognee/tasks/schema/ingest_database_schema.py b/cognee/tasks/schema/ingest_database_schema.py new file mode 100644 index 000000000..e3823701c --- /dev/null +++ b/cognee/tasks/schema/ingest_database_schema.py @@ -0,0 +1,134 @@ +from typing import List, Dict +from uuid import uuid5, NAMESPACE_OID +from cognee.infrastructure.engine.models.DataPoint import DataPoint +from sqlalchemy import text +from cognee.tasks.schema.models import DatabaseSchema, SchemaTable, SchemaRelationship +from cognee.infrastructure.databases.relational.get_migration_relational_engine import ( + get_migration_relational_engine, +) +from cognee.infrastructure.databases.relational.config import get_migration_config +from datetime import datetime, timezone + + +async def ingest_database_schema( + schema, + max_sample_rows: int = 0, +) -> Dict[str, List[DataPoint] | DataPoint]: + """ + Extract database schema metadata (optionally with sample data) and return DataPoint models for graph construction. + + Args: + schema: Database schema + max_sample_rows: Maximum sample rows per table (0 means no sampling) + + Returns: + Dict with keys: + "database_schema": DatabaseSchema + "schema_tables": List[SchemaTable] + "relationships": List[SchemaRelationship] + """ + + tables = {} + sample_data = {} + schema_tables = [] + schema_relationships = [] + + migration_config = get_migration_config() + engine = get_migration_relational_engine() + qi = engine.engine.dialect.identifier_preparer.quote + try: + max_sample_rows = max(0, int(max_sample_rows)) + except (TypeError, ValueError): + max_sample_rows = 0 + + def qname(name: str): + split_name = name.split(".") + return ".".join(qi(p) for p in split_name) + + async with engine.engine.begin() as cursor: + for table_name, details in schema.items(): + tn = qname(table_name) + if max_sample_rows > 0: + rows_result = await cursor.execute( + text(f"SELECT * FROM {tn} LIMIT :limit;"), # noqa: S608 - tn is fully quoted + {"limit": max_sample_rows}, + ) + rows = [dict(r) for r in rows_result.mappings().all()] + else: + rows = [] + + if engine.engine.dialect.name == "postgresql": + if "." in table_name: + schema_part, table_part = table_name.split(".", 1) + else: + schema_part, table_part = "public", table_name + estimate = await cursor.execute( + text( + "SELECT reltuples::bigint AS estimate " + "FROM pg_class c " + "JOIN pg_namespace n ON n.oid = c.relnamespace " + "WHERE n.nspname = :schema AND c.relname = :table" + ), + {"schema": schema_part, "table": table_part}, + ) + row_count_estimate = estimate.scalar() or 0 + else: + count_result = await cursor.execute(text(f"SELECT COUNT(*) FROM {tn};")) # noqa: S608 - tn is fully quoted + row_count_estimate = count_result.scalar() + + schema_table = SchemaTable( + id=uuid5(NAMESPACE_OID, name=f"{table_name}"), + name=table_name, + columns=details["columns"], + primary_key=details.get("primary_key"), + foreign_keys=details.get("foreign_keys", []), + sample_rows=rows, + row_count_estimate=row_count_estimate, + description=f"Relational database table with '{table_name}' with {len(details['columns'])} columns and approx. {row_count_estimate} rows." + f"Here are the columns this table contains: {details['columns']}" + f"Here are a few sample_rows to show the contents of the table: {rows}" + f"Table is part of the database: {migration_config.migration_db_name}", + ) + schema_tables.append(schema_table) + tables[table_name] = details + sample_data[table_name] = rows + + for fk in details.get("foreign_keys", []): + ref_table_fq = fk["ref_table"] + if "." not in ref_table_fq and "." in table_name: + ref_table_fq = f"{table_name.split('.', 1)[0]}.{ref_table_fq}" + + relationship_name = ( + f"{table_name}:{fk['column']}->{ref_table_fq}:{fk['ref_column']}" + ) + relationship = SchemaRelationship( + id=uuid5(NAMESPACE_OID, name=relationship_name), + name=relationship_name, + source_table=table_name, + target_table=ref_table_fq, + relationship_type="foreign_key", + source_column=fk["column"], + target_column=fk["ref_column"], + description=f"Relational database table foreign key relationship between: {table_name}.{fk['column']} → {ref_table_fq}.{fk['ref_column']}" + f"This foreing key relationship between table columns is a part of the following database: {migration_config.migration_db_name}", + ) + schema_relationships.append(relationship) + + id_str = f"{migration_config.migration_db_provider}:{migration_config.migration_db_name}" + database_schema = DatabaseSchema( + id=uuid5(NAMESPACE_OID, name=id_str), + name=migration_config.migration_db_name, + database_type=migration_config.migration_db_provider, + tables=tables, + sample_data=sample_data, + extraction_timestamp=datetime.now(timezone.utc), + description=f"Database schema containing {len(schema_tables)} tables and {len(schema_relationships)} relationships. " + f"The database type is {migration_config.migration_db_provider}." + f"The database contains the following tables: {tables}", + ) + + return { + "database_schema": database_schema, + "schema_tables": schema_tables, + "relationships": schema_relationships, + } diff --git a/cognee/tasks/schema/models.py b/cognee/tasks/schema/models.py new file mode 100644 index 000000000..4b13f420b --- /dev/null +++ b/cognee/tasks/schema/models.py @@ -0,0 +1,41 @@ +from cognee.infrastructure.engine.models.DataPoint import DataPoint +from typing import List, Dict, Optional +from datetime import datetime + + +class DatabaseSchema(DataPoint): + """Represents a complete database schema with sample data""" + + name: str + database_type: str # sqlite, postgres, etc. + tables: Dict[str, Dict] # Reuse existing schema format from SqlAlchemyAdapter + sample_data: Dict[str, List[Dict]] # Limited examples per table + extraction_timestamp: datetime + description: str + metadata: dict = {"index_fields": ["description", "name"]} + + +class SchemaTable(DataPoint): + """Represents an individual table schema with relationships""" + + name: str + columns: List[Dict] # Column definitions with types + primary_key: Optional[str] + foreign_keys: List[Dict] # Foreign key relationships + sample_rows: List[Dict] # Max 3-5 example rows + row_count_estimate: Optional[int] # Actual table size + description: str + metadata: dict = {"index_fields": ["description", "name"]} + + +class SchemaRelationship(DataPoint): + """Represents relationships between tables""" + + name: str + source_table: str + target_table: str + relationship_type: str # "foreign_key", "one_to_many", etc. + source_column: str + target_column: str + description: str + metadata: dict = {"index_fields": ["description", "name"]} diff --git a/cognee/tests/test_relational_db_migration.py b/cognee/tests/test_relational_db_migration.py index 68b46dbf5..2b69ce854 100644 --- a/cognee/tests/test_relational_db_migration.py +++ b/cognee/tests/test_relational_db_migration.py @@ -197,6 +197,80 @@ async def relational_db_migration(): print(f"All checks passed for {graph_db_provider} provider with '{relationship_label}' edges!") +async def test_schema_only_migration(): + # 1. Setup test DB and extract schema + migration_engine = await setup_test_db() + schema = await migration_engine.extract_schema() + + # 2. Setup graph engine + graph_engine = await get_graph_engine() + + # 4. Migrate schema only + await migrate_relational_database(graph_engine, schema=schema, schema_only=True) + + # 5. Verify number of tables through search + search_results = await cognee.search( + query_text="How many tables are there in this database", + query_type=cognee.SearchType.GRAPH_COMPLETION, + top_k=30, + ) + assert any("11" in r for r in search_results), ( + "Number of tables in the database reported in search_results is either None or not equal to 11" + ) + + graph_db_provider = os.getenv("GRAPH_DATABASE_PROVIDER", "networkx").lower() + + edge_counts = { + "is_part_of": 0, + "has_relationship": 0, + "foreign_key": 0, + } + + if graph_db_provider == "neo4j": + for rel_type in edge_counts.keys(): + query_str = f""" + MATCH ()-[r:{rel_type}]->() + RETURN count(r) as c + """ + rows = await graph_engine.query(query_str) + edge_counts[rel_type] = rows[0]["c"] + + elif graph_db_provider == "kuzu": + for rel_type in edge_counts.keys(): + query_str = f""" + MATCH ()-[r:EDGE]->() + WHERE r.relationship_name = '{rel_type}' + RETURN count(r) as c + """ + rows = await graph_engine.query(query_str) + edge_counts[rel_type] = rows[0][0] + + elif graph_db_provider == "networkx": + nodes, edges = await graph_engine.get_graph_data() + for _, _, key, _ in edges: + if key in edge_counts: + edge_counts[key] += 1 + + else: + raise ValueError(f"Unsupported graph database provider: {graph_db_provider}") + + # 7. Assert counts match expected values + expected_counts = { + "is_part_of": 11, + "has_relationship": 22, + "foreign_key": 11, + } + + for rel_type, expected in expected_counts.items(): + actual = edge_counts[rel_type] + assert actual == expected, ( + f"Expected {expected} edges for relationship '{rel_type}', but found {actual}" + ) + + print("Schema-only migration edge counts validated successfully!") + print(f"Edge counts: {edge_counts}") + + async def test_migration_sqlite(): database_to_migrate_path = os.path.join(pathlib.Path(__file__).parent, "test_data/") @@ -209,6 +283,7 @@ async def test_migration_sqlite(): ) await relational_db_migration() + await test_schema_only_migration() async def test_migration_postgres(): @@ -224,6 +299,7 @@ async def test_migration_postgres(): } ) await relational_db_migration() + await test_schema_only_migration() async def main(): diff --git a/cognee/tests/unit/modules/retrieval/graph_completion_retriever_context_extension_test.py b/cognee/tests/unit/modules/retrieval/graph_completion_retriever_context_extension_test.py index 74def2ae7..0e21fe351 100644 --- a/cognee/tests/unit/modules/retrieval/graph_completion_retriever_context_extension_test.py +++ b/cognee/tests/unit/modules/retrieval/graph_completion_retriever_context_extension_test.py @@ -7,7 +7,6 @@ import cognee from cognee.low_level import setup, DataPoint from cognee.tasks.storage import add_data_points from cognee.modules.graph.utils import resolve_edges_to_text -from cognee.infrastructure.databases.exceptions import DatabaseNotCreatedError from cognee.modules.retrieval.graph_completion_context_extension_retriever import ( GraphCompletionContextExtensionRetriever, ) @@ -165,9 +164,6 @@ class TestGraphCompletionWithContextExtensionRetriever: retriever = GraphCompletionContextExtensionRetriever() - with pytest.raises(DatabaseNotCreatedError): - await retriever.get_context("Who works at Figma?") - await setup() context = await retriever.get_context("Who works at Figma?") diff --git a/cognee/tests/unit/modules/retrieval/graph_completion_retriever_cot_test.py b/cognee/tests/unit/modules/retrieval/graph_completion_retriever_cot_test.py index 9a789a1bd..206cfaf84 100644 --- a/cognee/tests/unit/modules/retrieval/graph_completion_retriever_cot_test.py +++ b/cognee/tests/unit/modules/retrieval/graph_completion_retriever_cot_test.py @@ -7,7 +7,6 @@ import cognee from cognee.low_level import setup, DataPoint from cognee.modules.graph.utils import resolve_edges_to_text from cognee.tasks.storage import add_data_points -from cognee.infrastructure.databases.exceptions import DatabaseNotCreatedError from cognee.modules.retrieval.graph_completion_cot_retriever import GraphCompletionCotRetriever @@ -158,9 +157,6 @@ class TestGraphCompletionCoTRetriever: retriever = GraphCompletionCotRetriever() - with pytest.raises(DatabaseNotCreatedError): - await retriever.get_context("Who works at Figma?") - await setup() context = await retriever.get_context("Who works at Figma?") diff --git a/cognee/tests/unit/modules/retrieval/graph_completion_retriever_test.py b/cognee/tests/unit/modules/retrieval/graph_completion_retriever_test.py index 18fd94114..f462baced 100644 --- a/cognee/tests/unit/modules/retrieval/graph_completion_retriever_test.py +++ b/cognee/tests/unit/modules/retrieval/graph_completion_retriever_test.py @@ -7,7 +7,6 @@ import cognee from cognee.low_level import setup, DataPoint from cognee.modules.graph.utils import resolve_edges_to_text from cognee.tasks.storage import add_data_points -from cognee.infrastructure.databases.exceptions import DatabaseNotCreatedError from cognee.modules.retrieval.graph_completion_retriever import GraphCompletionRetriever @@ -218,9 +217,6 @@ class TestGraphCompletionRetriever: retriever = GraphCompletionRetriever() - with pytest.raises(DatabaseNotCreatedError): - await retriever.get_context("Who works at Figma?") - await setup() context = await retriever.get_context("Who works at Figma?") diff --git a/examples/python/graphiti_example.py b/examples/python/graphiti_example.py index f3bd86847..ece9c452b 100644 --- a/examples/python/graphiti_example.py +++ b/examples/python/graphiti_example.py @@ -48,7 +48,6 @@ async def main(): query = "When was Kamala Harris in office?" triplets = await brute_force_triplet_search( query=query, - user=user, top_k=3, collections=["graphitinode_content", "graphitinode_name", "graphitinode_summary"], ) diff --git a/examples/python/relational_database_migration_example.py b/examples/python/relational_database_migration_example.py index fae8cfb3d..6a5c3b78b 100644 --- a/examples/python/relational_database_migration_example.py +++ b/examples/python/relational_database_migration_example.py @@ -1,16 +1,15 @@ +from pathlib import Path import asyncio - -import cognee import os +import cognee +from cognee.infrastructure.databases.relational.config import get_migration_config from cognee.infrastructure.databases.graph import get_graph_engine from cognee.api.v1.visualize.visualize import visualize_graph from cognee.infrastructure.databases.relational import ( get_migration_relational_engine, ) - from cognee.modules.search.types import SearchType - from cognee.infrastructure.databases.relational import ( create_db_and_tables as create_relational_db_and_tables, ) @@ -32,16 +31,29 @@ from cognee.infrastructure.databases.vector.pgvector import ( async def main(): - engine = get_migration_relational_engine() - # Clean all data stored in Cognee await cognee.prune.prune_data() await cognee.prune.prune_system(metadata=True) - # Needed to create appropriate tables only on the Cognee side + # Needed to