Merge branch 'main' into fix/dark-mode-graph-text-colors

.github/workflows/docker-publish.yml

@@ -35,6 +35,18 @@ jobs:
           echo "Found tag: $TAG"
           echo "tag=$TAG" >> $GITHUB_OUTPUT
 
+      - name: Check if pre-release
+        id: check_prerelease
+        run: |
+          TAG="${{ steps.get_tag.outputs.tag }}"
+          if [[ "$TAG" == *"rc"* ]] || [[ "$TAG" == *"dev"* ]]; then
+            echo "is_prerelease=true" >> $GITHUB_OUTPUT
+            echo "This is a pre-release version: $TAG"
+          else
+            echo "is_prerelease=false" >> $GITHUB_OUTPUT
+            echo "This is a stable release: $TAG"
+          fi
+
       - name: Update version in __init__.py
         run: |
           sed -i "s/__version__ = \".*\"/__version__ = \"${{ steps.get_tag.outputs.tag }}\"/" lightrag/__init__.py
@@ -48,7 +60,7 @@ jobs:
           images: ghcr.io/${{ github.repository }}
           tags: |
             type=raw,value=${{ steps.get_tag.outputs.tag }}
-            type=raw,value=latest
+            type=raw,value=latest,enable=${{ steps.check_prerelease.outputs.is_prerelease == 'false' }}
 
       - name: Build and push Docker image
         uses: docker/build-push-action@v5

README-zh.md

@@ -335,15 +335,12 @@ class QueryParam:
     ll_keywords: list[str] = field(default_factory=list)
     """List of low-level keywords to refine retrieval focus."""
 
+    # History mesages is only send to LLM for context, not used for retrieval
     conversation_history: list[dict[str, str]] = field(default_factory=list)
     """Stores past conversation history to maintain context.
     Format: [{"role": "user/assistant", "content": "message"}].
     """
 
-    # Deprated: history message have negtive effect on query performance
-    history_turns: int = 0
-    """Number of complete conversation turns (user-assistant pairs) to consider in the response context."""
-
     ids: list[str] | None = None
     """List of ids to filter the results."""
 
@@ -355,7 +352,8 @@ class QueryParam:
 
     user_prompt: str | None = None
     """User-provided prompt for the query.
-    If proivded, this will be use instead of the default vaulue from prompt template.
+    Addition instructions for LLM. If provided, this will be inject into the prompt template.
+    It's purpose is the let user customize the way LLM generate the response.
     """
 
     enable_rerank: bool = True

README.md

@@ -336,15 +336,12 @@ class QueryParam:
     max_total_tokens: int = int(os.getenv("MAX_TOTAL_TOKENS", "30000"))
     """Maximum total tokens budget for the entire query context (entities + relations + chunks + system prompt)."""
 
+    # History mesages is only send to LLM for context, not used for retrieval
     conversation_history: list[dict[str, str]] = field(default_factory=list)
     """Stores past conversation history to maintain context.
     Format: [{"role": "user/assistant", "content": "message"}].
     """
 
-    # Deprated: history message have negtive effect on query performance
-    history_turns: int = 0
-    """Number of complete conversation turns (user-assistant pairs) to consider in the response context."""
-
     ids: list[str] | None = None
     """List of ids to filter the results."""
 
@@ -356,7 +353,8 @@ class QueryParam:
 
     user_prompt: str | None = None
     """User-provided prompt for the query.
-    If proivded, this will be use instead of the default vaulue from prompt template.
+    Addition instructions for LLM. If provided, this will be inject into the prompt template.
+    It's purpose is the let user customize the way LLM generate the response.
     """
 
     enable_rerank: bool = True

env.example

@@ -125,7 +125,7 @@ ENABLE_LLM_CACHE_FOR_EXTRACT=true
 SUMMARY_LANGUAGE=English
 
 ### Entity types that the LLM will attempt to recognize
-# ENTITY_TYPES='["Person", "Organization", "Location", "Event", "Concept", "Method", "Content", "Data", "Artifact", "NaturalObject"]'
+# ENTITY_TYPES='["Person", "Creature", "Organization", "Location", "Event", "Concept", "Method", "Content", "Data", "Artifact", "NaturalObject"]'
 
 ### Chunk size for document splitting, 500~1500 is recommended
 # CHUNK_SIZE=1200
@@ -175,6 +175,8 @@ LLM_BINDING_API_KEY=your_api_key
 # LLM_BINDING=openai
 
 ### OpenAI Compatible API Specific Parameters
+### Increased temperature values may mitigate infinite inference loops in certain LLM, such as Qwen3-30B.
+# OPENAI_LLM_TEMPERATURE=0.9
 ### Set the max_tokens to mitigate endless output of some LLM (less than LLM_TIMEOUT * llm_output_tokens/second, i.e. 9000 = 180s * 50 tokens/s)
 ### Typically, max_tokens does not include prompt content, though some models, such as Gemini Models, are exceptions
 ### For vLLM/SGLang doployed models, or most of OpenAI compatible API provider
@@ -183,17 +185,19 @@ LLM_BINDING_API_KEY=your_api_key
 OPENAI_LLM_MAX_COMPLETION_TOKENS=9000
 
 #### OpenAI's new API utilizes max_completion_tokens instead of max_tokens
-# OPENAI_LLM_MAX_TOKENS=9000
 # OPENAI_LLM_MAX_COMPLETION_TOKENS=9000
 
+### use the following command to see all support options for OpenAI, azure_openai or OpenRouter
+### lightrag-server --llm-binding openai --help
+### OpenAI Specific Parameters
+# OPENAI_LLM_REASONING_EFFORT=minimal
 ### OpenRouter Specific Parameters
 # OPENAI_LLM_EXTRA_BODY='{"reasoning": {"enabled": false}}'
 ### Qwen3 Specific Parameters depoly by vLLM
 # OPENAI_LLM_EXTRA_BODY='{"chat_template_kwargs": {"enable_thinking": false}}'
 
-### use the following command to see all support options for OpenAI, azure_openai or OpenRouter
-### lightrag-server --llm-binding openai --help
-
+### use the following command to see all support options for Ollama LLM
+### lightrag-server --llm-binding ollama --help
 ### Ollama Server Specific Parameters
 ### OLLAMA_LLM_NUM_CTX must be provided, and should at least larger than MAX_TOTAL_TOKENS + 2000
 OLLAMA_LLM_NUM_CTX=32768
@@ -201,8 +205,6 @@ OLLAMA_LLM_NUM_CTX=32768
 # OLLAMA_LLM_NUM_PREDICT=9000
 ### Stop sequences for Ollama LLM
 # OLLAMA_LLM_STOP='["</s>", "<|EOT|>"]'
-### use the following command to see all support options for Ollama LLM
-### lightrag-server --llm-binding ollama --help
 