create appropriate database tables only on the Cognee side await create_relational_db_and_tables() await create_vector_db_and_tables() + # In case environment variables are not set use the example database from the Cognee repo + migration_db_provider = os.environ.get("MIGRATION_DB_PROVIDER", "sqlite") + migration_db_path = os.environ.get( + "MIGRATION_DB_PATH", + os.path.join(Path(__file__).resolve().parent.parent.parent, "cognee/tests/test_data"), + ) + migration_db_name = os.environ.get("MIGRATION_DB_NAME", "migration_database.sqlite") + + migration_config = get_migration_config() + migration_config.migration_db_provider = migration_db_provider + migration_config.migration_db_path = migration_db_path + migration_config.migration_db_name = migration_db_name + + engine = get_migration_relational_engine() + print("\nExtracting schema of database to migrate.") schema = await engine.extract_schema() print(f"Migrated database schema:\n{schema}") @@ -53,10 +65,6 @@ async def main(): await migrate_relational_database(graph, schema=schema) print("Relational database migration complete.") - # Define location where to store html visualization of graph of the migrated database - home_dir = os.path.expanduser("~") - destination_file_path = os.path.join(home_dir, "graph_visualization.html") - # Make sure to set top_k at a high value for a broader search, the default value is only 10! # top_k represent the number of graph tripplets to supply to the LLM to answer your question search_results = await cognee.search( @@ -69,13 +77,25 @@ async def main(): # Having a top_k value set to too high might overwhelm the LLM context when specific questions need to be answered. # For this kind of question we've set the top_k to 30 search_results = await cognee.search( - query_type=SearchType.GRAPH_COMPLETION_COT, + query_type=SearchType.GRAPH_COMPLETION, query_text="What invoices are related to Leonie Köhler?", top_k=30, ) print(f"Search results: {search_results}") - # test.html is a file with visualized data migration + search_results = await cognee.search( + query_type=SearchType.GRAPH_COMPLETION, + query_text="What invoices are related to Luís Gonçalves?", + top_k=30, + ) + print(f"Search results: {search_results}") + + # If you check the relational database for this example you can see that the search results successfully found all + # the invoices related to the two customers, without any hallucinations or additional information + + # Define location where to store html visualization of graph of the migrated database + home_dir = os.path.expanduser("~") + destination_file_path = os.path.join(home_dir, "graph_visualization.html") print("Adding html visualization of graph database after migration.") await visualize_graph(destination_file_path) print(f"Visualization can be found at: {destination_file_path}") diff --git a/examples/start_ui_example.py b/examples/start_ui_example.py index 55796727b..1fb29d239 100644 --- a/examples/start_ui_example.py +++ b/examples/start_ui_example.py @@ -29,8 +29,11 @@ async def main(): print("=" * 60) # Start the UI server + def dummy_callback(pid): + pass + server = cognee.start_ui( - host="localhost", + pid_callback=dummy_callback, port=3000, open_browser=True, # This will automatically open your browser ) diff --git a/poetry.lock b/poetry.lock index b8cbdc95d..d88b94e5d 100644 --- a/poetry.lock +++ b/poetry.lock @@ -4,9 +4,10 @@ name = "aiobotocore" version = "2.24.2" description = "Async client for aws services using botocore and aiohttp" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"aws\"" files = [ {file = "aiobotocore-2.24.2-py3-none-any.whl", hash = "sha256:808c63b2bd344b91e2f2acb874831118a9f53342d248acd16a68455a226e283a"}, {file = "aiobotocore-2.24.2.tar.gz", hash = "sha256:dfb21bdb2610e8de4d22f401e91a24d50f1330a302d03c62c485757becd439a9"}, @@ -164,9 +165,10 @@ speedups = ["Brotli ; platform_python_implementation == \"CPython\"", "aiodns (> name = "aioitertools" version = "0.12.0" description = "itertools and builtins for AsyncIO and mixed iterables" -optional = false +optional = true python-versions = ">=3.8" groups = ["main"] +markers = "extra == \"aws\"" files = [ {file = "aioitertools-0.12.0-py3-none-any.whl", hash = "sha256:fc1f5fac3d737354de8831cbba3eb04f79dd649d8f3afb4c5b114925e662a796"}, {file = "aioitertools-0.12.0.tar.gz", hash = "sha256:c2a9055b4fbb7705f561b9d86053e8af5d10cc845d22c32008c43490b2d8dd6b"}, @@ -576,9 +578,10 @@ dev = ["backports.zoneinfo ; python_version < \"3.9\"", "freezegun (>=1.0,<2.0)" name = "backoff" version = "2.2.1" description = "Function decoration for backoff and retry" -optional = false +optional = true python-versions = ">=3.7,<4.0" groups = ["main"] +markers = "extra == \"deepeval\" or extra == \"posthog\" or extra == \"chromadb\" or extra == \"docs\" or extra == \"monitoring\"" files = [ {file = "backoff-2.2.1-py3-none-any.whl", hash = "sha256:63579f9a0628e06278f7e47b7d7d5b6ce20dc65c5e96a6f3ca99a6adca0396e8"}, {file = "backoff-2.2.1.tar.gz", hash = "sha256:03f829f5bb1923180821643f8753b0502c3b682293992485b0eef2807afa5cba"}, @@ -609,9 +612,10 @@ extras = ["regex"] name = "baml-py" version = "0.206.0" description = "BAML python bindings (pyproject.toml)" -optional = false +optional = true python-versions = "*" groups = ["main"] +markers = "extra == \"baml\"" files = [ {file = "baml_py-0.206.0-cp38-abi3-macosx_10_12_x86_64.whl", hash = "sha256:d9e95f0b481a18ae6936d720b8fc609baec4ea1eabbdde48f1536ffc94ebf39f"}, {file = "baml_py-0.206.0-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:0f698127da030b728c7aa2641c3164a3ab19779594019234361dd48f0784f195"}, @@ -759,9 +763,10 @@ css = ["tinycss2 (>=1.1.0,<1.5)"] name = "boto3" version = "1.40.18" description = "The AWS SDK for Python" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"neptune\" or extra == \"aws\"" files = [ {file = "boto3-1.40.18-py3-none-any.whl", hash = "sha256:daa776ba1251a7458c9d6c7627873d0c2460c8e8272d35759065580e9193700a"}, {file = "boto3-1.40.18.tar.gz", hash = "sha256:64301d39adecc154e3e595eaf0d4f28998ef0a5551f1d033aeac51a9e1a688e5"}, @@ -779,9 +784,10 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"] name = "botocore" version = "1.40.18" description = "Low-level, data-driven core of boto 3." -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"neptune\" or extra == \"aws\"" files = [ {file = "botocore-1.40.18-py3-none-any.whl", hash = "sha256:57025c46ca00cf8cec25de07a759521bfbfb3036a0f69b272654a354615dc45f"}, {file = "botocore-1.40.18.tar.gz", hash = "sha256:afd69bdadd8c55cc89d69de0799829e555193a352d87867f746e19020271cc0f"}, @@ -945,9 +951,10 @@ pycparser = {version = "*", markers = "implementation_name != \"PyPy\""} name = "cfgv" version = "3.4.0" description = "Validate configuration and produce human readable error messages." -optional = false +optional = true python-versions = ">=3.8" groups = ["main"] +markers = "extra == \"dev\"" files = [ {file = "cfgv-3.4.0-py2.py3-none-any.whl", hash = "sha256:b7265b1f29fd3316bfcd2b330d63d024f2bfd8bcb8b0272f8e19a504856c48f9"}, {file = "cfgv-3.4.0.tar.gz", hash = "sha256:e52591d4c5f5dead8e0f673fb16db7949d2cfb3f7da4582893288f0ded8fe560"}, @@ -1150,7 +1157,7 @@ description = "Cross-platform colored terminal text." optional = false python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7" groups = ["main"] -markers = "(platform_system == \"Windows\" or sys_platform == \"win32\" or os_name == \"nt\" or extra == \"llama-index\" or extra == \"dev\") and (platform_system == \"Windows\" or sys_platform == \"win32\" or extra == \"llama-index\" or extra == \"dev\" or extra == \"chromadb\") and (platform_system == \"Windows\" or python_version <= \"3.12\" or extra == \"notebook\" or extra == \"dev\" or extra == \"llama-index\" or extra == \"deepeval\" or extra == \"chromadb\") and (platform_system == \"Windows\" or extra == \"notebook\" or extra == \"dev\" or extra == \"llama-index\" or extra == \"deepeval\" or extra == \"chromadb\" or extra == \"codegraph\")" +markers = "(platform_system == \"Windows\" or sys_platform == \"win32\" or extra == \"llama-index\" or extra == \"dev\" or os_name == \"nt\") and (platform_system == \"Windows\" or sys_platform == \"win32\" or extra == \"llama-index\" or extra == \"dev\" or extra == \"chromadb\")" files = [ {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"}, {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"}, @@ -1194,10 +1201,10 @@ test = ["pytest"] name = "contourpy" version = "1.3.2" description = "Python library for calculating contours of 2D quadrilateral grids" -optional = false +optional = true python-versions = ">=3.10" groups = ["main"] -markers = "python_version == \"3.10\"" +markers = "python_version == \"3.10\" and extra == \"evals\"" files = [ {file = "contourpy-1.3.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ba38e3f9f330af820c4b27ceb4b9c7feee5fe0493ea53a8720f4792667465934"}, {file = "contourpy-1.3.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:dc41ba0714aa2968d1f8674ec97504a8f7e334f48eeacebcaa6256213acb0989"}, @@ -1272,10 +1279,10 @@ test-no-images = ["pytest", "pytest-cov", "pytest-rerunfailures", "pytest-xdist" name = "contourpy" version = "1.3.3" description = "Python library for calculating contours of 2D quadrilateral grids" -optional = false +optional = true python-versions = ">=3.11" groups = ["main"] -markers = "python_version >= \"3.11\"" +markers = "python_version >= \"3.11\" and extra == \"evals\"" files = [ {file = "contourpy-1.3.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:709a48ef9a690e1343202916450bc48b9e51c049b089c7f79a267b46cffcdaa1"}, {file = "contourpy-1.3.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:23416f38bfd74d5d28ab8429cc4d63fa67d5068bd711a85edb1c3fb0c3e2f381"}, @@ -1576,9 +1583,10 @@ files = [ name = "cycler" version = "0.12.1" description = "Composable style cycles" -optional = false +optional = true python-versions = ">=3.8" groups = ["main"] +markers = "extra == \"evals\"" files = [ {file = "cycler-0.12.1-py3-none-any.whl", hash = "sha256:85cef7cff222d8644161529808465972e51340599459b8ac3ccbac5a854e0d30"}, {file = "cycler-0.12.1.tar.gz", hash = "sha256:88bb128f02ba341da8ef447245a9e138fae777f6a23943da4540077d3601eb1c"}, @@ -1847,9 +1855,10 @@ files = [ name = "distlib" version = "0.4.0" description = "Distribution utilities" -optional = false +optional = true python-versions = "*" groups = ["main"] +markers = "extra == \"dev\"" files = [ {file = "distlib-0.4.0-py2.py3-none-any.whl", hash = "sha256:9659f7d87e46584a30b5780e43ac7a2143098441670ff0a49d5f9034c54a6c16"}, {file = "distlib-0.4.0.tar.gz", hash = "sha256:feec40075be03a04501a973d81f633735b4b69f98b05450592310c0f401a4e0d"}, @@ -1871,9 +1880,10 @@ files = [ name = "dlt" version = "1.16.0" description = "dlt is an open-source python-first scalable data loading library that does not require any backend to run." -optional = false +optional = true python-versions = "<3.15,>=3.9.2" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "dlt-1.16.0-py3-none-any.whl", hash = "sha256:882ef281bbdc32eaba3b5ced984a8ed7014d8978fd7ab4a58b198023c8938c9f"}, {file = "dlt-1.16.0.tar.gz", hash = "sha256:113d17a3f27aa4f41c3438b0b032a68d30db195d8415a471ba43a9502e971a21"}, @@ -2178,10 +2188,9 @@ sqlalchemy = {version = ">=2.0.0,<2.1.0", extras = ["asyncio"]} name = "fastembed" version = "0.6.0" description = "Fast, light, accurate library built for retrieval embedding generation" -optional = true +optional = false python-versions = ">=3.9.0" groups = ["main"] -markers = "extra == \"codegraph\" and python_version <= \"3.12\"" files = [ {file = "fastembed-0.6.0-py3-none-any.whl", hash = "sha256:a08385e9388adea0529a586004f2d588c9787880a510e4e5d167127a11e75328"}, {file = "fastembed-0.6.0.tar.gz", hash = "sha256:5c9ead25f23449535b07243bbe1f370b820dcc77ec2931e61674e3fe7ff24733"}, @@ -2194,8 +2203,12 @@ mmh3 = ">=4.1.0,<6.0.0" numpy = [ {version = ">=1.21", markers = "python_version >= \"3.10\" and python_version < \"3.12\""}, {version = ">=1.26", markers = "python_version == \"3.12\""}, + {version = ">=2.1.0", markers = "python_version >= \"3.13\""}, +] +onnxruntime = [ + {version = ">=1.17.0,<1.20.0 || >1.20.0", markers = "python_version >= \"3.10\" and python_version < \"3.13\""}, + {version = ">1.20.0", markers = "python_version >= \"3.13\""}, ] -onnxruntime = {version = ">=1.17.0,<1.20.0 || >1.20.0", markers = "python_version >= \"3.10\" and python_version < \"3.13\""} pillow = ">=10.3.0,<12.0.0" py-rust-stemmers = ">=0.1.0,<0.2.0" requests = ">=2.31,<3.0" @@ -2241,6 +2254,7 @@ files = [ {file = "fastuuid-0.12.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b9b31dd488d0778c36f8279b306dc92a42f16904cba54acca71e107d65b60b0c"}, {file = "fastuuid-0.12.0-cp313-cp313-manylinux_2_34_x86_64.whl", hash = "sha256:b19361ee649365eefc717ec08005972d3d1eb9ee39908022d98e3bfa9da59e37"}, {file = "fastuuid-0.12.0-cp313-cp313-win_amd64.whl", hash = "sha256:8fc66b11423e6f3e1937385f655bedd67aebe56a3dcec0cb835351cfe7d358c9"}, + {file = "fastuuid-0.12.0-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:2925f67b88d47cb16aa3eb1ab20fdcf21b94d74490e0818c91ea41434b987493"}, {file = "fastuuid-0.12.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:7b15c54d300279ab20a9cc0579ada9c9f80d1bc92997fc61fb7bf3103d7cb26b"}, {file = "fastuuid-0.12.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:458f1bc3ebbd76fdb89ad83e6b81ccd3b2a99fa6707cd3650b27606745cfb170"}, {file = "fastuuid-0.12.0-cp38-cp38-manylinux_2_34_x86_64.whl", hash = "sha256:a8f0f83fbba6dc44271a11b22e15838641b8c45612cdf541b4822a5930f6893c"}, @@ -2292,9 +2306,10 @@ files = [ name = "fonttools" version = "4.60.0" description = "Tools to manipulate font files" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"evals\"" files = [ {file = "fonttools-4.60.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:151282a235c36024168c21c02193e939e8b28c73d5fa0b36ae1072671d8fa134"}, {file = "fonttools-4.60.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:3f32cc42d485d9b1546463b9a7a92bdbde8aef90bac3602503e04c2ddb27e164"}, @@ -2581,9 +2596,10 @@ dev = ["flake8", "markdown", "twine", "wheel"] name = "gitdb" version = "4.0.12" description = "Git Object Database" -optional = false +optional = true python-versions = ">=3.7" groups = ["main"] +markers = "extra == \"dlt\" or extra == \"dev\"" files = [ {file = "gitdb-4.0.12-py3-none-any.whl", hash = "sha256:67073e15955400952c6565cc3e707c554a4eea2e428946f7a4c162fab9bd9bcf"}, {file = "gitdb-4.0.12.tar.gz", hash = "sha256:5ef71f855d191a3326fcfbc0d5da835f26b13fbcba60c32c21091c349ffdb571"}, @@ -2596,9 +2612,10 @@ smmap = ">=3.0.1,<6" name = "gitpython" version = "3.1.45" description = "GitPython is a Python library used to interact with Git repositories" -optional = false +optional = true python-versions = ">=3.7" groups = ["main"] +markers = "extra == \"dlt\" or extra == \"dev\"" files = [ {file = "gitpython-3.1.45-py3-none-any.whl", hash = "sha256:8908cb2e02fb3b93b7eb0f2827125cb699869470432cc885f019b8fd0fccff77"}, {file = "gitpython-3.1.45.tar.gz", hash = "sha256:85b0ee964ceddf211c41b9f27a49086010a190fd8132a24e21f362a4b36a791c"}, @@ -2615,9 +2632,10 @@ test = ["coverage[toml]", "ddt (>=1.1.1,!=1.4.3)", "mock ; python_version < \"3. name = "giturlparse" version = "0.12.0" description = "A Git URL parsing module (supports parsing and rewriting)" -optional = false +optional = true python-versions = ">=3.8" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "giturlparse-0.12.0-py2.py3-none-any.whl", hash = "sha256:412b74f2855f1da2fefa89fd8dde62df48476077a72fc19b62039554d27360eb"}, {file = "giturlparse-0.12.0.tar.gz", hash = "sha256:c0fff7c21acc435491b1779566e038757a205c1ffdcb47e4f81ea52ad8c3859a"}, @@ -3110,9 +3128,10 @@ hyperframe = ">=6.1,<7" name = "hexbytes" version = "1.3.1" description = "hexbytes: Python `bytes` subclass that decodes hex, with a readable console output" -optional = false +optional = true python-versions = "<4,>=3.8" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "hexbytes-1.3.1-py3-none-any.whl", hash = "sha256:da01ff24a1a9a2b1881c4b85f0e9f9b0f51b526b379ffa23832ae7899d29c2c7"}, {file = "hexbytes-1.3.1.tar.gz", hash = "sha256:a657eebebdfe27254336f98d8af6e2236f3f83aed164b87466b6cf6c5f5a4765"}, @@ -3371,9 +3390,10 @@ pyreadline3 = {version = "*", markers = "sys_platform == \"win32\" and python_ve name = "humanize" version = "4.13.0" description = "Python humanize utilities" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "humanize-4.13.0-py3-none-any.whl", hash = "sha256:b810820b31891813b1673e8fec7f1ed3312061eab2f26e3fa192c393d11ed25f"}, {file = "humanize-4.13.0.tar.gz", hash = "sha256:78f79e68f76f0b04d711c4e55d32bebef5be387148862cb1ef83d2b58e7935a0"}, @@ -3399,9 +3419,10 @@ files = [ name = "identify" version = "2.6.14" description = "File identification library for Python" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"dev\"" files = [ {file = "identify-2.6.14-py2.py3-none-any.whl", hash = "sha256:11a073da82212c6646b1f39bb20d4483bfb9543bd5566fec60053c4bb309bf2e"}, {file = "identify-2.6.14.tar.gz", hash = "sha256:663494103b4f717cb26921c52f8751363dc89db64364cd836a9bf1535f53cd6a"}, @@ -3834,9 +3855,10 @@ files = [ name = "jmespath" version = "1.0.1" description = "JSON Matching Expressions" -optional = false +optional = true python-versions = ">=3.7" groups = ["main"] +markers = "extra == \"neptune\" or extra == \"aws\"" files = [ {file = "jmespath-1.0.1-py3-none-any.whl", hash = "sha256:02e2e4cc71b5bcab88332eebf907519190dd9e6e82107fa7f83b1003a6252980"}, {file = "jmespath-1.0.1.tar.gz", hash = "sha256:90261b206d6defd58fdd5e85f478bf633a2901798906be2ad389150c5c60edbe"}, @@ -3846,9 +3868,10 @@ files = [ name = "joblib" version = "1.5.2" description = "Lightweight pipelining with Python functions" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"llama-index\" or extra == \"docs\" or extra == \"evals\"" files = [ {file = "joblib-1.5.2-py3-none-any.whl", hash = "sha256:4e1f0bdbb987e6d843c70cf43714cb276623def372df3c22fe5266b2670bc241"}, {file = "joblib-1.5.2.tar.gz", hash = "sha256:3faa5c39054b2f03ca547da9b2f52fde67c06240c31853f306aea97f13647b55"}, @@ -3902,9 +3925,10 @@ jsonpointer = ">=1.9" name = "jsonpath-ng" version = "1.7.0" description = "A final implementation of JSONPath for Python that aims to be standard compliant, including arithmetic and binary comparison operators and providing clear AST for metaprogramming." -optional = false +optional = true python-versions = "*" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "jsonpath-ng-1.7.0.tar.gz", hash = "sha256:f6f5f7fd4e5ff79c785f1573b394043b39849fb2bb47bcead935d12b00beab3c"}, ] @@ -4212,9 +4236,10 @@ test = ["hatch", "ipykernel", "openapi-core (>=0.18.0,<0.19.0)", "openapi-spec-v name = "kiwisolver" version = "1.4.9" description = "A fast implementation of the Cassowary constraint solver" -optional = false +optional = true python-versions = ">=3.10" groups = ["main"] +markers = "extra == \"evals\"" files = [ {file = "kiwisolver-1.4.9-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:b4b4d74bda2b8ebf4da5bd42af11d02d04428b2c32846e4c2c93219df8a7987b"}, {file = "kiwisolver-1.4.9-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:fb3b8132019ea572f4611d770991000d7f58127560c4889729248eb5852a102f"}, @@ -4555,9 +4580,10 @@ six = "*" name = "langfuse" version = "2.60.10" description = "A client library for accessing langfuse" -optional = false +optional = true python-versions = "<4.0,>=3.9" groups = ["main"] +markers = "extra == \"monitoring\"" files = [ {file = "langfuse-2.60.10-py3-none-any.whl", hash = "sha256:815c6369194aa5b2a24f88eb9952f7c3fc863272c41e90642a71f3bc76f4a11f"}, {file = "langfuse-2.60.10.tar.gz", hash = "sha256:a26d0d927a28ee01b2d12bb5b862590b643cc4e60a28de6e2b0c2cfff5dbfc6a"}, @@ -4776,10 +4802,9 @@ server = ["starlette (>=0.39.0)", "uvicorn (>=0.32.0)"] name = "loguru" version = "0.7.3" description = "Python logging made (stupidly) simple" -optional = true +optional = false python-versions = "<4.0,>=3.5" groups = ["main"] -markers = "extra == \"codegraph\" and python_version <= \"3.12\"" files = [ {file = "loguru-0.7.3-py3-none-any.whl", hash = "sha256:31a33c10c8e1e10422bfd431aeb5d351c7cf7fa671e3c4df004162264b28220c"}, {file = "loguru-0.7.3.tar.gz", hash = "sha256:19480589e77d47b8d85b2c827ad95d49bf31b0dcde16593892eb51dd18706eb6"}, @@ -5130,9 +5155,10 @@ tests = ["pytest", "simplejson"] name = "matplotlib" version = "3.10.6" description = "Python plotting package" -optional = false +optional = true python-versions = ">=3.10" groups = ["main"] +markers = "extra == \"evals\"" files = [ {file = "matplotlib-3.10.6-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:bc7316c306d97463a9866b89d5cc217824e799fa0de346c8f68f4f3d27c8693d"}, {file = "matplotlib-3.10.6-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d00932b0d160ef03f59f9c0e16d1e3ac89646f7785165ce6ad40c842db16cc2e"}, @@ -5491,10 +5517,9 @@ mkdocstrings = ">=0.26" name = "mmh3" version = "5.2.0" description = "Python extension for MurmurHash (MurmurHash3), a set of fast and robust hash functions." -optional = true +optional = false python-versions = ">=3.9" groups = ["main"] -markers = "(extra == \"codegraph\" or extra == \"chromadb\") and (python_version <= \"3.12\" or extra == \"chromadb\")" files = [ {file = "mmh3-5.2.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:81c504ad11c588c8629536b032940f2a359dda3b6cbfd4ad8f74cb24dcd1b0bc"}, {file = "mmh3-5.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0b898cecff57442724a0f52bf42c2de42de63083a91008fb452887e372f9c328"}, @@ -6092,9 +6117,10 @@ test-extras = ["pytest-mpl", "pytest-randomly"] name = "nltk" version = "3.9.1" description = "Natural Language Toolkit" -optional = false +optional = true python-versions = ">=3.8" groups = ["main"] +markers = "extra == \"llama-index\" or extra == \"docs\"" files = [ {file = "nltk-3.9.1-py3-none-any.whl", hash = "sha256:4fa26829c5b00715afe3061398a8989dc643b92ce7dd93fb4585a70930d168a1"}, {file = "nltk-3.9.1.tar.gz", hash = "sha256:87d127bd3de4bd89a4f81265e5fa59cb1b199b27440175370f7417d2bc7ae868"}, @@ -6118,9 +6144,10 @@ twitter = ["twython"] name = "nodeenv" version = "1.9.1" description = "Node.js virtual environment builder" -optional = false +optional = true python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7" groups = ["main"] +markers = "extra == \"dev\"" files = [ {file = "nodeenv-1.9.1-py2.py3-none-any.whl", hash = "sha256:ba11c9782d29c27c70ffbdda2d7415098754709be8a7056d79a737cd901155c9"}, {file = "nodeenv-1.9.1.tar.gz", hash = "sha256:6ec12890a2dab7946721edbfbcd91f3319c6ccc9aec47be7c7e6b7011ee6645f"}, @@ -6644,10 +6671,10 @@ test = ["pytest (>=8.3.0,<8.4.0)", "pytest-benchmark (>=5.1.0,<5.2.0)", "pytest- name = "orjson" version = "3.11.3" description = "Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] -markers = "(sys_platform != \"emscripten\" or platform_python_implementation != \"PyPy\" or extra == \"chromadb\") and (sys_platform != \"emscripten\" or extra == \"neptune\" or extra == \"langchain\" or extra == \"chromadb\")" +markers = "(sys_platform != \"emscripten\" or platform_python_implementation != \"PyPy\" or extra == \"chromadb\") and (sys_platform != \"emscripten\" or extra == \"neptune\" or extra == \"langchain\" or extra == \"chromadb\") and (platform_python_implementation != \"PyPy\" or extra == \"chromadb\" or extra == \"dlt\") and (extra == \"neptune\" or extra == \"langchain\" or extra == \"chromadb\" or extra == \"dlt\")" files = [ {file = "orjson-3.11.3-cp310-cp310-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:29cb1f1b008d936803e2da3d7cba726fc47232c45df531b29edf0b232dd737e7"}, {file = "orjson-3.11.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:97dceed87ed9139884a55db8722428e27bd8452817fbf1869c58b49fecab1120"}, @@ -6779,9 +6806,10 @@ lint = ["black"] name = "pandas" version = "2.3.2" description = "Powerful data structures for data analysis, time series, and statistics" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"docs\" or extra == \"evals\"" files = [ {file = "pandas-2.3.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:52bc29a946304c360561974c6542d1dd628ddafa69134a7131fdfd6a5d7a1a35"}, {file = "pandas-2.3.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:220cc5c35ffaa764dd5bb17cf42df283b5cb7fdf49e10a7b053a06c9cb48ee2b"}, @@ -6909,9 +6937,10 @@ files = [ name = "pathvalidate" version = "3.3.1" description = "pathvalidate is a Python library to sanitize/validate a string such as filenames/file-paths/etc." -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "pathvalidate-3.3.1-py3-none-any.whl", hash = "sha256:5263baab691f8e1af96092fa5137ee17df5bdfbd6cff1fcac4d6ef4bc2e1735f"}, {file = "pathvalidate-3.3.1.tar.gz", hash = "sha256:b18c07212bfead624345bb8e1d6141cdcf15a39736994ea0b94035ad2b1ba177"}, @@ -6926,9 +6955,10 @@ test = ["Faker (>=1.0.8)", "allpairspy (>=2)", "click (>=6.2)", "pytest (>=6.0.1 name = "pendulum" version = "3.1.0" description = "Python datetimes made easy" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "pendulum-3.1.0-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:aa545a59e6517cf43597455a6fb44daa4a6e08473d67a7ad34e4fa951efb9620"}, {file = "pendulum-3.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:299df2da6c490ede86bb8d58c65e33d7a2a42479d21475a54b467b03ccb88531"}, @@ -7206,9 +7236,10 @@ kaleido = ["kaleido (>=1.0.0)"] name = "pluggy" version = "1.6.0" description = "plugin and hook calling mechanisms for python" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"deepeval\" or extra == \"dev\" or extra == \"dlt\"" files = [ {file = "pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746"}, {file = "pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3"}, @@ -7222,9 +7253,10 @@ testing = ["coverage", "pytest", "pytest-benchmark"] name = "ply" version = "3.11" description = "Python Lex & Yacc" -optional = false +optional = true python-versions = "*" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "ply-3.11-py2.py3-none-any.whl", hash = "sha256:096f9b8350b65ebd2fd1346b12452efe5b9607f7482813ffca50c22722a807ce"}, {file = "ply-3.11.tar.gz", hash = "sha256:00c7c1aaa88358b9c765b6d3000c6eec0ba42abca5351b095321aef446081da3"}, @@ -7297,9 +7329,10 @@ test = ["anthropic", "coverage", "django", "flake8", "freezegun (==1.5.1)", "lan name = "pre-commit" version = "4.3.0" description = "A framework for managing and maintaining multi-language pre-commit hooks." -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"dev\"" files = [ {file = "pre_commit-4.3.0-py2.py3-none-any.whl", hash = "sha256:2b0747ad7e6e967169136edffee14c16e148a778a54e4f967921aa1ebf2308d8"}, {file = "pre_commit-4.3.0.tar.gz", hash = "sha256:499fe450cc9d42e9d58e606262795ecb64dd05438943c62b66f6a8673da30b16"}, @@ -7667,10 +7700,9 @@ bcrypt = ["bcrypt (>=4.1.2,<5)"] name = "py-rust-stemmers" version = "0.1.5" description = "Fast and parallel snowball stemmer" -optional = true +optional = false python-versions = "*" groups = ["main"] -markers = "extra == \"codegraph\" and python_version <= \"3.12\"" files = [ {file = "py_rust_stemmers-0.1.5-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:bfbd9034ae00419ff2154e33b8f5b4c4d99d1f9271f31ed059e5c7e9fa005844"}, {file = "py_rust_stemmers-0.1.