 ### Bedrock Specific Parameters
 # BEDROCK_LLM_TEMPERATURE=1.0
@@ -312,7 +314,7 @@ POSTGRES_IVFFLAT_LISTS=100
 NEO4J_URI=neo4j+s://xxxxxxxx.databases.neo4j.io
 NEO4J_USERNAME=neo4j
 NEO4J_PASSWORD='your_password'
-NEO4J_DATABASE=noe4j
+NEO4J_DATABASE=neo4j
 NEO4J_MAX_CONNECTION_POOL_SIZE=100
 NEO4J_CONNECTION_TIMEOUT=30
 NEO4J_CONNECTION_ACQUISITION_TIMEOUT=30

lightrag/__init__.py

@@ -1,5 +1,5 @@
 from .lightrag import LightRAG as LightRAG, QueryParam as QueryParam
 
-__version__ = "1.4.8.1"
+__version__ = "1.4.9.1"
 __author__ = "Zirui Guo"
 __url__ = "https://github.com/HKUDS/LightRAG"

lightrag/api/README-zh.md

@@ -140,18 +140,6 @@ docker compose up
 ```
 > 可以通过以下链接获取官方的docker compose文件：[docker-compose.yml]( https://raw.githubusercontent.com/HKUDS/LightRAG/refs/heads/main/docker-compose.yml) 。如需获取LightRAG的历史版本镜像，可以访问以下链接: [LightRAG Docker Images]( https://github.com/HKUDS/LightRAG/pkgs/container/lightrag)
 
-### 启动时自动扫描
-
-当使用 `--auto-scan-at-startup` 参数启动LightRAG Server时，系统将自动：
-
-1. 扫描输入目录中的新文件
-2. 为尚未在数据库中的新文档建立索引
-3. 使所有内容立即可用于 RAG 查询
-
-这种工作模式给启动一个临时的RAG任务提供给了方便。
-
-> `--input-dir` 参数指定要扫描的输入目录。您可以从 webui 触发输入目录扫描。
-
 ### 启动多个LightRAG实例
 
 有两种方式可以启动多个LightRAG实例。第一种方式是为每个实例配置一个完全独立的工作环境。此时需要为每个实例创建一个独立的工作目录，然后在这个工作目录上放置一个当前实例专用的`.env`配置文件。不同实例的配置文件中的服务器监听端口不能重复，然后在工作目录上执行 lightrag-server 启动服务即可。
@@ -290,7 +278,17 @@ LIGHTRAG_API_KEY=your-secure-api-key-here
 WHITELIST_PATHS=/health,/api/*
 ```
 
-> 健康检查和 Ollama 模拟端点默认不进行 API 密钥检查。
+> 健康检查和 Ollama 模拟端点默认不进行 API 密钥检查。为了安全原因，如果不需要提供Ollama服务，应该把`/api/*`从WHITELIST_PATHS中移除。
+
+API Key使用的请求头是 `X-API-Key` 。以下是使用API访问LightRAG Server的一个例子：
+
+```
+curl -X 'POST' \
+  'http://localhost:9621/documents/scan' \
+  -H 'accept: application/json' \
+  -H 'X-API-Key: your-secure-api-key-here-123' \
+  -d ''
+```
 
 * 账户凭证（Web 界面需要登录后才能访问）
 
@@ -432,7 +430,6 @@ LIGHTRAG_DOC_STATUS_STORAGE=PGDocStatusStorage
 | --ssl-keyfile | None | SSL 私钥文件路径（如果启用 --ssl 则必需） |
 | --llm-binding | ollama | LLM 绑定类型（lollms、ollama、openai、openai-ollama、azure_openai、aws_bedrock） |
 | --embedding-binding | ollama | 嵌入绑定类型（lollms、ollama、openai、azure_openai、aws_bedrock） |
-| auto-scan-at-startup | - | 扫描输入目录中的新文件并开始索引 |
 
 ### Reranking 配置
 

lightrag/api/README.md

@@ -143,18 +143,6 @@ docker compose up
 
 > You can get the official docker compose file from here: [docker-compose.yml](https://raw.githubusercontent.com/HKUDS/LightRAG/refs/heads/main/docker-compose.yml). For historical versions of LightRAG docker images, visit this link: [LightRAG Docker Images](https://github.com/HKUDS/LightRAG/pkgs/container/lightrag)
 
-### Auto scan on startup
-
-When starting the LightRAG Server with the `--auto-scan-at-startup` parameter, the system will automatically:
-
-1. Scan for new files in the input directory
-2. Index new documents that aren't already in the database
-3. Make all content immediately available for RAG queries
-
-This offers an efficient method for deploying ad-hoc RAG processes.
-
-> The `--input-dir` parameter specifies the input directory to scan. You can trigger the input directory scan from the Web UI.
-
 ### Starting Multiple LightRAG Instances
 
 There are two ways to start multiple LightRAG instances. The first way is to configure a completely independent working environment for each instance. This requires creating a separate working directory for each instance and placing a dedicated `.env` configuration file in that directory. The server listening ports in the configuration files of different instances cannot be the same. Then, you can start the service by running `lightrag-server` in the working directory.
@@ -292,7 +280,17 @@ LIGHTRAG_API_KEY=your-secure-api-key-here
 WHITELIST_PATHS=/health,/api/*
 ```
 
-> Health check and Ollama emulation endpoints are excluded from API Key check by default.
+> Health check and Ollama emulation endpoints are excluded from API Key check by default. For security reasons, remove `/api/*` from `WHITELIST_PATHS` if the Ollama service is not required.
+
+The API key is passed using the request header `X-API-Key`. Below is an example of accessing the LightRAG Server via API:
+
+```
+curl -X 'POST' \
+  'http://localhost:9621/documents/scan' \
+  -H 'accept: application/json' \
+  -H 'X-API-Key: your-secure-api-key-here-123' \
+  -d ''
+```
 
 * Account credentials (the Web UI requires login before access can be granted):
 
@@ -434,7 +432,6 @@ You cannot change storage implementation selection after adding documents to Lig
 | --ssl-keyfile         | None          | Path to SSL private key file (required if --ssl is enabled)                                                                     |
 | --llm-binding         | ollama        | LLM binding type (lollms, ollama, openai, openai-ollama, azure_openai, aws_bedrock)                                                          |
 | --embedding-binding   | ollama        | Embedding binding type (lollms, ollama, openai, azure_openai, aws_bedrock)                                                                   |
-| --auto-scan-at-startup| -             | Scan input directory for new files and start indexing                                                                           |
 
 ### Reranking Configuration
 

lightrag/api/__init__.py

@@ -1 +1 @@
-__api_version__ = "0222"
+__api_version__ = "0235"

lightrag/api/config.py

@@ -206,13 +206,6 @@ def parse_args() -> argparse.Namespace:
         help="Default workspace for all storage",
     )
 
-    parser.add_argument(
-        "--auto-scan-at-startup",
-        action="store_true",
-        default=False,
-        help="Enable automatic scanning when the program starts",
-    )
-
     # Server workers configuration
     parser.add_argument(
         "--workers",

lightrag/api/lightrag_server.py

@@ -2,8 +2,9 @@
 LightRAG FastAPI Server
 """
 
-from fastapi import FastAPI, Depends, HTTPException
-import asyncio
+from fastapi import FastAPI, Depends, HTTPException, Request
+from fastapi.exceptions import RequestValidationError
+from fastapi.responses import JSONResponse
 import os
 import logging
 import logging.config
@@ -45,7 +46,6 @@ from lightrag.constants import (
 from lightrag.api.routers.document_routes import (
     DocumentManager,
     create_document_routes,
-    run_scanning_process,
 )
 from lightrag.api.routers.query_routes import create_query_routes
 from lightrag.api.routers.graph_routes import create_graph_routes
@@ -54,7 +54,6 @@ from lightrag.api.routers.ollama_api import OllamaAPI
 from lightrag.utils import logger, set_verbose_debug
 from lightrag.kg.shared_storage import (
     get_namespace_data,
-    get_pipeline_status_lock,
     initialize_pipeline_status,
     cleanup_keyed_lock,
     finalize_share_data,
@@ -212,24 +211,6 @@ def create_app(args):
             # Data migration regardless of storage implementation
             await rag.check_and_migrate_data()
 
-            pipeline_status = await get_namespace_data("pipeline_status")
-
-            should_start_autoscan = False
-            async with get_pipeline_status_lock():
-                # Auto scan documents if enabled
-                if args.auto_scan_at_startup:
-                    if not pipeline_status.get("autoscanned", False):
-                        pipeline_status["autoscanned"] = True
-                        should_start_autoscan = True
-
-            # Only run auto scan when no other process started it first
-            if should_start_autoscan:
-                # Create background task
-                task = asyncio.create_task(run_scanning_process(rag, doc_manager))
-                app.state.background_tasks.add(task)
-                task.add_done_callback(app.state.background_tasks.discard)
-                logger.info(f"Process {os.getpid()} auto scan task started at startup.")
-
             ASCIIColors.green("\nServer is ready to accept connections! 🚀\n")
 
             yield
@@ -266,6 +247,35 @@ def create_app(args):
 
     app = FastAPI(**app_kwargs)
 
+    # Add custom validation error handler for /query/data endpoint
+    @app.exception_handler(RequestValidationError)
+    async def validation_exception_handler(
+        request: Request, exc: RequestValidationError
+    ):
+        # Check if this is a request to /query/data endpoint
+        if request.url.path.endswith("/query/data"):
+            # Extract error details
+            error_details = []
+            for error in exc.errors():
+                field_path = " -> ".join(str(loc) for loc in error["loc"])
+                error_details.append(f"{field_path}: {error['msg']}")
+
+            error_message = "; ".join(error_details)
+
+            # Return in the expected format for /query/data
+            return JSONResponse(
+                status_code=400,
+                content={
+                    "status": "failure",
+                    "message": f"Validation error: {error_message}",
+                    "data": {},
+                    "metadata": {},
+                },
+            )
+        else:
+            # For other endpoints, return the default FastAPI validation error
+            return JSONResponse(status_code=422, content={"detail": exc.errors()})
+
     def get_cors_origins():
         """Get allowed origins from global_args
         Returns a list of allowed origins, defaults to ["*"] if not set

lightrag/api/routers/document_routes.py

@@ -745,6 +745,60 @@ class DocumentManager:
         return any(filename.lower().endswith(ext) for ext in self.supported_extensions)
 
 
+def validate_file_path_security(file_path_str: str, base_dir: Path) -> Optional[Path]:
+    """
+    Validate file path security to prevent Path Traversal attacks.
+
+    Args:
+        file_path_str: The file path string to validate
+        base_dir: The base directory that the file must be within
+
+    Returns:
+        Path: Safe file path if valid, None if unsafe or invalid
+    """
+    if not file_path_str or not file_path_str.strip():
+        return None
+
+    try:
+        # Clean the file path string
+        clean_path_str = file_path_str.strip()
+
+        # Check for obvious path traversal patterns before processing
+        # This catches both Unix (..) and Windows (..\) style traversals
+        if ".." in clean_path_str:
+            # Additional check for Windows-style backslash traversal
+            if (
+                "\\..\\" in clean_path_str
+                or clean_path_str.startswith("..\\")
+                or clean_path_str.endswith("\\..")
+            ):
+                # logger.warning(
+                #     f"Security violation: Windows path traversal attempt detected - {file_path_str}"