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c7162ae66df2bb0fc39b350c24a049f5f5151c03c046092ba095c2141ec223a2"}, @@ -8268,66 +8300,6 @@ files = [ [package.extras] dev = ["build", "flake8", "mypy", "pytest", "twine"] -[[package]] -name = "pyside6" -version = "6.9.2" -description = "Python bindings for the Qt cross-platform application and UI framework" -optional = true -python-versions = "<3.14,>=3.9" -groups = ["main"] -markers = "extra == \"gui\"" -files = [ - {file = "pyside6-6.9.2-cp39-abi3-macosx_12_0_universal2.whl", hash = "sha256:71245c76bfbe5c41794ffd8546730ec7cc869d4bbe68535639e026e4ef8a7714"}, - {file = "pyside6-6.9.2-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:64a9e2146e207d858e00226f68d7c1b4ab332954742a00dcabb721bb9e4aa0cd"}, - {file = "pyside6-6.9.2-cp39-abi3-manylinux_2_39_aarch64.whl", hash = "sha256:a78fad16241a1f2ed0fa0098cf3d621f591fc75b4badb7f3fa3959c9d861c806"}, - {file = "pyside6-6.9.2-cp39-abi3-win_amd64.whl", hash = "sha256:d1afbf48f9a5612b9ee2dc7c384c1a65c08b5830ba5e7d01f66d82678e5459df"}, - {file = "pyside6-6.9.2-cp39-abi3-win_arm64.whl", hash = "sha256:1499b1d7629ab92119118e2636b4ace836b25e457ddf01003fdca560560b8c0a"}, -] - -[package.dependencies] -PySide6_Addons = "6.9.2" -PySide6_Essentials = "6.9.2" -shiboken6 = "6.9.2" - -[[package]] -name = "pyside6-addons" -version = "6.9.2" -description = "Python bindings for the Qt cross-platform application and UI framework (Addons)" -optional = true -python-versions = "<3.14,>=3.9" -groups = ["main"] -markers = "extra == \"gui\"" -files = [ - {file = "pyside6_addons-6.9.2-cp39-abi3-macosx_12_0_universal2.whl", hash = "sha256:7019fdcc0059626eb1608b361371f4dc8cb7f2d02f066908fd460739ff5a07cd"}, - {file = "pyside6_addons-6.9.2-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:24350e5415317f269e743d1f7b4933fe5f59d90894aa067676c9ce6bfe9e7988"}, - {file = "pyside6_addons-6.9.2-cp39-abi3-manylinux_2_39_aarch64.whl", hash = "sha256:af8dee517de8d336735a6543f7dd496eb580e852c14b4d2304b890e2a29de499"}, - {file = "pyside6_addons-6.9.2-cp39-abi3-win_amd64.whl", hash = "sha256:98d2413904ee4b2b754b077af7875fa6ec08468c01a6628a2c9c3d2cece4874f"}, - {file = "pyside6_addons-6.9.2-cp39-abi3-win_arm64.whl", hash = "sha256:b430cae782ff1a99fb95868043557f22c31b30c94afb9cf73278584e220a2ab6"}, -] - -[package.dependencies] -PySide6_Essentials = "6.9.2" -shiboken6 = "6.9.2" - -[[package]] -name = "pyside6-essentials" -version = "6.9.2" -description = "Python bindings for the Qt cross-platform application and UI framework (Essentials)" -optional = true -python-versions = "<3.14,>=3.9" -groups = ["main"] -markers = "extra == \"gui\"" -files = [ - {file = "pyside6_essentials-6.9.2-cp39-abi3-macosx_12_0_universal2.whl", hash = "sha256:713eb8dcbb016ff10e6fca129c1bf2a0fd8cfac979e689264e0be3b332f9398e"}, - {file = "pyside6_essentials-6.9.2-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:84b8ca4fa56506e2848bdb4c7a0851a5e7adcb916bef9bce25ce2eeb6c7002cc"}, - {file = "pyside6_essentials-6.9.2-cp39-abi3-manylinux_2_39_aarch64.whl", hash = "sha256:d0f701503974bd51b408966539aa6956f3d8536e547ea8002fbfb3d77796bbc3"}, - {file = "pyside6_essentials-6.9.2-cp39-abi3-win_amd64.whl", hash = "sha256:b2f746f795138ac63eb173f9850a6db293461a1b6ce22cf6dafac7d194a38951"}, - {file = "pyside6_essentials-6.9.2-cp39-abi3-win_arm64.whl", hash = "sha256:ecd7b5cd9e271f397fb89a6357f4ec301d8163e50869c6c557f9ccc6bed42789"}, -] - -[package.dependencies] -shiboken6 = "6.9.2" - [[package]] name = "pysocks" version = "1.7.1" @@ -8621,9 +8593,10 @@ XlsxWriter = ">=0.5.7" name = "pytz" version = "2025.2" description = "World timezone definitions, modern and historical" -optional = false +optional = true python-versions = "*" groups = ["main"] +markers = "extra == \"neo4j\" or extra == \"graphiti\" or extra == \"docs\" or extra == \"evals\" or extra == \"dlt\"" files = [ {file = "pytz-2025.2-py2.py3-none-any.whl", hash = "sha256:5ddf76296dd8c44c26eb8f4b6f35488f3ccbf6fbbd7adee0b7262d43f0ec2f00"}, {file = "pytz-2025.2.tar.gz", hash = "sha256:360b9e3dbb49a209c21ad61809c7fb453643e048b38924c765813546746e81c3"}, @@ -8636,7 +8609,7 @@ description = "Python for Window Extensions" optional = false python-versions = "*" groups = ["main"] -markers = "sys_platform == \"win32\" or platform_system == \"Windows\"" +markers = "(sys_platform == \"win32\" or platform_system == \"Windows\") and (platform_python_implementation != \"PyPy\" or platform_system == \"Windows\" or extra == \"dlt\")" files = [ {file = "pywin32-311-cp310-cp310-win32.whl", hash = "sha256:d03ff496d2a0cd4a5893504789d4a15399133fe82517455e78bad62efbb7f0a3"}, {file = "pywin32-311-cp310-cp310-win_amd64.whl", hash = "sha256:797c2772017851984b97180b0bebe4b620bb86328e8a884bb626156295a63b3b"}, @@ -8863,19 +8836,6 @@ files = [ [package.dependencies] cffi = {version = "*", markers = "implementation_name == \"pypy\""} -[[package]] -name = "qasync" -version = "0.27.1" -description = "Python library for using asyncio in Qt-based applications" -optional = true -python-versions = ">=3.8,<4.0" -groups = ["main"] -markers = "extra == \"gui\"" -files = [ - {file = "qasync-0.27.1-py3-none-any.whl", hash = "sha256:5d57335723bc7d9b328dadd8cb2ed7978640e4bf2da184889ce50ee3ad2602c7"}, - {file = "qasync-0.27.1.tar.gz", hash = "sha256:8dc768fd1ee5de1044c7c305eccf2d39d24d87803ea71189d4024fb475f4985f"}, -] - [[package]] name = "rapidfuzz" version = "3.14.1" @@ -9231,9 +9191,10 @@ requests = ">=2.0.1,<3.0.0" name = "requirements-parser" version = "0.13.0" description = "This is a small Python module for parsing Pip requirement files." -optional = false +optional = true python-versions = "<4.0,>=3.8" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "requirements_parser-0.13.0-py3-none-any.whl", hash = "sha256:2b3173faecf19ec5501971b7222d38f04cb45bb9d87d0ad629ca71e2e62ded14"}, {file = "requirements_parser-0.13.0.tar.gz", hash = "sha256:0843119ca2cb2331de4eb31b10d70462e39ace698fd660a915c247d2301a4418"}, @@ -9313,9 +9274,10 @@ jupyter = ["ipywidgets (>=7.5.1,<9)"] name = "rich-argparse" version = "1.7.1" description = "Rich help formatters for argparse and optparse" -optional = false +optional = true python-versions = ">=3.8" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "rich_argparse-1.7.1-py3-none-any.whl", hash = "sha256:a8650b42e4a4ff72127837632fba6b7da40784842f08d7395eb67a9cbd7b4bf9"}, {file = "rich_argparse-1.7.1.tar.gz", hash = "sha256:d7a493cde94043e41ea68fb43a74405fa178de981bf7b800f7a3bd02ac5c27be"}, @@ -9539,9 +9501,10 @@ files = [ name = "s3fs" version = "2025.3.2" description = "Convenient Filesystem interface over S3" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"aws\"" files = [ {file = "s3fs-2025.3.2-py3-none-any.whl", hash = "sha256:81eae3f37b4b04bcc08845d7bcc607c6ca45878813ef7e6a28d77b2688417130"}, {file = "s3fs-2025.3.2.tar.gz", hash = "sha256:6798f896ec76dd3bfd8beb89f0bb7c5263cb2760e038bae0978505cd172a307c"}, @@ -9563,9 +9526,10 @@ boto3 = ["aiobotocore[boto3] (>=2.5.4,<3.0.0)"] name = "s3transfer" version = "0.13.1" description = "An Amazon S3 Transfer Manager" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"neptune\" or extra == \"aws\"" files = [ {file = "s3transfer-0.13.1-py3-none-any.whl", hash = "sha256:a981aa7429be23fe6dfc13e80e4020057cbab622b08c0315288758d67cabc724"}, {file = "s3transfer-0.13.1.tar.gz", hash = "sha256:c3fdba22ba1bd367922f27ec8032d6a1cf5f10c934fb5d68cf60fd5a23d936cf"}, @@ -9621,9 +9585,10 @@ torch = ["safetensors[numpy]", "torch (>=1.10)"] name = "scikit-learn" version = "1.7.2" description = "A set of python modules for machine learning and data mining" -optional = false +optional = true python-versions = ">=3.10" groups = ["main"] +markers = "extra == \"evals\"" files = [ {file = "scikit_learn-1.7.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:6b33579c10a3081d076ab403df4a4190da4f4432d443521674637677dc91e61f"}, {file = "scikit_learn-1.7.2-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:36749fb62b3d961b1ce4fedf08fa57a1986cd409eff2d783bca5d4b9b5fce51c"}, @@ -9677,10 +9642,10 @@ tests = ["matplotlib (>=3.5.0)", "mypy (>=1.15)", "numpydoc (>=1.2.0)", "pandas name = "scipy" version = "1.15.3" description = "Fundamental algorithms for scientific computing in Python" -optional = false +optional = true python-versions = ">=3.10" groups = ["main"] -markers = "python_version == \"3.10\"" +markers = "python_version == \"3.10\" and extra == \"evals\"" files = [ {file = "scipy-1.15.3-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:a345928c86d535060c9c2b25e71e87c39ab2f22fc96e9636bd74d1dbf9de448c"}, {file = "scipy-1.15.3-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:ad3432cb0f9ed87477a8d97f03b763fd1d57709f1bbde3c9369b1dff5503b253"}, @@ -9742,10 +9707,10 @@ test = ["Cython", "array-api-strict (>=2.0,<2.1.1)", "asv", "gmpy2", "hypothesis name = "scipy" version = "1.16.2" description = "Fundamental algorithms for scientific computing in Python" -optional = false +optional = true python-versions = ">=3.11" groups = ["main"] -markers = "python_version >= \"3.11\"" +markers = "python_version >= \"3.11\" and extra == \"evals\"" files = [ {file = "scipy-1.16.2-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:6ab88ea43a57da1af33292ebd04b417e8e2eaf9d5aa05700be8d6e1b6501cd92"}, {file = "scipy-1.16.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:c95e96c7305c96ede73a7389f46ccd6c659c4da5ef1b2789466baeaed3622b6e"}, @@ -9822,9 +9787,10 @@ test = ["Cython", "array-api-strict (>=2.3.1)", "asv", "gmpy2", "hypothesis (>=6 name = "semver" version = "3.0.4" description = "Python helper for Semantic Versioning (https://semver.org)" -optional = false +optional = true python-versions = ">=3.7" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "semver-3.0.4-py3-none-any.whl", hash = "sha256:9c824d87ba7f7ab4a1890799cec8596f15c1241cb473404ea1cb0c55e4b04746"}, {file = "semver-3.0.4.tar.gz", hash = "sha256:afc7d8c584a5ed0a11033af086e8af226a9c0b206f313e0301f8dd7b6b589602"}, @@ -9852,9 +9818,10 @@ win32 = ["pywin32 ; sys_platform == \"win32\""] name = "sentry-sdk" version = "2.38.0" description = "Python client for Sentry (https://sentry.io)" -optional = false +optional = true python-versions = ">=3.6" groups = ["main"] +markers = "extra == \"deepeval\" or extra == \"monitoring\"" files = [ {file = "sentry_sdk-2.38.0-py2.py3-none-any.whl", hash = "sha256:2324aea8573a3fa1576df7fb4d65c4eb8d9929c8fa5939647397a07179eef8d0"}, {file = "sentry_sdk-2.38.0.tar.gz", hash = "sha256:792d2af45e167e2f8a3347143f525b9b6bac6f058fb2014720b40b84ccbeb985"}, @@ -9911,9 +9878,10 @@ unleash = ["UnleashClient (>=6.0.1)"] name = "setuptools" version = "80.9.0" description = "Easily download, build, install, upgrade, and uninstall Python packages" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"notebook\" or extra == \"dev\" or extra == \"llama-index\" or extra == \"deepeval\" or extra == \"dlt\"" files = [ {file = "setuptools-80.9.0-py3-none-any.whl", hash = "sha256:062d34222ad13e0cc312a4c02d73f059e86a4acbfbdea8f8f76b28c99f306922"}, {file = "setuptools-80.9.0.tar.gz", hash = "sha256:f36b47402ecde768dbfafc46e8e4207b4360c654f1f3bb84475f0a28628fb19c"}, @@ -9940,22 +9908,6 @@ files = [ {file = "shellingham-1.5.4.tar.gz", hash = "sha256:8dbca0739d487e5bd35ab3ca4b36e11c4078f3a234bfce294b0a0291363404de"}, ] -[[package]] -name = "shiboken6" -version = "6.9.2" -description = "Python/C++ bindings helper module" -optional = true -python-versions = "<3.14,>=3.9" -groups = ["main"] -markers = "extra == \"gui\"" -files = [ - {file = "shiboken6-6.9.2-cp39-abi3-macosx_12_0_universal2.whl", hash = "sha256:8bb1c4326330e53adeac98bfd9dcf57f5173a50318a180938dcc4825d9ca38da"}, - {file = "shiboken6-6.9.2-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3b54c0a12ea1b03b9dc5dcfb603c366e957dc75341bf7cb1cc436d0d848308ee"}, - {file = "shiboken6-6.9.2-cp39-abi3-manylinux_2_39_aarch64.whl", hash = "sha256:a5f5985938f5acb604c23536a0ff2efb3cccb77d23da91fbaff8fd8ded3dceb4"}, - {file = "shiboken6-6.9.2-cp39-abi3-win_amd64.whl", hash = "sha256:68c33d565cd4732be762d19ff67dfc53763256bac413d392aa8598b524980bc4"}, - {file = "shiboken6-6.9.2-cp39-abi3-win_arm64.whl", hash = "sha256:c5b827797b3d89d9b9a3753371ff533fcd4afc4531ca51a7c696952132098054"}, -] - [[package]] name = "sigtools" version = "4.0.1" @@ -9980,9 +9932,10 @@ tests = ["coverage", "mock", "repeated-test (>=2.2.1)", "sphinx"] name = "simplejson" version = "3.20.1" description = "Simple, fast, extensible JSON encoder/decoder for Python" -optional = false +optional = true python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.5" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "simplejson-3.20.1-cp27-cp27m-manylinux1_i686.whl", hash = "sha256:f5272b5866b259fe6c33c4a8c5073bf8b359c3c97b70c298a2f09a69b52c7c41"}, {file = "simplejson-3.20.1-cp27-cp27m-manylinux1_x86_64.whl", hash = "sha256:5c0de368f3052a59a1acf21f8b2dd28686a9e4eba2da7efae7ed9554cb31e7bc"}, @@ -10112,9 +10065,10 @@ files = [ name = "smmap" version = "5.0.2" description = "A pure Python implementation of a sliding window memory map manager" -optional = false +optional = true python-versions = ">=3.7" groups = ["main"] +markers = "extra == \"dlt\" or extra == \"dev\"" files = [ {file = "smmap-5.0.2-py3-none-any.whl", hash = "sha256:b30115f0def7d7531d22a0fb6502488d879e75b260a9db4d0819cfb25403af5e"}, {file = "smmap-5.0.2.tar.gz", hash = "sha256:26ea65a03958fa0c8a1c7e8c7a58fdc77221b8910f6be2131affade476898ad5"}, @@ -10245,9 +10199,10 @@ sqlcipher = ["sqlcipher3_binary"] name = "sqlglot" version = "27.16.3" description = "An easily customizable SQL parser and transpiler" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"dlt\"" files = [ {file = "sqlglot-27.16.3-py3-none-any.whl", hash = "sha256:3765ef1da6c9a04dd9e9ab4bcf24ca54daae72d86d693954aed84dbbbff2ff3b"}, {file = "sqlglot-27.16.3.tar.gz", hash = "sha256:bf5cc3b7c90c3682365353a318089e69e859939943d7882562ba39be650a6202"}, @@ -10406,9 +10361,10 @@ typing = ["mypy (>=1.6,<2.0)", "traitlets (>=5.11.1)"] name = "threadpoolctl" version = "3.6.0" description = "threadpoolctl" -optional = false +optional = true python-versions = ">=3.9" groups = ["main"] +markers = "extra == \"evals\"" files = [ {file = "threadpoolctl-3.6.0-py3-none-any.whl", hash = "sha256:43a0b8fd5a2928500110039e43a5eed8480b918967083ea48dc3ab9f13c4a7fb"}, {file = "threadpoolctl-3.6.0.tar.gz", hash = "sha256:8ab8b4aa3491d812b623328249fab5302a68d2d71745c8a4c719a2fcaba9f44e"}, @@ -10575,9 +10531,10 @@ files = [ name = "tomlkit" version = "0.13.3" description = "Style preserving TOML library" -optional = false +optional = true python-versions = ">=3.8" groups = ["main"] +markers = "extra == \"dlt\" or extra == \"dev\"" files = [ {file = "tomlkit-0.13.3-py3-none-any.whl", hash = "sha256:c89c649d79ee40629a9fda55f8ace8c6a1b42deb912b2a8fd8d942ddadb606b0"}, {file = "tomlkit-0.13.3.tar.gz", hash = "sha256:430cf247ee57df2b94ee3fbe588e71d362a941ebb545dec29b53961d61add2a1"}, @@ -10914,9 +10871,10 @@ typing-extensions = ">=4.12.0" name = "tzdata" version = "2025.2" description = "Provider of IANA time zone data" -optional = false +optional = true python-versions = ">=2" groups = ["main"] +markers = "extra == \"docs\" or extra == \"evals\" or extra == \"dlt\"" files = [ {file = "tzdata-2025.2-py2.py3-none-any.whl", hash = "sha256:1a403fada01ff9221ca8044d701868fa132215d84beb92242d9acd2147f667a8"}, {file = "tzdata-2025.2.tar.gz", hash = "sha256:b60a638fcc0daffadf82fe0f57e53d06bdec2f36c4df66280ae79bce6bd6f2b9"}, @@ -11157,9 +11115,10 @@ test = ["aiohttp (>=3.10.5)", "flake8 (>=5.0,<6.0)", "mypy (>=0.800)", "psutil", name = "virtualenv" version = "20.34.0" description = "Virtual