+                # )
+                return None
+
+        # Normalize path separators (convert backslashes to forward slashes)
+        # This helps handle Windows-style paths on Unix systems
+        normalized_path = clean_path_str.replace("\\", "/")
+
+        # Create path object and resolve it (handles symlinks and relative paths)
+        candidate_path = (base_dir / normalized_path).resolve()
+        base_dir_resolved = base_dir.resolve()
+
+        # Check if the resolved path is within the base directory
+        if not candidate_path.is_relative_to(base_dir_resolved):
+            # logger.warning(
+            #     f"Security violation: Path traversal attempt detected - {file_path_str}"
+            # )
+            return None
+
+        return candidate_path
+
+    except (OSError, ValueError, Exception) as e:
+        logger.warning(f"Invalid file path detected: {file_path_str} - {str(e)}")
+        return None
+
+
 def get_unique_filename_in_enqueued(target_dir: Path, original_name: str) -> str:
     """Generate a unique filename in the target directory by adding numeric suffixes if needed
 
@@ -1341,9 +1395,37 @@ async def run_scanning_process(
         logger.info(f"Found {total_files} files to index.")
 
         if new_files:
-            # Process all files at once with track_id
-            await pipeline_index_files(rag, new_files, track_id)
-            logger.info(f"Scanning process completed: {total_files} files Processed.")
+            # Check for files with PROCESSED status and filter them out
+            valid_files = []
+            processed_files = []
+
+            for file_path in new_files:
+                filename = file_path.name
+                existing_doc_data = await rag.doc_status.get_doc_by_file_path(filename)
+
+                if existing_doc_data and existing_doc_data.get("status") == "processed":
+                    # File is already PROCESSED, skip it with warning
+                    processed_files.append(filename)
+                    logger.warning(f"Skipping already processed file: {filename}")
+                else:
+                    # File is new or in non-PROCESSED status, add to processing list
+                    valid_files.append(file_path)
+
+            # Process valid files (new files + non-PROCESSED status files)
+            if valid_files:
+                await pipeline_index_files(rag, valid_files, track_id)
+                if processed_files:
+                    logger.info(
+                        f"Scanning process completed: {len(valid_files)} files Processed {len(processed_files)} skipped."
+                    )
+                else:
+                    logger.info(
+                        f"Scanning process completed: {len(valid_files)} files Processed."
+                    )
+            else:
+                logger.info(
+                    "No files to process after filtering already processed files."
+                )
         else:
             # No new files to index, check if there are any documents in the queue
             logger.info(
@@ -1429,51 +1511,37 @@ async def background_delete_documents(
                     ):
                         try:
                             deleted_files = []
-                            # check and delete files from input_dir directory
-                            file_path = doc_manager.input_dir / result.file_path
-                            if file_path.exists():
-                                try:
-                                    file_path.unlink()
-                                    deleted_files.append(file_path.name)
-                                    file_delete_msg = f"Successfully deleted input_dir file: {result.file_path}"
-                                    logger.info(file_delete_msg)
-                                    async with pipeline_status_lock:
-                                        pipeline_status["latest_message"] = (
-                                            file_delete_msg
-                                        )
-                                        pipeline_status["history_messages"].append(
-                                            file_delete_msg
-                                        )
-                                except Exception as file_error:
-                                    file_error_msg = f"Failed to delete input_dir file {result.file_path}: {str(file_error)}"
-                                    logger.debug(file_error_msg)
-                                    async with pipeline_status_lock:
-                                        pipeline_status["latest_message"] = (
-                                            file_error_msg
-                                        )
-                                        pipeline_status["history_messages"].append(
-                                            file_error_msg
-                                        )
+                            # SECURITY FIX: Use secure path validation to prevent arbitrary file deletion
+                            safe_file_path = validate_file_path_security(
+                                result.file_path, doc_manager.input_dir
+                            )
 
-                            # Also check and delete files from __enqueued__ directory
-                            enqueued_dir = doc_manager.input_dir / "__enqueued__"
-                            if enqueued_dir.exists():
-                                # Look for files with the same name or similar names (with numeric suffixes)
-                                base_name = Path(result.file_path).stem
-                                extension = Path(result.file_path).suffix
-
-                                # Search for exact match and files with numeric suffixes
-                                for enqueued_file in enqueued_dir.glob(
-                                    f"{base_name}*{extension}"
-                                ):
+                            if safe_file_path is None:
+                                # Security violation detected - log and skip file deletion
+                                security_msg = f"Security violation: Unsafe file path detected for deletion - {result.file_path}"
+                                logger.warning(security_msg)
+                                async with pipeline_status_lock:
+                                    pipeline_status["latest_message"] = security_msg
+                                    pipeline_status["history_messages"].append(
+                                        security_msg
+                                    )
+                            else:
+                                # check and delete files from input_dir directory
+                                if safe_file_path.exists():
                                     try:
-                                        enqueued_file.unlink()
-                                        deleted_files.append(enqueued_file.name)
-                                        logger.info(
-                                            f"Successfully deleted enqueued file: {enqueued_file.name}"
-                                        )
-                                    except Exception as enqueued_error:
-                                        file_error_msg = f"Failed to delete enqueued file {enqueued_file.name}: {str(enqueued_error)}"
+                                        safe_file_path.unlink()
+                                        deleted_files.append(safe_file_path.name)
+                                        file_delete_msg = f"Successfully deleted input_dir file: {result.file_path}"
+                                        logger.info(file_delete_msg)
+                                        async with pipeline_status_lock:
+                                            pipeline_status["latest_message"] = (
+                                                file_delete_msg
+                                            )
+                                            pipeline_status["history_messages"].append(
+                                                file_delete_msg
+                                            )
+                                    except Exception as file_error:
+                                        file_error_msg = f"Failed to delete input_dir file {result.file_path}: {str(file_error)}"
                                         logger.debug(file_error_msg)
                                         async with pipeline_status_lock:
                                             pipeline_status["latest_message"] = (
@@ -1483,8 +1551,47 @@ async def background_delete_documents(
                                                 file_error_msg
                                             )
 
+                                # Also check and delete files from __enqueued__ directory
+                                enqueued_dir = doc_manager.input_dir / "__enqueued__"
+                                if enqueued_dir.exists():
+                                    # SECURITY FIX: Validate that the file path is safe before processing
+                                    # Only proceed if the original path validation passed
+                                    base_name = Path(result.file_path).stem
+                                    extension = Path(result.file_path).suffix
+
+                                    # Search for exact match and files with numeric suffixes
+                                    for enqueued_file in enqueued_dir.glob(
+                                        f"{base_name}*{extension}"
+                                    ):
+                                        # Additional security check: ensure enqueued file is within enqueued directory
+                                        safe_enqueued_path = (
+                                            validate_file_path_security(
+                                                enqueued_file.name, enqueued_dir
+                                            )
+                                        )
+                                        if safe_enqueued_path is not None:
+                                            try:
+                                                enqueued_file.unlink()
+                                                deleted_files.append(enqueued_file.name)
+                                                logger.info(
+                                                    f"Successfully deleted enqueued file: {enqueued_file.name}"
+                                                )
+                                            except Exception as enqueued_error:
+                                                file_error_msg = f"Failed to delete enqueued file {enqueued_file.name}: {str(enqueued_error)}"
+                                                logger.debug(file_error_msg)
+                                                async with pipeline_status_lock:
+                                                    pipeline_status[
+                                                        "latest_message"
+                                                    ] = file_error_msg
+                                                    pipeline_status[
+                                                        "history_messages"
+                                                    ].append(file_error_msg)
+                                        else:
+                                            security_msg = f"Security violation: Unsafe enqueued file path detected - {enqueued_file.name}"
+                                            logger.warning(security_msg)
+
                             if deleted_files == []:
-                                file_error_msg = f"File deletion skipped, missing file: {result.file_path}"
+                                file_error_msg = f"File deletion skipped, missing or unsafe file: {result.file_path}"
                                 logger.warning(file_error_msg)
                                 async with pipeline_status_lock:
                                     pipeline_status["latest_message"] = file_error_msg
@@ -1618,8 +1725,19 @@ def create_document_routes(
                     detail=f"Unsupported file type. Supported types: {doc_manager.supported_extensions}",
                 )
 
+            # Check if filename already exists in doc_status storage
+            existing_doc_data = await rag.doc_status.get_doc_by_file_path(safe_filename)
+            if existing_doc_data:
+                # Get document status information for error message
+                status = existing_doc_data.get("status", "unknown")
+                return InsertResponse(
+                    status="duplicated",
+                    message=f"File '{safe_filename}' already exists in document storage (Status: {status}).",
+                    track_id="",
+                )
+
             file_path = doc_manager.input_dir / safe_filename
-            # Check if file already exists
+            # Check if file already exists in file system
             if file_path.exists():
                 return InsertResponse(
                     status="duplicated",
@@ -1669,6 +1787,24 @@ def create_document_routes(
             HTTPException: If an error occurs during text processing (500).
         """
         try:
+            # Check if file_source already exists in doc_status storage
+            if (
+                request.file_source
+                and request.file_source.strip()
+                and request.file_source != "unknown_source"
+            ):
+                existing_doc_data = await rag.doc_status.get_doc_by_file_path(
+                    request.file_source
+                )
+                if existing_doc_data:
+                    # Get document status information for error message
+                    status = existing_doc_data.get("status", "unknown")
+                    return InsertResponse(
+                        status="duplicated",
+                        message=f"File source '{request.file_source}' already exists in document storage (Status: {status}).",
+                        track_id="",
+                    )
+
             # Generate track_id for text insertion
             track_id = generate_track_id("insert")
 
@@ -1715,6 +1851,26 @@ def create_document_routes(
             HTTPException: If an error occurs during text processing (500).
         """
         try:
+            # Check if any file_sources already exist in doc_status storage
+            if request.file_sources:
+                for file_source in request.file_sources:
+                    if (
+                        file_source
+                        and file_source.strip()
+                        and file_source != "unknown_source"
+                    ):
+                        existing_doc_data = await rag.doc_status.get_doc_by_file_path(