Python Environment builder" -optional = false +optional = true python-versions = ">=3.8" groups = ["main"] +markers = "extra == \"dev\"" files = [ {file = "virtualenv-20.34.0-py3-none-any.whl", hash = "sha256:341f5afa7eee943e4984a9207c025feedd768baff6753cd660c857ceb3e36026"}, {file = "virtualenv-20.34.0.tar.gz", hash = "sha256:44815b2c9dee7ed86e387b842a84f20b93f7f417f95886ca1996a72a4138eb1a"}, @@ -11495,10 +11454,10 @@ test = ["pytest (>=6.0.0)", "setuptools (>=65)"] name = "win-precise-time" version = "1.4.2" description = "" -optional = false +optional = true python-versions = ">=3.7" groups = ["main"] -markers = "os_name == \"nt\" and python_version <= \"3.12\"" +markers = "extra == \"dlt\" and os_name == \"nt\" and python_version <= \"3.12\"" files = [ {file = "win-precise-time-1.4.2.tar.gz", hash = "sha256:89274785cbc5f2997e01675206da3203835a442c60fd97798415c6b3c179c0b9"}, {file = "win_precise_time-1.4.2-cp310-cp310-win32.whl", hash = "sha256:7fa13a2247c2ef41cd5e9b930f40716eacc7fc1f079ea72853bd5613fe087a1a"}, @@ -11519,10 +11478,10 @@ files = [ name = "win32-setctime" version = "1.2.0" description = "A small Python utility to set file creation time on Windows" -optional = true +optional = false python-versions = ">=3.5" groups = ["main"] -markers = "sys_platform == \"win32\" and extra == \"codegraph\" and python_version <= \"3.12\"" +markers = "sys_platform == \"win32\"" files = [ {file = "win32_setctime-1.2.0-py3-none-any.whl", hash = "sha256:95d644c4e708aba81dc3704a116d8cbc974d70b3bdb8be1d150e36be6e9d1390"}, {file = "win32_setctime-1.2.0.tar.gz", hash = "sha256:ae1fdf948f5640aae05c511ade119313fb6a30d7eabe25fef9764dca5873c4c0"}, @@ -11909,23 +11868,25 @@ cffi = ["cffi (>=1.17,<2.0) ; platform_python_implementation != \"PyPy\" and pyt anthropic = ["anthropic"] api = [] aws = ["s3fs"] +baml = ["baml-py"] chromadb = ["chromadb", "pypika"] codegraph = ["fastembed", "transformers", "tree-sitter", "tree-sitter-python"] debug = ["debugpy"] deepeval = ["deepeval"] -dev = ["coverage", "deptry", "gitpython", "mkdocs-material", "mkdocs-minify-plugin", "mkdocstrings", "mypy", "notebook", "pylint", "pytest", "pytest-asyncio", "pytest-cov", "ruff", "tweepy"] +dev = ["coverage", "deptry", "gitpython", "mkdocs-material", "mkdocs-minify-plugin", "mkdocstrings", "mypy", "notebook", "pre-commit", "pylint", "pytest", "pytest-asyncio", "pytest-cov", "ruff", "tweepy"] distributed = ["modal"] +dlt = ["dlt"] docs = ["unstructured"] -evals = ["gdown", "plotly"] +evals = ["gdown", "matplotlib", "pandas", "plotly", "scikit-learn"] falkordb = ["falkordb"] gemini = ["google-generativeai"] graphiti = ["graphiti-core"] groq = ["groq"] -gui = ["pyside6", "qasync"] huggingface = ["transformers"] langchain = ["langchain_text_splitters", "langsmith"] llama-index = ["llama-index-core"] mistral = ["mistral-common"] +monitoring = ["langfuse", "sentry-sdk"] neo4j = ["neo4j"] neptune = ["langchain_aws"] notebook = ["notebook"] @@ -11937,4 +11898,4 @@ posthog = ["posthog"] [metadata] lock-version = "2.1" python-versions = ">=3.10,<=3.13" -content-hash = "fc32c4e05914cf364d4feb0c3baec9771d149eb65626e5337fa2eb55e7130499" +content-hash = "49d2d5207803b6b56e0bbf2be871941f4fc4535d0bc823815e0a7cbe61e12574" diff --git a/pyproject.toml b/pyproject.toml index c2a6317f3..5c4e7908c 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -20,49 +20,38 @@ classifiers = [ "Operating System :: Microsoft :: Windows", ] dependencies = [ - "openai>=1.80.1,<2.0.0", + "openai>=1.80.1", "python-dotenv>=1.0.1,<2.0.0", "pydantic>=2.10.5,<3.0.0", "pydantic-settings>=2.2.1,<3", "typing_extensions>=4.12.2,<5.0.0", - "nltk>=3.9.1,<4.0.0", "numpy>=1.26.4, <=4.0.0", - "pandas>=2.2.2,<3.0.0", - # Note: New s3fs and boto3 versions don't work well together - # Always use comaptible fixed versions of these two dependencies - "s3fs[boto3]==2025.3.2", "sqlalchemy>=2.0.39,<3.0.0", "aiosqlite>=0.20.0,<1.0.0", "tiktoken>=0.8.0,<1.0.0", - "litellm>=1.71.0, <2.0.0", + "litellm>=1.76.0", "instructor>=1.9.1,<2.0.0", - "langfuse>=2.32.0,<3", "filetype>=1.2.0,<2.0.0", "aiohttp>=3.11.14,<4.0.0", "aiofiles>=23.2.1,<24.0.0", "rdflib>=7.1.4,<7.2.0", "pypdf>=4.1.0,<7.0.0", "jinja2>=3.1.3,<4", - "matplotlib>=3.8.3,<4", - "networkx>=3.4.2,<4", "lancedb>=0.24.0,<1.0.0", "nbformat>=5.7.0,<6.0.0", "alembic>=1.13.3,<2", - "pre-commit>=4.0.1,<5", - "scikit-learn>=1.6.1,<2", "limits>=4.4.1,<5", "fastapi>=0.115.7,<1.0.0", "python-multipart>=0.0.20,<1.0.0", "fastapi-users[sqlalchemy]>=14.0.1,<15.0.0", - "dlt[sqlalchemy]>=1.9.0,<2", - "sentry-sdk[fastapi]>=2.9.0,<3", "structlog>=25.2.0,<26", - "baml-py (==0.206.0)", "pympler>=1.1,<2.0.0", - "onnxruntime>=1.0.0,<2.0.0", - "pylance>=0.22.0,<1.0.0", + "onnxruntime<=1.22.1", + "pylance>=0.22.0,<=0.36.0", "kuzu (==0.11.0)", "python-magic-bin<0.5 ; platform_system == 'Windows'", # Only needed for Windows + "fastembed<=0.6.0", + "networkx>=3.4.2,<4", "uvicorn>=0.34.0,<1.0.0", "gunicorn>=20.1.0,<24", "websockets>=15.0.1,<16.0.0", @@ -71,6 +60,7 @@ dependencies = [ [project.optional-dependencies] api=[] + distributed = [ "modal>=1.0.5,<2.0.0", ] @@ -116,25 +106,28 @@ codegraph = [ evals = [ "plotly>=6.0.0,<7", "gdown>=5.2.0,<6", + "pandas>=2.2.2,<3.0.0", + "matplotlib>=3.8.3,<4", + "scikit-learn>=1.6.1,<2", ] -gui = [ - "pyside6>=6.8.3,<7", - "qasync>=0.27.1,<0.28", -] + graphiti = ["graphiti-core>=0.7.0,<0.8"] # Note: New s3fs and boto3 versions don't work well together # Always use comaptible fixed versions of these two dependencies aws = ["s3fs[boto3]==2025.3.2"] +dlt = ["dlt[sqlalchemy]>=1.9.0,<2"] +baml = ["baml-py (==0.206.0)"] dev = [ "pytest>=7.4.0,<8", "pytest-cov>=6.1.1,<7.0.0", "pytest-asyncio>=0.21.1,<0.22", "coverage>=7.3.2,<8", "mypy>=1.7.1,<2", + "pre-commit>=4.0.1,<5", "notebook>=7.1.0,<8", "deptry>=0.20.0,<0.21", "pylint>=3.0.3,<4", - "ruff>=0.9.2,<1.0.0", + "ruff>=0.9.2,<=0.13.1", "tweepy>=4.14.0,<5.0.0", "gitpython>=3.1.43,<4", "mkdocs-material>=9.5.42,<10", @@ -143,6 +136,8 @@ dev = [ ] debug = ["debugpy>=1.8.9,<2.0.0"] +monitoring = ["sentry-sdk[fastapi]>=2.9.0,<3", "langfuse>=2.32.0,<3"] + [project.urls] Homepage = "https://www.cognee.ai" Repository = "https://github.com/topoteretes/cognee" diff --git a/uv.lock b/uv.lock index be7815d57..e380e5dba 100644 --- a/uv.lock +++ b/uv.lock @@ -2,16 +2,16 @@ version = 1 requires-python = ">=3.10, <=3.13" resolution-markers = [ "python_full_version >= '3.13' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.12.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version < '3.11' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", "python_full_version >= '3.13' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.12.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version < '3.11' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version >= '3.13' and sys_platform == 'emscripten'", + "python_full_version == '3.12.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version == '3.12.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.12.*' and sys_platform == 'emscripten'", + "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.11.*' and sys_platform == 'emscripten'", + "python_full_version < '3.11' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version < '3.11' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version < '3.11' and sys_platform == 'emscripten'", ] @@ -221,7 +221,7 @@ wheels = [ [[package]] name = "anyio" -version = "4.10.0" +version = "4.11.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "exceptiongroup", marker = "python_full_version < '3.11'" }, @@ -229,9 +229,9 @@ dependencies = [ { name = "sniffio" }, { name = "typing-extensions", marker = "python_full_version < '3.13'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/f1/b4/636b3b65173d3ce9a38ef5f0522789614e590dab6a8d505340a4efe4c567/anyio-4.10.0.tar.gz", hash = "sha256:3f3fae35c96039744587aa5b8371e7e8e603c0702999535961dd336026973ba6", size = 213252 } +sdist = { url = "https://files.pythonhosted.org/packages/c6/78/7d432127c41b50bccba979505f272c16cbcadcc33645d5fa3a738110ae75/anyio-4.11.0.tar.gz", hash = "sha256:82a8d0b81e318cc5ce71a5f1f8b5c4e63619620b63141ef8c995fa0db95a57c4", size = 219094, upload-time = "2025-09-23T09:19:12.58Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/6f/12/e5e0282d673bb9746bacfb6e2dba8719989d3660cdb2ea79aee9a9651afb/anyio-4.10.0-py3-none-any.whl", hash = "sha256:60e474ac86736bbfd6f210f7a61218939c318f43f9972497381f1c5e930ed3d1", size = 107213 }, + { url = "https://files.pythonhosted.org/packages/15/b3/9b1a8074496371342ec1e796a96f99c82c945a339cd81a8e73de28b4cf9e/anyio-4.11.0-py3-none-any.whl", hash = "sha256:0287e96f4d26d4149305414d4e3bc32f0dcd0862365a4bddea19d7a1ec38c4fc", size = 109097, upload-time = "2025-09-23T09:19:10.601Z" }, ] [[package]] @@ -296,14 +296,14 @@ wheels = [ [[package]] name = "asgiref" -version = "3.9.1" +version = "3.9.2" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "typing-extensions", marker = "python_full_version < '3.11'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/90/61/0aa957eec22ff70b830b22ff91f825e70e1ef732c06666a805730f28b36b/asgiref-3.9.1.tar.gz", hash = "sha256:a5ab6582236218e5ef1648f242fd9f10626cfd4de8dc377db215d5d5098e3142", size = 36870 } +sdist = { url = "https://files.pythonhosted.org/packages/7f/bf/0f3ecda32f1cb3bf1dca480aca08a7a8a3bdc4bed2343a103f30731565c9/asgiref-3.9.2.tar.gz", hash = "sha256:a0249afacb66688ef258ffe503528360443e2b9a8d8c4581b6ebefa58c841ef1", size = 36894, upload-time = "2025-09-23T15:00:55.136Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/7c/3c/0464dcada90d5da0e71018c04a140ad6349558afb30b3051b4264cc5b965/asgiref-3.9.1-py3-none-any.whl", hash = "sha256:f3bba7092a48005b5f5bacd747d36ee4a5a61f4a269a6df590b43144355ebd2c", size = 23790 }, + { url = "https://files.pythonhosted.org/packages/c7/d1/69d02ce34caddb0a7ae088b84c356a625a93cd4ff57b2f97644c03fad905/asgiref-3.9.2-py3-none-any.whl", hash = "sha256:0b61526596219d70396548fc003635056856dba5d0d086f86476f10b33c75960", size = 23788, upload-time = "2025-09-23T15:00:53.627Z" }, ] [[package]] @@ -821,31 +821,24 @@ dependencies = [ { name = "aiohttp" }, { name = "aiosqlite" }, { name = "alembic" }, - { name = "baml-py" }, - { name = "dlt", extra = ["sqlalchemy"] }, { name = "fastapi" }, { name = "fastapi-users", extra = ["sqlalchemy"] }, + { name = "fastembed" }, { name = "filetype" }, { name = "gunicorn" }, { name = "instructor" }, { name = "jinja2" }, { name = "kuzu" }, { name = "lancedb" }, - { name = "langfuse" }, { name = "limits" }, { name = "litellm" }, - { name = "matplotlib" }, - { name = "mistralai" }, { name = "nbformat" }, { name = "networkx", version = "3.4.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" }, { name = "networkx", version = "3.5", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" }, - { name = "nltk" }, { name = "numpy", version = "1.26.4", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.12'" }, { name = "numpy", version = "2.3.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12'" }, { name = "onnxruntime" }, { name = "openai" }, - { name = "pandas" }, - { name = "pre-commit" }, { name = "pydantic" }, { name = "pydantic-settings" }, { name = "pylance" }, @@ -855,9 +848,6 @@ dependencies = [ { name = "python-magic-bin", marker = "sys_platform == 'win32'" }, { name = "python-multipart" }, { name = "rdflib" }, - { name = "s3fs", extra = ["boto3"] }, - { name = "scikit-learn" }, - { name = "sentry-sdk", extra = ["fastapi"] }, { name = "sqlalchemy" }, { name = "structlog" }, { name = "tiktoken" }, @@ -873,6 +863,9 @@ anthropic = [ aws = [ { name = "s3fs", extra = ["boto3"] }, ] +baml = [ + { name = "baml-py" }, +] chromadb = [ { name = "chromadb" }, { name = "pypika" }, @@ -898,6 +891,7 @@ dev = [ { name = "mkdocstrings", extra = ["python"] }, { name = "mypy" }, { name = "notebook" }, + { name = "pre-commit" }, { name = "pylint" }, { name = "pytest" }, { name = "pytest-asyncio" }, @@ -908,12 +902,18 @@ dev = [ distributed = [ { name = "modal" }, ] +dlt = [ + { name = "dlt", extra = ["sqlalchemy"] }, +] docs = [ { name = "unstructured", extra = ["csv", "doc", "docx", "epub", "md", "odt", "org", "ppt", "pptx", "rst", "rtf", "tsv", "xlsx"] }, ] evals = [ { name = "gdown" }, + { name = "matplotlib" }, + { name = "pandas" }, { name = "plotly" }, + { name = "scikit-learn" }, ] falkordb = [ { name = "falkordb" }, @@ -927,10 +927,6 @@ graphiti = [ groq = [ { name = "groq" }, ] -gui = [ - { name = "pyside6" }, - { name = "qasync" }, -] huggingface = [ { name = "transformers" }, ] @@ -944,6 +940,10 @@ llama-index = [ mistral = [ { name = "mistral-common" }, ] +monitoring = [ + { name = "langfuse" }, + { name = "sentry-sdk", extra = ["fastapi"] }, +] neo4j = [ { name = "neo4j" }, ] @@ -979,16 +979,17 @@ requires-dist = [ { name = "anthropic", marker = "extra == 'anthropic'", specifier = ">=0.27" }, { name = "asyncpg", marker = "extra == 'postgres'", specifier = ">=0.30.0,<1.0.0" }, { name = "asyncpg", marker = "extra == 'postgres-binary'", specifier = ">=0.30.0,<1.0.0" }, - { name = "baml-py", specifier = "==0.206.0" }, + { name = "baml-py", marker = "extra == 'baml'", specifier = "==0.206.0" }, { name = "chromadb", marker = "extra == 'chromadb'", specifier = ">=0.6,<0.7" }, { name = "coverage", marker = "extra == 'dev'", specifier = ">=7.3.2,<8" }, { name = "debugpy", marker = "extra == 'debug'", specifier = ">=1.8.9,<2.0.0" }, { name = "deepeval", marker = "extra == 'deepeval'", specifier = ">=3.0.1,<4" }, { name = "deptry", marker = "extra == 'dev'", specifier = ">=0.20.0,<0.21" }, - { name = "dlt", extras = ["sqlalchemy"], specifier = ">=1.9.0,<2" }, + { name = "dlt", extras = ["sqlalchemy"], marker = "extra == 'dlt'", specifier = ">=1.9.0,<2" }, { name = "falkordb", marker = "extra == 'falkordb'", specifier = ">=1.0.9,<2.0.0" }, { name = "fastapi", specifier = ">=0.115.7,<1.0.0" }, { name = "fastapi-users", extras = ["sqlalchemy"], specifier = ">=14.0.1,<15.0.0" }, + { name = "fastembed", specifier = "<=0.6.0" }, { name = "fastembed", marker = "python_full_version < '3.13' and extra == 'codegraph'", specifier = "<=0.6.0" }, { name = "filetype", specifier = ">=1.2.0,<2.0.0" }, { name = "gdown", marker = "extra == 'evals'", specifier = ">=5.2.0,<6" }, @@ -1003,12 +1004,12 @@ requires-dist = [ { name = "lancedb", specifier = ">=0.24.0,<1.0.0" }, { name = "langchain-aws", marker = "extra == 'neptune'", specifier = ">=0.2.22" }, { name = "langchain-text-splitters", marker = "extra == 'langchain'", specifier = ">=0.3.2,<1.0.0" }, - { name = "langfuse", specifier = ">=2.32.0,<3" }, + { name = "langfuse", marker = "extra == 'monitoring'", specifier = ">=2.32.0,<3" }, { name = "langsmith", marker = "extra == 'langchain'", specifier = ">=0.2.3,<1.0.0" }, { name = "limits", specifier = ">=4.4.1,<5" }, - { name = "litellm", specifier = ">=1.71.0,<2.0.0" }, + { name = "litellm", specifier = ">=1.76.0" }, { name = "llama-index-core", marker = "extra == 'llama-index'", specifier = ">=0.12.11,<0.13" }, - { name = "matplotlib", specifier = ">=3.8.3,<4" }, + { name = "matplotlib", marker = "extra == 'evals'", specifier = ">=3.8.3,<4" }, { name = "mistral-common", marker = "extra == 'mistral'", specifier = ">=1.5.2,<2" }, { name = "mistralai", specifier = ">=1.9.10" }, { name = "mkdocs-material", marker = "extra == 'dev'", specifier = ">=9.5.42,<10" }, @@ -1019,41 +1020,37 @@ requires-dist = [ { name = "nbformat", specifier = ">=5.7.0,<6.0.0" }, { name = "neo4j", marker = "extra == 'neo4j'", specifier = ">=5.28.0,<6" }, { name = "networkx", specifier = ">=3.4.2,<4" }, - { name = "nltk", specifier = ">=3.9.1,<4.0.0" }, { name = "notebook", marker = "extra == 'dev'", specifier = ">=7.1.0,<8" }, { name = "notebook", marker = "extra == 'notebook'", specifier = ">=7.1.0,<8" }, { name = "numpy", specifier = ">=1.26.4,<=4.0.0" }, - { name = "onnxruntime", specifier = ">=1.0.0,<2.0.0" }, - { name = "openai", specifier = ">=1.80.1,<2.0.0" }, - { name = "pandas", specifier = ">=2.2.2,<3.0.0" }, + { name = "onnxruntime", specifier = "<=1.22.1" }, + { name = "openai", specifier = ">=1.80.1" }, + { name = "pandas", marker = "extra == 'evals'", specifier = ">=2.2.2,<3.0.0" }, { name = "pgvector", marker = "extra == 'postgres'", specifier = ">=0.3.5,<0.4" }, { name = "pgvector", marker = "extra == 'postgres-binary'", specifier = ">=0.3.5,<0.4" }, { name = "plotly", marker = "extra == 'evals'", specifier = ">=6.0.0,<7" }, { name = "posthog", marker = "extra == 'posthog'", specifier = ">=3.5.0,<4" }, - { name = "pre-commit", specifier = ">=4.0.1,<5" }, + { name = "pre-commit", marker = "extra == 'dev'", specifier = ">=4.0.1,<5" }, { name = "psycopg2", marker = "extra == 'postgres'", specifier = ">=2.9.10,<3" }, { name = "psycopg2-binary", marker = "extra == 'postgres-binary'", specifier = ">=2.9.10,<3.0.0" }, { name = "pydantic", specifier = ">=2.10.5,<3.0.0" }, { name = "pydantic-settings", specifier = ">=2.2.1,<3" }, - { name = "pylance", specifier = ">=0.22.0,<1.0.0" }, + { name = "pylance", specifier = ">=0.22.0,<=0.36.0" }, { name = "pylint", marker = "extra == 'dev'", specifier = ">=3.0.3,<4" }, { name = "pympler", specifier = ">=1.1,<2.0.0" }, { name = "pypdf", specifier = ">=4.1.0,<7.0.0" }, { name = "pypika", marker = "extra == 'chromadb'", specifier = "==0.48.9" }, - { name = "pyside6", marker = "extra == 'gui'", specifier = ">=6.8.3,<7" }, { name = "pytest", marker = "extra == 'dev'", specifier = ">=7.4.0,<8" }, { name = "pytest-asyncio", marker = "extra == 'dev'", specifier = ">=0.21.1,<0.22" }, { name = "pytest-cov", marker = "extra == 'dev'", specifier = ">=6.1.1,<7.0.0" }, { name = "python-dotenv", specifier = ">=1.0.1,<2.0.0" }, { name = "python-magic-bin", marker = "sys_platform == 'win32'", specifier = "<0.5" }, { name = "python-multipart", specifier = ">=0.0.20,<1.0.0" }, - { name = "qasync", marker = "extra == 'gui'", specifier = ">=0.27.1,<0.28" }, { name = "rdflib", specifier = ">=7.1.4,<7.2.0" }, - { name = "ruff", marker = "extra == 'dev'", specifier = ">=0.9.2,<1.0.0" }, - { name = "s3fs", extras = ["boto3"], specifier = "==2025.3.2" }, + { name = "ruff", marker = "extra == 'dev'", specifier = ">=0.9.2,<=0.13.1" }, { name = "s3fs", extras = ["boto3"], marker = "extra == 'aws'", specifier = "==2025.3.2" }, - { name = "scikit-learn", specifier = ">=1.6.1,<2" }, - { name = "sentry-sdk", extras = ["fastapi"], specifier = ">=2.9.0,<3" }, + { name = "scikit-learn", marker = "extra == 'evals'", specifier = ">=1.6.1,<2" }, + { name = "sentry-sdk", extras = ["fastapi"], marker = "extra == 'monitoring'", specifier = ">=2.9.0,<3" }, { name = "sqlalchemy", specifier = ">=2.0.39,<3.0.0" }, { name = "structlog", specifier = ">=25.2.0,<26" }, { name = "tiktoken", specifier = ">=0.8.0,<1.0.0" }, @@ -1068,6 +1065,7 @@ requires-dist = [ { name = "uvicorn", specifier = ">=0.34.0,<1.0.0" }, { name = "websockets", specifier = ">=15.0.1,<16.0.0" }, ] +provides-extras = ["api", "distributed", "neo4j", "neptune", "postgres", "postgres-binary", "notebook", "langchain", "llama-index", "gemini", "huggingface", "ollama", "mistral", "anthropic", "deepeval", "posthog", "falkordb", "groq", "chromadb", "docs", "codegraph", "evals", "graphiti", "aws", "dlt", "baml", "dev", "debug", "monitoring"] [[package]] name = "colorama" @@ -1177,13 +1175,13 @@ version = "1.3.3" source = { registry = "https://pypi.org/simple" } resolution-markers = [ "python_full_version >= '3.13' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.12.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", "python_full_version >= '3.13' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.12.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version >= '3.13' and sys_platform == 'emscripten'", + "python_full_version == '3.12.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version == '3.12.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.12.*' and sys_platform == 'emscripten'", + "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.11.*' and sys_platform == 'emscripten'", ] dependencies = [ @@ -1588,7 +1586,7 @@ wheels = [ [[package]] name = "dlt" -version = "1.16.0" +version = "1.17.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "click" }, @@ -1619,9 +1617,9 @@ dependencies = [ { name = "tzdata" }, { name = "win-precise-time", marker = "python_full_version < '3.13' and os_name == 'nt'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/47/45/8f32b8cc4c709c79edc54763ab0e5f62df55a17bfaf8c31e2d2538422e34/dlt-1.16.0.tar.gz", hash = "sha256:113d17a3f27aa4f41c3438b0b032a68d30db195d8415a471ba43a9502e971a21", size = 809187 } +sdist = { url = "https://files.pythonhosted.org/packages/af/2e/959f7ba35a710c4128bd7ff329038af35791c77346beeeb16c6d3e2bd87c/dlt-1.17.0.tar.gz", hash = "sha256:7a41a360f0cfeb155da1da3cdd51edb3749a4378d99bb6d1d0a26c7ef471198d", size = 823873, upload-time = "2025-09-24T10:54:00.95Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/c6/1c/0a96ced9fb52e859b44624cc86ace5f59324ca899ac7e5a5cfeb1f1c797c/dlt-1.16.0-py3-none-any.whl", hash = "sha256:882ef281bbdc32eaba3b5ced984a8ed7014d8978fd7ab4a58b198023c8938c9f", size = 1029963 }, + { url = "https://files.pythonhosted.org/packages/e1/ed/86aa307dd764ed56c2ab32fa7842a9b5a3a1b3a3b4709307756fd9ac756b/dlt-1.17.0-py3-none-any.whl", hash = "sha256:e5da62695cfbd37f2569b16af3e50582dc2ede2af5c1c014ded7bb7c089de5b1", size = 1048344, upload-time = "2025-09-24T10:53:58.642Z" }, ] [package.optional-dependencies] @@ -1864,11 +1862,11 @@ wheels = [ [[package]] name = "flatbuffers" -version = "25.2.10" +version = "25.9.23" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/e4/30/eb5dce7994fc71a2f685d98ec33cc660c0a5887db5610137e60d8cbc4489/flatbuffers-25.2.10.tar.gz", hash = "sha256:97e451377a41262f8d9bd4295cc836133415cc03d8cb966410a4af92eb00d26e", size = 22170 } +sdist = { url = "https://files.pythonhosted.org/packages/9d/1f/3ee70b0a55137442038f2a33469cc5fddd7e0ad2abf83d7497c18a2b6923/flatbuffers-25.9.23.tar.gz", hash = "sha256:676f9fa62750bb50cf531b42a0a2a118ad8f7f797a511eda12881c016f093b12", size = 22067, upload-time = "2025-09-24T05:25:30.106Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/b8/25/155f9f080d5e4bc0082edfda032ea2bc2b8fab3f4d25d46c1e9dd22a1a89/flatbuffers-25.2.10-py2.py3-none-any.whl", hash = "sha256:ebba5f4d5ea615af3f7fd70fc310636fbb2bbd1f566ac0a23d98dd412de50051", size = 30953 }, + { url = "https://files.pythonhosted.org/packages/ee/1b/00a78aa2e8fbd63f9af08c9c19e6deb3d5d66b4dda677a0f61654680ee89/flatbuffers-25.9.23-py2.py3-none-any.whl", hash = "sha256:255538574d6cb6d0a79a17ec8bc0d30985913b87513a01cce8bcdb6b4c44d0e2", size = 30869, upload-time = "2025-09-24T05:25:28.912Z" }, ] [[package]] @@ -2123,7 +2121,7 @@ grpc = [ [[package]] name = "google-api-python-client" -version = "2.182.0" +version = "2.183.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "google-api-core" }, @@ -2132,9 +2130,9 @@ dependencies = [ { name = "httplib2" }, { name = "uritemplate" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/6f/cb/b85b1d7d7fd520739fb70c4878f1f414043c3c34434bc90ba9d4f93366ed/google_api_python_client-2.182.0.tar.gz", hash = "sha256:cb2aa127e33c3a31e89a06f39cf9de982db90a98dee020911b21013afafad35f", size = 13599318 } +sdist = { url = "https://files.pythonhosted.org/packages/fa/1f/49a2c83fc6dcd8b127cc9efbecf7d5fc36109c2028ba22ed6cb4d072fca4/google_api_python_client-2.183.0.tar.gz", hash = "sha256:abae37e04fecf719388e5c02f707ed9cdf952f10b217c79a3e76c636762e3ea9", size = 13645623, upload-time = "2025-09-23T22:27:00.854Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/c1/29/76dabe97ebb710ca9a308f0415b2206e37d149983ec2becbf66525c52322/google_api_python_client-2.182.0-py3-none-any.whl", hash = "sha256:a9b071036d41a17991d8fbf27bedb61f2888a39ae5696cb5a326bf999b2d5209", size = 14168745 }, + { url = "https://files.pythonhosted.org/packages/ab/06/1974f937172854bc7622eff5c2390f33542ceb843f305922922c8f5f7f17/google_api_python_client-2.183.0-py3-none-any.whl", hash = "sha256:2005b6e86c27be1db1a43f43e047a0f8e004159f3cceddecb08cf1624bddba31", size = 14214837, upload-time = "2025-09-23T22:26:57.758Z" }, ] [[package]] @@ -2549,7 +2547,7 @@ wheels = [ [[package]] name = "huggingface-hub" -version = "0.35.0" +version = "0.35.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "filelock" }, @@ -2561,9 +2559,9 @@ dependencies = [ { name = "tqdm" }, { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/37/79/d71d40efa058e8c4a075158f8855bc2998037b5ff1c84f249f34435c1df7/huggingface_hub-0.35.0.tar.gz", hash = "sha256:ccadd2a78eef75effff184ad89401413629fabc52cefd76f6bbacb9b1c0676ac", size = 461486 } +sdist = { url = "https://files.pythonhosted.org/packages/f6/42/0e7be334a6851cd7d51cc11717cb95e89333ebf0064431c0255c56957526/huggingface_hub-0.35.1.tar.gz", hash = "sha256:3585b88c5169c64b7e4214d0e88163d4a709de6d1a502e0cd0459e9ee2c9c572", size = 461374, upload-time = "2025-09-23T13:43:47.074Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/fe/85/a18508becfa01f1e4351b5e18651b06d210dbd96debccd48a452acccb901/huggingface_hub-0.35.0-py3-none-any.whl", hash = "sha256:f2e2f693bca9a26530b1c0b9bcd4c1495644dad698e6a0060f90e22e772c31e9", size = 563436 }, + { url = "https://files.pythonhosted.org/packages/f1/60/4acf0c8a3925d9ff491dc08fe84d37e09cfca9c3b885e0db3d4dedb98cea/huggingface_hub-0.35.1-py3-none-any.whl", hash = "sha256:2f0e2709c711e3040e31d3e0418341f7092910f1462dd00350c4e97af47280a8", size = 563340, upload-time = "2025-09-23T13:43:45.343Z" }, ] [[package]] @@ -2734,13 +2732,13 @@ version = "9.5.0" source = { registry = "https://pypi.org/simple" } resolution-markers = [ "python_full_version >= '3.13' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.12.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", "python_full_version >= '3.13' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.12.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version >= '3.13' and sys_platform == 'emscripten'", + "python_full_version == '3.12.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version == '3.12.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.12.*' and sys_platform == 'emscripten'", + "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.11.*' and sys_platform == 'emscripten'", ] dependencies = [ @@ -3308,7 +3306,7 @@ wheels = [ [[package]] name = "lance-namespace-urllib3-client" -version = "0.0.14" +version = "0.0.15" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "pydantic" }, @@ -3316,14 +3314,14 @@ dependencies = [ { name = "typing-extensions" }, { name = "urllib3" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/43/09/727f5749da387a16ffd342339d859073e950ae451f66554bfba8e8adac71/lance_namespace_urllib3_client-0.0.14.tar.gz", hash = "sha256:911c6a3b5c2c98f4239b6d96609cf840e740c3af5482f5fb22096afb9db1dc1c", size = 134488 } +sdist = { url = "https://files.pythonhosted.org/packages/a8/14/023f12f2d1e624965a361b535b94cc65dfd949d7325e85372f3eb1c75a95/lance_namespace_urllib3_client-0.0.15.tar.gz", hash = "sha256:27a7bf3add1c03ed5e9ccbf83632b2d5468c4d0e1d2fd7a7fe612d9e70934113", size = 134497, upload-time = "2025-09-24T05:46:10.2Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/ca/90/ceb58b9a9f3aca0af1c294d71115ee9d44d6d82e0c9dc57d6743574d6358/lance_namespace_urllib3_client-0.0.14-py3-none-any.whl", hash = "sha256:40277cfcf7c9084419c2784e7924b3e316f6fe5b8057f4dc62a49f3b40c2d80c", size = 229639 }, + { url = "https://files.pythonhosted.org/packages/e7/7d/76f92398313658be01b982f29fb2407bf2ed0f920b49d00628b97618ee96/lance_namespace_urllib3_client-0.0.15-py3-none-any.whl", hash = "sha256:ea931c557489002bff212a21f3929827c8ad9cb7c626747714e120a47698ffdd", size = 229640, upload-time = "2025-09-24T05:46:08.795Z" }, ] [[package]] name = "lancedb" -version = "0.25.0" +version = "0.25.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "deprecation" }, @@ -3337,13 +3335,13 @@ dependencies = [ { name = "tqdm" }, ] wheels = [ - { url = "https://files.pythonhosted.org/packages/a2/e7/10953deea89b06ae5bc568169d5ae888ff6df314decb92b9b3e453f53f0b/lancedb-0.25.0-cp39-abi3-macosx_10_15_x86_64.whl", hash = "sha256:ae2e80b7b3be3fa4d92fc8d500f47549dd1f8d28ca5092f1c898b92d0cfd4393", size = 34171227 }, - { url = "https://files.pythonhosted.org/packages/55/7f/2874a3709f1b8c487e707e171c9004a9240af3af0fd7a247b9187bb6e0f7/lancedb-0.25.0-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:a9d67ea9edffa596c6f190151fdd535da8e355a4fd1979c1dc19d540a5665916", size = 31552856 }, - { url = "https://files.pythonhosted.org/packages/e3/e9/faab70ad918576ed3bb7cb936474137ac265ac3026d3e16e30cd4d3daac2/lancedb-0.25.0-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8fe20079ed86b1ab75c65dcfc920a9646c835e9c40ef825cadd148c11b0001e", size = 32487962 }, - { url = "https://files.pythonhosted.org/packages/ce/40/5471bc8115f287040b5afdf9d7a20c4685ec16cddb4a7da79e7c1f63914e/lancedb-0.25.