+                            file_source
+                        )
+                        if existing_doc_data:
+                            # Get document status information for error message
+                            status = existing_doc_data.get("status", "unknown")
+                            return InsertResponse(
+                                status="duplicated",
+                                message=f"File source '{file_source}' already exists in document storage (Status: {status}).",
+                                track_id="",
+                            )
+
             # Generate track_id for texts insertion
             track_id = generate_track_id("insert")
 
@@ -2017,20 +2173,24 @@ def create_document_routes(
             logger.error(traceback.format_exc())
             raise HTTPException(status_code=500, detail=str(e))
 
+    # TODO: Deprecated
     @router.get(
         "", response_model=DocsStatusesResponse, dependencies=[Depends(combined_auth)]
     )
     async def documents() -> DocsStatusesResponse:
         """
-        Get the status of all documents in the system.
+        Get the status of all documents in the system. This endpoint is deprecated; use /documents/paginated instead.
+        To prevent excessive resource consumption, a maximum of 1,000 records is returned.
 
         This endpoint retrieves the current status of all documents, grouped by their
-        processing status (PENDING, PROCESSING, PROCESSED, FAILED).
+        processing status (PENDING, PROCESSING, PROCESSED, FAILED). The results are
+        limited to 1000 total documents with fair distribution across all statuses.
 
         Returns:
             DocsStatusesResponse: A response object containing a dictionary where keys are
                                 DocStatus values and values are lists of DocStatusResponse
                                 objects representing documents in each status category.
+                                Maximum 1000 documents total will be returned.
 
         Raises:
             HTTPException: If an error occurs while retrieving document statuses (500).
@@ -2047,12 +2207,45 @@ def create_document_routes(
             results: List[Dict[str, DocProcessingStatus]] = await asyncio.gather(*tasks)
 
             response = DocsStatusesResponse()
+            total_documents = 0
+            max_documents = 1000
 
+            # Convert results to lists for easier processing
+            status_documents = []
             for idx, result in enumerate(results):
                 status = statuses[idx]
+                docs_list = []
                 for doc_id, doc_status in result.items():
+                    docs_list.append((doc_id, doc_status))
+                status_documents.append((status, docs_list))
+
+            # Fair distribution: round-robin across statuses
+            status_indices = [0] * len(
+                status_documents
+            )  # Track current index for each status
+            current_status_idx = 0
+
+            while total_documents < max_documents:
+                # Check if we have any documents left to process
+                has_remaining = False
+                for status_idx, (status, docs_list) in enumerate(status_documents):
+                    if status_indices[status_idx] < len(docs_list):
+                        has_remaining = True
+                        break
+
+                if not has_remaining:
+                    break
+
+                # Try to get a document from the current status
+                status, docs_list = status_documents[current_status_idx]
+                current_index = status_indices[current_status_idx]
+
+                if current_index < len(docs_list):
+                    doc_id, doc_status = docs_list[current_index]
+
                     if status not in response.statuses:
                         response.statuses[status] = []
+
                     response.statuses[status].append(
                         DocStatusResponse(
                             id=doc_id,
@@ -2068,6 +2261,13 @@ def create_document_routes(
                             file_path=doc_status.file_path,
                         )
                     )
+
+                    status_indices[current_status_idx] += 1
+                    total_documents += 1
+
+                # Move to next status (round-robin)
+                current_status_idx = (current_status_idx + 1) % len(status_documents)
+
             return response
         except Exception as e:
             logger.error(f"Error GET /documents: {str(e)}")

lightrag/api/routers/graph_routes.py

@@ -45,6 +45,56 @@ def create_graph_routes(rag, api_key: Optional[str] = None):
                 status_code=500, detail=f"Error getting graph labels: {str(e)}"
             )
 
+    @router.get("/graph/label/popular", dependencies=[Depends(combined_auth)])
+    async def get_popular_labels(
+        limit: int = Query(
+            300, description="Maximum number of popular labels to return", ge=1, le=1000
+        ),
+    ):
+        """
+        Get popular labels by node degree (most connected entities)
+
+        Args:
+            limit (int): Maximum number of labels to return (default: 300, max: 1000)
+
+        Returns:
+            List[str]: List of popular labels sorted by degree (highest first)
+        """
+        try:
+            return await rag.chunk_entity_relation_graph.get_popular_labels(limit)
+        except Exception as e:
+            logger.error(f"Error getting popular labels: {str(e)}")
+            logger.error(traceback.format_exc())
+            raise HTTPException(
+                status_code=500, detail=f"Error getting popular labels: {str(e)}"
+            )
+
+    @router.get("/graph/label/search", dependencies=[Depends(combined_auth)])
+    async def search_labels(
+        q: str = Query(..., description="Search query string"),
+        limit: int = Query(
+            50, description="Maximum number of search results to return", ge=1, le=100
+        ),
+    ):
+        """
+        Search labels with fuzzy matching
+
+        Args:
+            q (str): Search query string
+            limit (int): Maximum number of results to return (default: 50, max: 100)
+
+        Returns:
+            List[str]: List of matching labels sorted by relevance
+        """
+        try:
+            return await rag.chunk_entity_relation_graph.search_labels(q, limit)
+        except Exception as e:
+            logger.error(f"Error searching labels with query '{q}': {str(e)}")
+            logger.error(traceback.format_exc())
+            raise HTTPException(
+                status_code=500, detail=f"Error searching labels: {str(e)}"
+            )
+
     @router.get("/graphs", dependencies=[Depends(combined_auth)])
     async def get_knowledge_graph(
         label: str = Query(..., description="Label to get knowledge graph for"),

lightrag/api/routers/ollama_api.py

@@ -483,6 +483,12 @@ class OllamaAPI:
                 if not messages:
                     raise HTTPException(status_code=400, detail="No messages provided")
 
+                # Validate that the last message is from a user
+                if messages[-1].role != "user":
+                    raise HTTPException(
+                        status_code=400, detail="Last message must be from user role"
+                    )
+
                 # Get the last message as query and previous messages as history
                 query = messages[-1].content
                 # Convert OllamaMessage objects to dictionaries
@@ -499,7 +505,7 @@ class OllamaAPI:
                 prompt_tokens = estimate_tokens(cleaned_query)
 
                 param_dict = {
-                    "mode": mode,
+                    "mode": mode.value,
                     "stream": request.stream,
                     "only_need_context": only_need_context,
                     "conversation_history": conversation_history,
@@ -510,12 +516,6 @@ class OllamaAPI:
                 if user_prompt is not None:
                     param_dict["user_prompt"] = user_prompt
 
-                if (
-                    hasattr(self.rag, "args")
-                    and self.rag.args.history_turns is not None
-                ):
-                    param_dict["history_turns"] = self.rag.args.history_turns
-
                 query_param = QueryParam(**param_dict)
 
                 if request.stream:

lightrag/api/utils_api.py

@@ -218,8 +218,6 @@ def display_splash_screen(args: argparse.Namespace) -> None:
     ASCIIColors.yellow(f"{args.log_level}")
     ASCIIColors.white("    ├─ Verbose Debug: ", end="")
     ASCIIColors.yellow(f"{args.verbose}")
-    ASCIIColors.white("    ├─ History Turns: ", end="")
-    ASCIIColors.yellow(f"{args.history_turns}")
     ASCIIColors.white("    ├─ API Key: ", end="")
     ASCIIColors.yellow("Set" if args.key else "Not Set")
     ASCIIColors.white("    └─ JWT Auth: ", end="")

lightrag/api/webui/assets/_basePickBy-4-C6UZHi.js

@@ -1 +0,0 @@
-import{e as v,c as b,g as m,k as O,h as P,j as p,l as w,m as c,n as x,t as A,o as N}from"./_baseUniq-CN7ubuxw.js";import{aU as g,aq as _,aV as $,aW as E,aX as F,aY as I,aZ as M,a_ as y,a$ as B,b0 as T}from"./mermaid-vendor-CuJcWrH0.js";var S=/\s/;function q(n){for(var r=n.length;r--&&S.test(n.charAt(r)););return r}var G=/^\s+/;function H(n){return n&&n.slice(0,q(n)+1).replace(G,"")}var o=NaN,L=/^[-+]0x[0-9a-f]+$/i,R=/^0b[01]+$/i,W=/^0o[0-7]+$/i,X=parseInt;function Y(n){if(typeof n=="number")return n;if(v(n))return o;if(g(n)){var r=typeof n.valueOf=="function"?n.valueOf():n;n=g(r)?r+"":r}if(typeof n!="string")return n===0?n:+n;n=H(n);var t=R.test(n);return t||W.test(n)?X(n.slice(2),t?2:8):L.test(n)?o:+n}var z=1/0,C=17976931348623157e292;function K(n){if(!n)return n===0?n:0;if(n=Y(n),n===z||n===-1/0){var r=n<0?-1:1;return r*C}return n===n?n:0}function U(n){var r=K(n),t=r%1;return r===r?t?r-t:r:0}function fn(n){var r=n==null?0:n.length;return r?b(n):[]}var l=Object.prototype,Z=l.hasOwnProperty,dn=_(function(n,r){n=Object(n);var t=-1,e=r.length,a=e>2?r[2]:void 0;for(a&&$(r[0],r[1],a)&&(e=1);++t<e;)for(var f=r[t],i=E(f),s=-1,d=i.length;++s<d;){var u=i[s],h=n[u];(h===void 0||F(h,l[u])&&!Z.call(n,u))&&(n[u]=f[u])}return n});function un(n){var r=n==null?0:n.length;return r?n[r-1]:void 0}function D(n){return function(r,t,e){var a=Object(r);if(!I(r)){var f=m(t);r=O(r),t=function(s){return f(a[s],s,a)}}var i=n(r,t,e);return i>-1?a[f?r[i]:i]:void 0}}var J=Math.max;function Q(n,r,t){var e=n==null?0:n.length;if(!e)return-1;var a=t==null?0:U(t);return a<0&&(a=J(e+a,0)),P(n,m(r),a)}var hn=D(Q);function V(n,r){var t=-1,e=I(n)?Array(n.length):[];return p(n,function(a,f,i){e[++t]=r(a,f,i)}),e}function gn(n,r){var t=M(n)?w:V;return t(n,m(r))}var j=Object.prototype,k=j.hasOwnProperty;function nn(n,r){return n!=null&&k.call(n,r)}function mn(n,r){return n!=null&&c(n,r,nn)}function rn(n,r){return n<r}function tn(n,r,t){for(var e=-1,a=n.length;++e<a;){var f=n[e],i=r(f);if(i!=null&&(s===void 0?i===i&&!v(i):t(i,s)))var s=i,d=f}return d}function on(n){return n&&n.length?tn(n,y,rn):void 0}function an(n,r,t,e){if(!g(n))return n;r=x(r,n);for(var a=-1,f=r.length,i=f-1,s=n;s!=null&&++a<f;){var d=A(r[a]),u=t;if(d==="__proto__"||d==="constructor"||d==="prototype")return n;if(a!=i){var h=s[d];u=void 0,u===void 0&&(u=g(h)?h:B(r[a+1])?[]:{})}T(s,d,u),s=s[d]}return n}function vn(n,r,t){for(var e=-1,a=r.length,f={};++e<a;){var i=r[e],s=N(n,i);t(s,i)&&an(f,x(i,n),s)}return f}export{rn as a,tn as b,V as c,vn as d,on as e,fn as f,hn as g,mn as h,dn as i,U as j,un as l,gn as m,K as t};

lightrag/api/webui/assets/_basePickBy-DEiY070O.js

@@ -0,0 +1 @@
+import{e as o,c as l,g as b,k as O,h as P,j as p,l as w,m as c,n as v,t as A,o as N}from"./_baseUniq-D5S4RK2K.js";import{a_ as g,aw as _,a$ as $,b0 as E,b1 as F,b2 as x,b3 as M,b4 as y,b5 as B,b6 as T}from"./mermaid-vendor-kG8Trx8h.js";var S=/\s/;function G(n){for(var r=n.length;r--&&S.test(n.charAt(r)););return r}var H=/^\s+/;function L(n){return n&&n.slice(0,G(n)+1).replace(H,"")}var m=NaN,R=/^[-+]0x[0-9a-f]+$/i,q=/^0b[01]+$/i,z=/^0o[0-7]+$/i,C=parseInt;function K(n){if(typeof n=="number")return n;if(o(n))return m;if(g(n)){var r=typeof n.valueOf=="function"?n.valueOf():n;n=g(r)?r+"":r}if(typeof n!="string")return n===0?n:+n;n=L(n);var t=q.test(n);return t||z.test(n)?C(n.slice(2),t?2:8):R.test(n)?m:+n}var W=1/0,X=17976931348623157e292;function Y(n){if(!n)return n===0?n:0;if(n=K(n),n===W||n===-1/0){var r=n<0?-1:1;return r*X}return n===n?n:0}function D(n){var r=Y(n),t=r%1;return r===r?t?r-t:r:0}function fn(n){var r=n==null?0:n.length;return r?l(n):[]}var I=Object.prototype,J=I.hasOwnProperty,dn=_(function(n,r){n=Object(n);var t=-1,e=r.length,i=e>2?r[2]:void 0;for(i&&$(r[0],r[1],i)&&(e=1);++t<e;)for(var f=r[t],a=E(f),s=-1,d=a.length;++s<d;){var u=a[s],h=n[u];(h===void 0||F(h,I[u])&&!J.call(n,u))&&(n[u]=f[u])}return n});function un(n){var r=n==null?0:n.length;return r?n[r-1]:void 0}function Q(n){return function(r,t,e){var i=Object(r);if(!x(r)){var f=b(t);r=O(r),t=function(s){return f(i[s],s,i)}}var a=n(r,t,e);return a>-1?i[f?r[a]:a]:void 0}}var U=Math.max;function Z(n,r,t){var e=n==null?0:n.length;if(!e)return-1;var i=t==null?0:D(t);return i<0&&(i=U(e+i,0)),P(n,b(r),i)}var hn=Q(Z);function V(n,r){var t=-1,e=x(n)?Array(n.length):[];return p(n,function(i,f,a){e[++t]=r(i,f,a)}),e}function gn(n,r){var t=M(n)?w:V;return t(n,b(r))}var j=Object.prototype,k=j.hasOwnProperty;function nn(n,r){return n!=null&&k.call(n,r)}function bn(n,r){return n!=null&&c(n,r,nn)}function rn(n,r){return n<r}function tn(n,r,t){for(var e=-1,i=n.length;++e<i;){var f=n[e],a=r(f);if(a!=null&&(s===void 0?a===a&&!o(a):t(a,s)))var s=a,d=f}return d}function mn(n){return n&&n.length?tn(n,y,rn):void 0}function an(n,r,t,e){if(!g(n))return n;r=v(r,n);for(var i=-1,f=r.length,a=f-1,s=n;s!=null&&++i<f;){var d=A(r[i]),u=t;if(d==="__proto__"||d==="constructor"||d==="prototype")return n;if(i!=a){var h=s[d];u=void 0,u===void 0&&(u=g(h)?h:B(r[i+1])?[]:{})}T(s,d,u),s=s[d]}return n}function on(n,r,t){for(var e=-1,i=r.length,f={};++e<i;){var a=r[e],s=N(n,a);t(s,a)&&an(f,v(a,n),s)}return f}export{rn as a,tn as b,V as c,on as d,mn as e,fn as f,hn as g,bn as h,dn as i,D as j,un as l,gn as m,Y as t};

lightrag/api/webui/assets/chunk-353BL4L5-CG4Wb5Ni.js

@@ -1 +1 @@
-import{_ as l}from"./mermaid-vendor-CuJcWrH0.js";function m(e,c){var i,t,o;e.accDescr&&((i=c.setAccDescription)==null||i.call(c,e.accDescr)),e.accTitle&&((t=c.setAccTitle)==null||t.call(c,e.accTitle)),e.title&&((o=c.setDiagramTitle)==null||o.call(c,e.title))}l(m,"populateCommonDb");export{m as p};
+import{_ as l}from"./mermaid-vendor-kG8Trx8h.js";function m(e,c){var i,t,o;e.accDescr&&((i=c.setAccDescription)==null||i.call(c,e.accDescr)),e.accTitle&&((t=c.setAccTitle)==null||t.call(c,e.accTitle)),e.title&&((o=c.setDiagramTitle)==null||o.call(c,e.title))}l(m,"populateCommonDb");export{m as p};

lightrag/api/webui/assets/chunk-67H74DCK-Bn3D4qrX.js

@@ -1 +1 @@