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b37bc402d85c83e454d9f2e79480b31acc5904bb159a4fc715032c7560494157", size = 35726794 }, - { url = "https://files.pythonhosted.org/packages/47/5e/aa3d9d2c7a834a9aa539b2b1c731ab860f7e32e2c87b9086ad233ecb13cd/lancedb-0.25.0-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:f9bbc20bd1e64be359ca11c90428c00b0062d26b0291bddf32ab5471a3525c76", size = 32492508 }, - { url = "https://files.pythonhosted.org/packages/fa/37/75f4e3ed7fa00a2cd5d321e8bf13441cdb61a83fbbcd0fa0f1a7241affe1/lancedb-0.25.0-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:1306be9c08e208a5bcb5188275f47f962c2eda96369fad5949a3ddaf592afc6d", size = 35776383 }, - { url = "https://files.pythonhosted.org/packages/b5/af/eb217ea1daab5c28ce4c764d2f672f4e3a5bcd3d4faf7921a8ee28c6cb5b/lancedb-0.25.0-cp39-abi3-win_amd64.whl", hash = "sha256:f66283e5d63c99c2bfbd4eaa134d9a5c5b0145eb26a972648214f8ba87777e24", size = 37826272 }, + { url = "https://files.pythonhosted.org/packages/ad/2b/ed9870288506d8ca61cddf7b1dbb03c68f95b8797feb49467b33ef185477/lancedb-0.25.1-cp39-abi3-macosx_10_15_x86_64.whl", hash = "sha256:ec0a1cab435a5307054b84ffb798a4d828253f23698848788bfe31930e343c6c", size = 34985432, upload-time = "2025-09-23T23:15:56.558Z" }, + { url = "https://files.pythonhosted.org/packages/58/75/320f9142918b646b4b6d0277676c2466d2e0ce2a22aca320d0113b3ef035/lancedb-0.25.1-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:69e1f8343f6a4ff6985ea13f5c5cdf6d07435d04f8279c4fc6e623a34ceadda0", size = 31993179, upload-time = "2025-09-23T22:20:23.039Z" }, + { url = "https://files.pythonhosted.org/packages/fd/44/d223cb64c9feb78dfa3857690d743e961f76e065935c8c4304cb64659882/lancedb-0.25.1-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9432134155474e73907fc5e1f8a4310433b9234a0c5f964c21b4c39aca50dde6", size = 32872519, upload-time = "2025-09-23T22:29:03.5Z" }, + { url = "https://files.pythonhosted.org/packages/61/a6/e6d88d8076fa8c40b7b6f96a37f21c75ce3518ccbf64a351d26ae983461a/lancedb-0.25.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:955c6e1aa4e249be7456ea7f7c42ba119be5a5c2c51f4d78efeb6c4f3cc2dbdf", size = 36325984, upload-time = "2025-09-23T22:31:46.118Z" }, + { url = "https://files.pythonhosted.org/packages/97/84/14d4f0c3a98a324fcb401161e25fb1699c69ba1cd2928983fb283bd8b04f/lancedb-0.25.1-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:d584bdfb96372c03a209bb8f010eb7358135e4adddb903ae1385450af39e1187", size = 32883704, upload-time = "2025-09-23T22:27:41.393Z" }, + { url = "https://files.pythonhosted.org/packages/68/10/3e8ae8bf9880b2fed10122cef5e535bd67f0df0a874cc3122220d47ca255/lancedb-0.25.1-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:c495da53d3dfa105364f202710d0bb2f031fe54a077b9c2ac9d098d02bd20bb2", size = 36369514, upload-time = "2025-09-23T22:30:53.605Z" }, + { url = "https://files.pythonhosted.org/packages/0d/fb/dce4757f257cb4e11e13b71ce502dc5d1caf51f1e5cccfdae85bf23960a0/lancedb-0.25.1-cp39-abi3-win_amd64.whl", hash = "sha256:2c6effc10c8263ea84261f49d5ff1957c18814ed7e3eaa5094d71b1aa0573871", size = 38390878, upload-time = "2025-09-23T22:55:24.687Z" }, ] [[package]] @@ -3422,7 +3420,7 @@ wheels = [ [[package]] name = "langsmith" -version = "0.4.30" +version = "0.4.31" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "httpx" }, @@ -3433,18 +3431,18 @@ dependencies = [ { name = "requests-toolbelt" }, { name = "zstandard" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/fe/d5/4cc88f246ce615a518a715cd2bf40001d1678ad6805a3706a90570adca8f/langsmith-0.4.30.tar.gz", hash = "sha256:388fe1060aca6507be41f417c7d4168a92dffe27f28bb6ef8a1bfee4a59f3681", size = 958857 } +sdist = { url = "https://files.pythonhosted.org/packages/55/f5/edbdf89a162ee025348b3b2080fb3b88f4a1040a5a186f32d34aca913994/langsmith-0.4.31.tar.gz", hash = "sha256:5fb3729e22bd9a225391936cb9d1080322e6c375bb776514af06b56d6c46ed3e", size = 959698, upload-time = "2025-09-25T04:18:19.55Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/ae/d1/b2b2ea7b443c6b028aca209d2e653256912906900cc146e64c65201211b7/langsmith-0.4.30-py3-none-any.whl", hash = "sha256:110767eb83e6da2cc99cfc61958631b5c36624758b52e7af35ec5550ad846cb3", size = 386300 }, + { url = "https://files.pythonhosted.org/packages/3e/8e/e7a43d907a147e1f87eebdd6737483f9feba52a5d4b20f69d0bd6f2fa22f/langsmith-0.4.31-py3-none-any.whl", hash = "sha256:64f340bdead21defe5f4a6ca330c11073e35444989169f669508edf45a19025f", size = 386347, upload-time = "2025-09-25T04:18:16.69Z" }, ] [[package]] name = "lark" version = "1.3.0" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/1d/37/a13baf0135f348af608c667633cbe5d13aa2c5c15a56ae9ad3e6cba45ae3/lark-1.3.0.tar.gz", hash = "sha256:9a3839d0ca5e1faf7cfa3460e420e859b66bcbde05b634e73c369c8244c5fa48", size = 259551 } +sdist = { url = "https://files.pythonhosted.org/packages/1d/37/a13baf0135f348af608c667633cbe5d13aa2c5c15a56ae9ad3e6cba45ae3/lark-1.3.0.tar.gz", hash = "sha256:9a3839d0ca5e1faf7cfa3460e420e859b66bcbde05b634e73c369c8244c5fa48", size = 259551, upload-time = "2025-09-22T13:45:05.072Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/a8/3e/1c6b43277de64fc3c0333b0e72ab7b52ddaaea205210d60d9b9f83c3d0c7/lark-1.3.0-py3-none-any.whl", hash = "sha256:80661f261fb2584a9828a097a2432efd575af27d20be0fd35d17f0fe37253831", size = 113002 }, + { url = "https://files.pythonhosted.org/packages/a8/3e/1c6b43277de64fc3c0333b0e72ab7b52ddaaea205210d60d9b9f83c3d0c7/lark-1.3.0-py3-none-any.whl", hash = "sha256:80661f261fb2584a9828a097a2432efd575af27d20be0fd35d17f0fe37253831", size = 113002, upload-time = "2025-09-22T13:45:03.747Z" }, ] [[package]] @@ -3463,7 +3461,7 @@ wheels = [ [[package]] name = "litellm" -version = "1.77.3" +version = "1.77.4" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "aiohttp" }, @@ -3480,9 +3478,9 @@ dependencies = [ { name = "tiktoken" }, { name = "tokenizers" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/92/86/8bfd372d3d437b773b4b81d6da35674a569c10a9b805409257790e3af271/litellm-1.77.3.tar.gz", hash = "sha256:d8f9d674ef4e7673b1af02428fde27de5a8e84ca7268f003902340586aac7d96", size = 10314535 } +sdist = { url = "https://files.pythonhosted.org/packages/ab/b7/0d3c6dbcff3064238d123f90ae96764a85352f3f5caab6695a55007fd019/litellm-1.77.4.tar.gz", hash = "sha256:ce652e10ecf5b36767bfdf58e53b2802e22c3de383b03554e6ee1a4a66fa743d", size = 10330773, upload-time = "2025-09-24T17:52:44.876Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/81/b2/122602255b582fdcf630f8e44b5c9175391abe10be5e2f4db6a7d4173df1/litellm-1.77.3-py3-none-any.whl", hash = "sha256:f0c8c6bcfa2c9cd9e9fa0304f9a94894d252e7c74f118c37a8f2e4e525b2592b", size = 9118886 }, + { url = "https://files.pythonhosted.org/packages/3c/32/90f8587818d146d604ed6eec95f96378363fda06b14817399cc68853383e/litellm-1.77.4-py3-none-any.whl", hash = "sha256:66c2bb776f1e19ceddfa977a2bbf7f05e6f26c4b1fec8b2093bd171d842701b8", size = 9138493, upload-time = "2025-09-24T17:52:40.764Z" }, ] [[package]] @@ -4445,13 +4443,13 @@ version = "3.5" source = { registry = "https://pypi.org/simple" } resolution-markers = [ "python_full_version >= '3.13' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.12.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", "python_full_version >= '3.13' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.12.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version >= '3.13' and sys_platform == 'emscripten'", + "python_full_version == '3.12.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version == '3.12.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.12.*' and sys_platform == 'emscripten'", + "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.11.*' and sys_platform == 'emscripten'", ] sdist = { url = "https://files.pythonhosted.org/packages/6c/4f/ccdb8ad3a38e583f214547fd2f7ff1fc160c43a75af88e6aec213404b96a/networkx-3.5.tar.gz", hash = "sha256:d4c6f9cf81f52d69230866796b82afbccdec3db7ae4fbd1b65ea750feed50037", size = 2471065 } @@ -4517,10 +4515,10 @@ version = "1.26.4" source = { registry = "https://pypi.org/simple" } resolution-markers = [ "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version < '3.11' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version < '3.11' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.11.*' and sys_platform == 'emscripten'", + "python_full_version < '3.11' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version < '3.11' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version < '3.11' and sys_platform == 'emscripten'", ] sdist = { url = "https://files.pythonhosted.org/packages/65/6e/09db70a523a96d25e115e71cc56a6f9031e7b8cd166c1ac8438307c14058/numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010", size = 15786129 } @@ -4557,10 +4555,10 @@ version = "2.3.3" source = { registry = "https://pypi.org/simple" } resolution-markers = [ "python_full_version >= '3.13' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.12.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", "python_full_version >= '3.13' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.12.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version >= '3.13' and sys_platform == 'emscripten'", + "python_full_version == '3.12.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version == '3.12.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.12.*' and sys_platform == 'emscripten'", ] sdist = { url = "https://files.pythonhosted.org/packages/d0/19/95b3d357407220ed24c139018d2518fab0a61a948e68286a25f1a4d049ff/numpy-2.3.3.tar.gz", hash = "sha256:ddc7c39727ba62b80dfdbedf400d1c10ddfa8eefbd7ec8dcb118be8b56d31029", size = 20576648 } @@ -4638,15 +4636,15 @@ wheels = [ [[package]] name = "ollama" -version = "0.5.4" +version = "0.6.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "httpx" }, { name = "pydantic" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/72/62/a36be4555e4218d6c8b35e72e0dfe0823845400097275cd81c9aec4ddf39/ollama-0.5.4.tar.gz", hash = "sha256:75857505a5d42e5e58114a1b78cc8c24596d8866863359d8a2329946a9b6d6f3", size = 45233 } +sdist = { url = "https://files.pythonhosted.org/packages/d6/47/f9ee32467fe92744474a8c72e138113f3b529fc266eea76abfdec9a33f3b/ollama-0.6.0.tar.gz", hash = "sha256:da2b2d846b5944cfbcee1ca1e6ee0585f6c9d45a2fe9467cbcd096a37383da2f", size = 50811, upload-time = "2025-09-24T22:46:02.417Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/1b/af/d0a23c8fdec4c8ddb771191d9b36a57fbce6741835a78f1b18ab6d15ae7d/ollama-0.5.4-py3-none-any.whl", hash = "sha256:6374c9bb4f2a371b3583c09786112ba85b006516745689c172a7e28af4d4d1a2", size = 13548 }, + { url = "https://files.pythonhosted.org/packages/b5/c1/edc9f41b425ca40b26b7c104c5f6841a4537bb2552bfa6ca66e81405bb95/ollama-0.6.0-py3-none-any.whl", hash = "sha256:534511b3ccea2dff419ae06c3b58d7f217c55be7897c8ce5868dfb6b219cf7a0", size = 14130, upload-time = "2025-09-24T22:46:01.19Z" }, ] [[package]] @@ -4685,7 +4683,7 @@ wheels = [ [[package]] name = "openai" -version = "1.108.2" +version = "1.109.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "anyio" }, @@ -4697,9 +4695,9 @@ dependencies = [ { name = "tqdm" }, { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/8c/ff/1dc7bec988cfbab80c2b0ee61d5178915117a4f02f68777d528219e84866/openai-1.108.2.tar.gz", hash = "sha256:e6ce793e0ef8a52d343850a5411edbd5b21214f64a8d29cdca0fcb929e8e3155", size = 563898 } +sdist = { url = "https://files.pythonhosted.org/packages/c6/a1/a303104dc55fc546a3f6914c842d3da471c64eec92043aef8f652eb6c524/openai-1.109.1.tar.gz", hash = "sha256:d173ed8dbca665892a6db099b4a2dfac624f94d20a93f46eb0b56aae940ed869", size = 564133, upload-time = "2025-09-24T13:00:53.075Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/13/2d/1cb19289feef689206cd8995d7be6b5d76b7e8d64fd51438acecc11ee395/openai-1.108.2-py3-none-any.whl", hash = "sha256:4c7caa23845a49aebd8f65e01b35739b5b2df5e621d4666cbe55f0973fae81b7", size = 948390 }, + { url = "https://files.pythonhosted.org/packages/1d/2a/7dd3d207ec669cacc1f186fd856a0f61dbc255d24f6fdc1a6715d6051b0f/openai-1.109.1-py3-none-any.whl", hash = "sha256:6bcaf57086cf59159b8e27447e4e7dd019db5d29a438072fbd49c290c7e65315", size = 948627, upload-time = "2025-09-24T13:00:50.754Z" }, ] [[package]] @@ -5813,16 +5811,16 @@ pycountry = [ [[package]] name = "pydantic-settings" -version = "2.10.1" +version = "2.11.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "pydantic" }, { name = "python-dotenv" }, { name = "typing-inspection" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/68/85/1ea668bbab3c50071ca613c6ab30047fb36ab0da1b92fa8f17bbc38fd36c/pydantic_settings-2.10.1.tar.gz", hash = "sha256:06f0062169818d0f5524420a360d632d5857b83cffd4d42fe29597807a1614ee", size = 172583 } +sdist = { url = "https://files.pythonhosted.org/packages/20/c5/dbbc27b814c71676593d1c3f718e6cd7d4f00652cefa24b75f7aa3efb25e/pydantic_settings-2.11.0.tar.gz", hash = "sha256:d0e87a1c7d33593beb7194adb8470fc426e95ba02af83a0f23474a04c9a08180", size = 188394, upload-time = "2025-09-24T14:19:11.764Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/58/f0/427018098906416f580e3cf1366d3b1abfb408a0652e9f31600c24a1903c/pydantic_settings-2.10.1-py3-none-any.whl", hash = "sha256:a60952460b99cf661dc25c29c0ef171721f98bfcb52ef8d9ea4c943d7c8cc796", size = 45235 }, + { url = "https://files.pythonhosted.org/packages/83/d6/887a1ff844e64aa823fb4905978d882a633cfe295c32eacad582b78a7d8b/pydantic_settings-2.11.0-py3-none-any.whl", hash = "sha256:fe2cea3413b9530d10f3a5875adffb17ada5c1e1bab0b2885546d7310415207c", size = 48608, upload-time = "2025-09-24T14:19:10.015Z" }, ] [[package]] @@ -5974,54 +5972,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/5a/dc/491b7661614ab97483abf2056be1deee4dc2490ecbf7bff9ab5cdbac86e1/pyreadline3-3.5.4-py3-none-any.whl", hash = "sha256:eaf8e6cc3c49bcccf145fc6067ba8643d1df34d604a1ec0eccbf7a18e6d3fae6", size = 83178 }, ] -[[package]] -name = "pyside6" -version = "6.9.2" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "pyside6-addons" }, - { name = "pyside6-essentials" }, - { name = "shiboken6" }, -] -wheels = [ - { url = "https://files.pythonhosted.org/packages/43/42/43577413bd5ab26f5f21e7a43c9396aac158a5d01900c87e4609c0e96278/pyside6-6.9.2-cp39-abi3-macosx_12_0_universal2.whl", hash = "sha256:71245c76bfbe5c41794ffd8546730ec7cc869d4bbe68535639e026e4ef8a7714", size = 558102 }, - { url = "https://files.pythonhosted.org/packages/12/df/cb84f802df3dcc1d196d2f9f37dbb8227761826f936987c9386b8ae1ffcc/pyside6-6.9.2-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:64a9e2146e207d858e00226f68d7c1b4ab332954742a00dcabb721bb9e4aa0cd", size = 558243 }, - { url = "https://files.pythonhosted.org/packages/94/2d/715db9da437b4632d06e2c4718aee9937760b84cf36c23d5441989e581b0/pyside6-6.9.2-cp39-abi3-manylinux_2_39_aarch64.whl", hash = "sha256:a78fad16241a1f2ed0fa0098cf3d621f591fc75b4badb7f3fa3959c9d861c806", size = 558245 }, - { url = "https://files.pythonhosted.org/packages/59/90/2e75cbff0e17f16b83d2b7e8434ae9175cae8d6ff816c9b56d307cf53c86/pyside6-6.9.2-cp39-abi3-win_amd64.whl", hash = "sha256:d1afbf48f9a5612b9ee2dc7c384c1a65c08b5830ba5e7d01f66d82678e5459df", size = 564604 }, - { url = "https://files.pythonhosted.org/packages/dc/34/e3dd4e046673efcbcfbe0aa2760df06b2877739b8f4da60f0229379adebd/pyside6-6.9.2-cp39-abi3-win_arm64.whl", hash = "sha256:1499b1d7629ab92119118e2636b4ace836b25e457ddf01003fdca560560b8c0a", size = 401833 }, -] - -[[package]] -name = "pyside6-addons" -version = "6.9.2" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "pyside6-essentials" }, - { name = "shiboken6" }, -] -wheels = [ - { url = "https://files.pythonhosted.org/packages/47/39/a8f4a55001b6a0aaee042e706de2447f21c6dc2a610f3d3debb7d04db821/pyside6_addons-6.9.2-cp39-abi3-macosx_12_0_universal2.whl", hash = "sha256:7019fdcc0059626eb1608b361371f4dc8cb7f2d02f066908fd460739ff5a07cd", size = 316693692 }, - { url = "https://files.pythonhosted.org/packages/14/48/0b16e9dabd4cafe02d59531832bc30b6f0e14c92076e90dd02379d365cb2/pyside6_addons-6.9.2-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:24350e5415317f269e743d1f7b4933fe5f59d90894aa067676c9ce6bfe9e7988", size = 166984613 }, - { url = "https://files.pythonhosted.org/packages/f4/55/dc42a73387379bae82f921b7659cd2006ec0e80f7052f83ddc07e9eb9cca/pyside6_addons-6.9.2-cp39-abi3-manylinux_2_39_aarch64.whl", hash = "sha256:af8dee517de8d336735a6543f7dd496eb580e852c14b4d2304b890e2a29de499", size = 162908466 }, - { url = "https://files.pythonhosted.org/packages/14/fa/396a2e86230c493b565e2dc89dc64e4b1c63582ac69afe77b693c3817a53/pyside6_addons-6.9.2-cp39-abi3-win_amd64.whl", hash = "sha256:98d2413904ee4b2b754b077af7875fa6ec08468c01a6628a2c9c3d2cece4874f", size = 160216647 }, - { url = "https://files.pythonhosted.org/packages/a7/fe/25f61259f1d5ec4648c9f6d2abd8e2cba2188f10735a57abafda719958e5/pyside6_addons-6.9.2-cp39-abi3-win_arm64.whl", hash = "sha256:b430cae782ff1a99fb95868043557f22c31b30c94afb9cf73278584e220a2ab6", size = 27126649 }, -] - -[[package]] -name = "pyside6-essentials" -version = "6.9.2" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "shiboken6" }, -] -wheels = [ - { url = "https://files.pythonhosted.org/packages/08/21/41960c03721a99e7be99a96ebb8570bdfd6f76f512b5d09074365e27ce28/pyside6_essentials-6.9.2-cp39-abi3-macosx_12_0_universal2.whl", hash = "sha256:713eb8dcbb016ff10e6fca129c1bf2a0fd8cfac979e689264e0be3b332f9398e", size = 133092348 }, - { url = "https://files.pythonhosted.org/packages/3e/02/e38ff18f3d2d8d3071aa6823031aad6089267aa4668181db65ce9948bfc0/pyside6_essentials-6.9.2-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:84b8ca4fa56506e2848bdb4c7a0851a5e7adcb916bef9bce25ce2eeb6c7002cc", size = 96569791 }, - { url = "https://files.pythonhosted.org/packages/9a/a1/1203d4db6919b42a937d9ac5ddb84b20ea42eb119f7c1ddeb77cb8fdb00c/pyside6_essentials-6.9.2-cp39-abi3-manylinux_2_39_aarch64.whl", hash = "sha256:d0f701503974bd51b408966539aa6956f3d8536e547ea8002fbfb3d77796bbc3", size = 94311809 }, - { url = "https://files.pythonhosted.org/packages/a8/e3/3b3e869d3e332b6db93f6f64fac3b12f5c48b84f03f2aa50ee5c044ec0de/pyside6_essentials-6.9.2-cp39-abi3-win_amd64.whl", hash = "sha256:b2f746f795138ac63eb173f9850a6db293461a1b6ce22cf6dafac7d194a38951", size = 72624566 }, - { url = "https://files.pythonhosted.org/packages/91/70/db78afc8b60b2e53f99145bde2f644cca43924a4dd869ffe664e0792730a/pyside6_essentials-6.9.2-cp39-abi3-win_arm64.whl", hash = "sha256:ecd7b5cd9e271f397fb89a6357f4ec301d8163e50869c6c557f9ccc6bed42789", size = 49561720 }, -] - [[package]] name = "pysocks" version = "1.7.1" @@ -6380,15 +6330,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/01/1b/5dbe84eefc86f48473947e2f41711aded97eecef1231f4558f1f02713c12/pyzmq-27.1.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:c9f7f6e13dff2e44a6afeaf2cf54cee5929ad64afaf4d40b50f93c58fc687355", size = 544862 }, ] -[[package]] -name = "qasync" -version = "0.27.1" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/1c/e0/7c7c973f52e1765d6ddfc41e9272294f65d5d52b8f5f5eae92adf411ad46/qasync-0.27.1.tar.gz", hash = "sha256:8dc768fd1ee5de1044c7c305eccf2d39d24d87803ea71189d4024fb475f4985f", size = 14287 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/51/06/bc628aa2981bcfd452a08ee435b812fd3eee4ada8acb8a76c4a09d1a5a77/qasync-0.27.1-py3-none-any.whl", hash = "sha256:5d57335723bc7d9b328dadd8cb2ed7978640e4bf2da184889ce50ee3ad2602c7", size = 14866 }, -] - [[package]] name = "rapidfuzz" version = "3.14.1" @@ -7007,13 +6948,13 @@ version = "1.16.2" source = { registry = "https://pypi.org/simple" } resolution-markers = [ "python_full_version >= '3.13' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.12.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", "python_full_version >= '3.13' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.12.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", - "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version >= '3.13' and sys_platform == 'emscripten'", + "python_full_version == '3.12.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version == '3.12.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.12.*' and sys_platform == 'emscripten'", + "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'emscripten'", + "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'emscripten'", "python_full_version == '3.11.*' and sys_platform == 'emscripten'", ] dependencies = [ @@ -7084,15 +7025,15 @@ wheels = [ [[package]] name = "sentry-sdk" -version = "2.38.0" +version = "2.39.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "certifi" }, { name = "urllib3" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/b2/22/60fd703b34d94d216b2387e048ac82de3e86b63bc28869fb076f8bb0204a/sentry_sdk-2.38.0.tar.gz", hash = "sha256:792d2af45e167e2f8a3347143f525b9b6bac6f058fb2014720b40b84ccbeb985", size = 348116 } +sdist = { url = "https://files.pythonhosted.org/packages/4c/72/43294fa4bdd75c51610b5104a3ff834459ba653abb415150aa7826a249dd/sentry_sdk-2.39.0.tar.gz", hash = "sha256:8c185854d111f47f329ab6bc35993f28f7a6b7114db64aa426b326998cfa14e9", size = 348556, upload-time = "2025-09-25T09:15:39.064Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/7a/84/bde4c4bbb269b71bc09316af8eb00da91f67814d40337cc12ef9c8742541/sentry_sdk-2.38.0-py2.py3-none-any.whl", hash = "sha256:2324aea8573a3fa1576df7fb4d65c4eb8d9929c8fa5939647397a07179eef8d0", size = 370346 }, + { url = "https://files.pythonhosted.org/packages/dd/44/4356cc64246ba7b2b920f7c97a85c3c52748e213e250b512ee8152eb559d/sentry_sdk-2.39.0-py2.py3-none-any.whl", hash = "sha256:ba655ca5e57b41569b18e2a5552cb3375209760a5d332cdd87c6c3f28f729602", size = 370851, upload-time = "2025-09-25T09:15:36.35Z" }, ] [package.optional-dependencies] @@ -7118,18 +7059,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/e0/f9/0595336914c5619e5f28a1fb793285925a8cd4b432c9da0a987836c7f822/shellingham-1.5.4-py2.py3-none-any.whl", hash = "sha256:7ecfff8f2fd72616f7481040475a65b2bf8af90a56c89140852d1120324e8686", size = 9755 }, ] -[[package]] -name = "shiboken6" -version = "6.9.2" -source = { registry = "https://pypi.org/simple" } -wheels = [ - { url = "https://files.pythonhosted.org/packages/1a/1e/62a8757aa0aa8d5dbf876f6cb6f652a60be9852e7911b59269dd983a7fb5/shiboken6-6.9.2-cp39-abi3-macosx_12_0_universal2.whl", hash = "sha256:8bb1c4326330e53adeac98bfd9dcf57f5173a50318a180938dcc4825d9ca38da", size = 406337 }, - { url = "https://files.pythonhosted.org/packages/3b/bb/72a8ed0f0542d9ea935f385b396ee6a4bbd94749c817cbf2be34e80a16d3/shiboken6-6.9.2-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3b54c0a12ea1b03b9dc5dcfb603c366e957dc75341bf7cb1cc436d0d848308ee", size = 206733 }, - { url = "https://files.pythonhosted.org/packages/52/c4/09e902f5612a509cef2c8712c516e4fe44f3a1ae9fcd8921baddb5e6bae4/shiboken6-6.9.2-cp39-abi3-manylinux_2_39_aarch64.whl", hash = "sha256:a5f5985938f5acb604c23536a0ff2efb3cccb77d23da91fbaff8fd8ded3dceb4", size = 202784 }, - { url = "https://files.pythonhosted.org/packages/a4/ea/a56b094a4bf6facf89f52f58e83684e168b1be08c14feb8b99969f3d4189/shiboken6-6.9.2-cp39-abi3-win_amd64.whl", hash = "sha256:68c33d565cd4732be762d19ff67dfc53763256bac413d392aa8598b524980bc4", size = 1152089 }, - { url = "https://files.pythonhosted.org/packages/48/64/562a527fc55fbf41fa70dae735929988215505cb5ec0809fb0aef921d4a0/shiboken6-6.9.2-cp39-abi3-win_arm64.whl", hash = "sha256:c5b827797b3d89d9b9a3753371ff533fcd4afc4531ca51a7c696952132098054", size = 1708948 }, -] - [[package]] name = "sigtools" version = "4.0.1" @@ -7291,11 +7220,11 @@ asyncio = [ [[package]] name = "sqlglot" -version = "27.16.3" +version = "27.18.0" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/8f/a9/c50f262c5b1a4ca110a110b3ea2312e9a2febee19c21f849389501d08c5c/sqlglot-27.16.3.tar.gz", hash = "sha256:bf5cc3b7c90c3682365353a318089e69e859939943d7882562ba39be650a6202", size = 5471626 } +sdist = { url = "https://files.pythonhosted.org/packages/01/56/ef3c705c750b262d4cca787982e3b640d46e8b40ba06d1d5577fb1bb4d76/sqlglot-27.18.0.tar.gz", hash = "sha256:6901eb1805226f38852e53c473d67c8e13bacf11ffe5d90170874f3d7b199acf", size = 5478250, upload-time = "2025-09-25T10:31:47.423Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/48/16/3ef8601ebef21b0971179242589d9811e68c9032c22f1910e3a68fe698ff/sqlglot-27.16.3-py3-none-any.whl", hash = "sha256:3765ef1da6c9a04dd9e9ab4bcf24ca54daae72d86d693954aed84dbbbff2ff3b", size = 518006 }, + { url = "https://files.pythonhosted.org/packages/ca/cc/110103f57c249bed40e85bd069ec3d2c29250ea228c89ed9d161924bb44d/sqlglot-27.18.0-py3-none-any.whl", hash = "sha256:71c122ddc99128347e1cd9ad6ed08b378cdf233e27eb78abce7542f47c723edd", size = 520293, upload-time = "2025-09-25T10:31:44.927Z" }, ] [[package]] @@ -7662,7 +7591,7 @@ wheels = [ [[package]] name = "typer" -version = "0.19.1" +version = "0.19.2" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "click" }, @@ -7670,9 +7599,9 @@ dependencies = [ { name = "shellingham" }, { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/03/ea/9cc57c3c627fd7a6a0907ea371019fe74c3ec00e3cf209a6864140a602ad/typer-0.19.1.tar.gz", hash = "sha256:cb881433a4b15dacc875bb0583d1a61e78497806741f9aba792abcab390c03e6", size = 104802 } +sdist = { url = "https://files.pythonhosted.org/packages/21/ca/950278884e2ca20547ff3eb109478c6baf6b8cf219318e6bc4f666fad8e8/typer-0.19.2.tar.gz", hash = "sha256:9ad824308ded0ad06cc716434705f691d4ee0bfd0fb081839d2e426860e7fdca", size = 104755, upload-time = "2025-09-23T09:47:48.256Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/1e/fa/6473c00b5eb26a2ba427813107699d3e6f4e1a4afad3f7494b17bdef3422/typer-0.19.1-py3-none-any.whl", hash = "sha256:914b2b39a1da4bafca5f30637ca26fa622a5bf9f515e5fdc772439f306d5682a", size = 46876 }, + { url = "https://files.pythonhosted.org/packages/00/22/35617eee79080a5d071d0f14ad698d325ee6b3bf824fc0467c03b30e7fa8/typer-0.19.2-py3-none-any.whl", hash = "sha256:755e7e19670ffad8283db353267cb81ef252f595aa6834a0d1ca9312d9326cb9", size = 46748, upload-time = "2025-09-23T09:47:46.777Z" }, ] [[package]] @@ -7885,16 +7814,16 @@ wheels = [ [[package]] name = "uvicorn" -version = "0.36.0" +version = "0.37.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "click" }, { name = "h11" }, { name = "typing-extensions", marker = "python_full_version < '3.11'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/ef/5e/f0cd46063a02fd8515f0e880c37d2657845b7306c16ce6c4ffc44afd9036/uvicorn-0.36.0.tar.gz", hash = "sha256:527dc68d77819919d90a6b267be55f0e76704dca829d34aea9480be831a9b9d9", size = 80032 } +sdist = { url = "https://files.pythonhosted.org/packages/71/57/1616c8274c3442d802621abf5deb230771c7a0fec9414cb6763900eb3868/uvicorn-0.37.0.tar.gz", hash = "sha256:4115c8add6d3fd536c8ee77f0e14a7fd2ebba939fed9b02583a97f80648f9e13", size = 80367, upload-time = "2025-09-23T13:33:47.486Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/96/06/5cc0542b47c0338c1cb676b348e24a1c29acabc81000bced518231dded6f/uvicorn-0.36.0-py3-none-any.whl", hash = "sha256:6bb4ba67f16024883af8adf13aba3a9919e415358604ce46780d3f9bdc36d731", size = 67675 }, + { url = "https://files.pythonhosted.org/packages/85/cd/584a2ceb5532af99dd09e50919e3615ba99aa127e9850eafe5f31ddfdb9a/uvicorn-0.37.0-py3-none-any.whl", hash = "sha256:913b2b88672343739927ce381ff9e2ad62541f9f8289664fa1d1d3803fa2ce6c", size = 67976, upload-time = "2025-09-23T13:33:45.842Z" }, ] [package.optional-dependencies] @@ -8071,9 +8000,9 @@ wheels = [ name = "wcwidth" version = "0.2.14" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/24/30/6b0809f4510673dc723187aeaf24c7f5459922d01e2f794277a3dfb90345/wcwidth-0.2.14.tar.gz", hash = "sha256:4d478375d31bc5395a3c55c40ccdf3354688364cd61c4f6adacaa9215d0b3605", size = 102293 } +sdist = { url = "https://files.pythonhosted.org/packages/24/30/6b0809f4510673dc723187aeaf24c7f5459922d01e2f794277a3dfb90345/wcwidth-0.2.14.tar.gz", hash = "sha256:4d478375d31bc5395a3c55c40ccdf3354688364cd61c4f6adacaa9215d0b3605", size = 102293, upload-time = "2025-09-22T16:29:53.023Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/af/b5/123f13c975e9f27ab9c0770f514345bd406d0e8d3b7a0723af9d43f710af/wcwidth-0.2.14-py2.py3-none-any.whl", hash = "sha256:a7bb560c8aee30f9957e5f9895805edd20602f2d7f720186dfd906e82b4982e1", size = 37286 }, + { url = "https://files.pythonhosted.org/packages/af/b5/123f13c975e9f27ab9c0770f514345bd406d0e8d3b7a0723af9d43f710af/wcwidth-0.2.14-py2.py3-none-any.whl", hash = "sha256:a7bb560c8aee30f9957e5f9895805edd20602f2d7f720186dfd906e82b4982e1", size = 37286, upload-time = "2025-09-22T16:29:51.641Z" }, ] [[package]]