-import{_ as n,a1 as x,j as l}from"./mermaid-vendor-CuJcWrH0.js";var c=n((a,t)=>{const e=a.append("rect");if(e.attr("x",t.x),e.attr("y",t.y),e.attr("fill",t.fill),e.attr("stroke",t.stroke),e.attr("width",t.width),e.attr("height",t.height),t.name&&e.attr("name",t.name),t.rx&&e.attr("rx",t.rx),t.ry&&e.attr("ry",t.ry),t.attrs!==void 0)for(const r in t.attrs)e.attr(r,t.attrs[r]);return t.class&&e.attr("class",t.class),e},"drawRect"),d=n((a,t)=>{const e={x:t.startx,y:t.starty,width:t.stopx-t.startx,height:t.stopy-t.starty,fill:t.fill,stroke:t.stroke,class:"rect"};c(a,e).lower()},"drawBackgroundRect"),g=n((a,t)=>{const e=t.text.replace(x," "),r=a.append("text");r.attr("x",t.x),r.attr("y",t.y),r.attr("class","legend"),r.style("text-anchor",t.anchor),t.class&&r.attr("class",t.class);const s=r.append("tspan");return s.attr("x",t.x+t.textMargin*2),s.text(e),r},"drawText"),h=n((a,t,e,r)=>{const s=a.append("image");s.attr("x",t),s.attr("y",e);const i=l.sanitizeUrl(r);s.attr("xlink:href",i)},"drawImage"),m=n((a,t,e,r)=>{const s=a.append("use");s.attr("x",t),s.attr("y",e);const i=l.sanitizeUrl(r);s.attr("xlink:href",`#${i}`)},"drawEmbeddedImage"),y=n(()=>({x:0,y:0,width:100,height:100,fill:"#EDF2AE",stroke:"#666",anchor:"start",rx:0,ry:0}),"getNoteRect"),p=n(()=>({x:0,y:0,width:100,height:100,"text-anchor":"start",style:"#666",textMargin:0,rx:0,ry:0,tspan:!0}),"getTextObj");export{d as a,p as b,m as c,c as d,h as e,g as f,y as g};
+import{_ as n,a2 as x,j as l}from"./mermaid-vendor-kG8Trx8h.js";var c=n((a,t)=>{const e=a.append("rect");if(e.attr("x",t.x),e.attr("y",t.y),e.attr("fill",t.fill),e.attr("stroke",t.stroke),e.attr("width",t.width),e.attr("height",t.height),t.name&&e.attr("name",t.name),t.rx&&e.attr("rx",t.rx),t.ry&&e.attr("ry",t.ry),t.attrs!==void 0)for(const r in t.attrs)e.attr(r,t.attrs[r]);return t.class&&e.attr("class",t.class),e},"drawRect"),d=n((a,t)=>{const e={x:t.startx,y:t.starty,width:t.stopx-t.startx,height:t.stopy-t.starty,fill:t.fill,stroke:t.stroke,class:"rect"};c(a,e).lower()},"drawBackgroundRect"),g=n((a,t)=>{const e=t.text.replace(x," "),r=a.append("text");r.attr("x",t.x),r.attr("y",t.y),r.attr("class","legend"),r.style("text-anchor",t.anchor),t.class&&r.attr("class",t.class);const s=r.append("tspan");return s.attr("x",t.x+t.textMargin*2),s.text(e),r},"drawText"),h=n((a,t,e,r)=>{const s=a.append("image");s.attr("x",t),s.attr("y",e);const i=l.sanitizeUrl(r);s.attr("xlink:href",i)},"drawImage"),m=n((a,t,e,r)=>{const s=a.append("use");s.attr("x",t),s.attr("y",e);const i=l.sanitizeUrl(r);s.attr("xlink:href",`#${i}`)},"drawEmbeddedImage"),y=n(()=>({x:0,y:0,width:100,height:100,fill:"#EDF2AE",stroke:"#666",anchor:"start",rx:0,ry:0}),"getNoteRect"),p=n(()=>({x:0,y:0,width:100,height:100,"text-anchor":"start",style:"#666",textMargin:0,rx:0,ry:0,tspan:!0}),"getTextObj");export{d as a,p as b,m as c,c as d,h as e,g as f,y as g};

lightrag/api/webui/assets/chunk-AACKK3MU-Crxfynqn.js

@@ -1 +1 @@
-import{_ as s}from"./mermaid-vendor-CuJcWrH0.js";var t,e=(t=class{constructor(i){this.init=i,this.records=this.init()}reset(){this.records=this.init()}},s(t,"ImperativeState"),t);export{e as I};
+import{_ as s}from"./mermaid-vendor-kG8Trx8h.js";var t,e=(t=class{constructor(i){this.init=i,this.records=this.init()}reset(){this.records=this.init()}},s(t,"ImperativeState"),t);export{e as I};

lightrag/api/webui/assets/chunk-BFAMUDN2-ILoF6WWe.js

@@ -0,0 +1 @@
+import{_ as a,d as o}from"./mermaid-vendor-kG8Trx8h.js";var d=a((t,e)=>{let n;return e==="sandbox"&&(n=o("#i"+t)),(e==="sandbox"?o(n.nodes()[0].contentDocument.body):o("body")).select(`[id="${t}"]`)},"getDiagramElement");export{d as g};

lightrag/api/webui/assets/chunk-E2GYISFI-Cp-cMcdp.js

@@ -0,0 +1,15 @@
+import{_ as e}from"./mermaid-vendor-kG8Trx8h.js";var l=e(()=>`
+  /* Font Awesome icon styling - consolidated */
+  .label-icon {
+    display: inline-block;
+    height: 1em;
+    overflow: visible;
+    vertical-align: -0.125em;
+  }
+  
+  .node .label-icon path {
+    fill: currentColor;
+    stroke: revert;
+    stroke-width: revert;
+  }
+`,"getIconStyles");export{l as g};

lightrag/api/webui/assets/chunk-RZ5BOZE2-D3gEMbCJ.js

@@ -1 +0,0 @@
-import{_ as n,d as r,e as d,l as g}from"./mermaid-vendor-CuJcWrH0.js";var u=n((e,t)=>{let o;return t==="sandbox"&&(o=r("#i"+e)),(t==="sandbox"?r(o.nodes()[0].contentDocument.body):r("body")).select(`[id="${e}"]`)},"getDiagramElement"),b=n((e,t,o,i)=>{e.attr("class",o);const{width:a,height:s,x:h,y:x}=l(e,t);d(e,s,a,i);const c=w(h,x,a,s,t);e.attr("viewBox",c),g.debug(`viewBox configured: ${c} with padding: ${t}`)},"setupViewPortForSVG"),l=n((e,t)=>{var i;const o=((i=e.node())==null?void 0:i.getBBox())||{width:0,height:0,x:0,y:0};return{width:o.width+t*2,height:o.height+t*2,x:o.x,y:o.y}},"calculateDimensionsWithPadding"),w=n((e,t,o,i,a)=>`${e-a} ${t-a} ${o} ${i}`,"createViewBox");export{u as g,b as s};

lightrag/api/webui/assets/chunk-SKB7J2MH-CCgDhfF0.js

@@ -0,0 +1 @@
+import{_ as a,e as w,l as x}from"./mermaid-vendor-kG8Trx8h.js";var d=a((e,t,i,o)=>{e.attr("class",i);const{width:r,height:h,x:n,y:c}=u(e,t);w(e,h,r,o);const s=l(n,c,r,h,t);e.attr("viewBox",s),x.debug(`viewBox configured: ${s} with padding: ${t}`)},"setupViewPortForSVG"),u=a((e,t)=>{var o;const i=((o=e.node())==null?void 0:o.getBBox())||{width:0,height:0,x:0,y:0};return{width:i.width+t*2,height:i.height+t*2,x:i.x,y:i.y}},"calculateDimensionsWithPadding"),l=a((e,t,i,o,r)=>`${e-r} ${t-r} ${i} ${o}`,"createViewBox");export{d as s};

lightrag/api/webui/assets/classDiagram-GIVACNV2-BryW-IRL.js

@@ -1 +0,0 @@
-import{s as a,c as s,a as e,C as t}from"./chunk-A2AXSNBT-DGt_KYJH.js";import{_ as i}from"./mermaid-vendor-CuJcWrH0.js";import"./chunk-RZ5BOZE2-D3gEMbCJ.js";import"./feature-graph-CeEpF_Yb.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";var f={parser:e,get db(){return new t},renderer:s,styles:a,init:i(r=>{r.class||(r.class={}),r.class.arrowMarkerAbsolute=r.arrowMarkerAbsolute},"init")};export{f as diagram};

lightrag/api/webui/assets/classDiagram-M3E45YP4-Uf76G6Vz.js

@@ -0,0 +1 @@
+import{s as a,c as s,a as e,C as t}from"./chunk-SZ463SBG-BmUQcRTs.js";import{_ as i}from"./mermaid-vendor-kG8Trx8h.js";import"./chunk-E2GYISFI-Cp-cMcdp.js";import"./chunk-BFAMUDN2-ILoF6WWe.js";import"./chunk-SKB7J2MH-CCgDhfF0.js";import"./feature-graph-7h-VS-iL.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";var c={parser:e,get db(){return new t},renderer:s,styles:a,init:i(r=>{r.class||(r.class={}),r.class.arrowMarkerAbsolute=r.arrowMarkerAbsolute},"init")};export{c as diagram};

lightrag/api/webui/assets/classDiagram-v2-COTLJTTW-BryW-IRL.js

@@ -1 +0,0 @@
-import{s as a,c as s,a as e,C as t}from"./chunk-A2AXSNBT-DGt_KYJH.js";import{_ as i}from"./mermaid-vendor-CuJcWrH0.js";import"./chunk-RZ5BOZE2-D3gEMbCJ.js";import"./feature-graph-CeEpF_Yb.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";var f={parser:e,get db(){return new t},renderer:s,styles:a,init:i(r=>{r.class||(r.class={}),r.class.arrowMarkerAbsolute=r.arrowMarkerAbsolute},"init")};export{f as diagram};

lightrag/api/webui/assets/classDiagram-v2-YAWTLIQI-Uf76G6Vz.js

@@ -0,0 +1 @@
+import{s as a,c as s,a as e,C as t}from"./chunk-SZ463SBG-BmUQcRTs.js";import{_ as i}from"./mermaid-vendor-kG8Trx8h.js";import"./chunk-E2GYISFI-Cp-cMcdp.js";import"./chunk-BFAMUDN2-ILoF6WWe.js";import"./chunk-SKB7J2MH-CCgDhfF0.js";import"./feature-graph-7h-VS-iL.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";var c={parser:e,get db(){return new t},renderer:s,styles:a,init:i(r=>{r.class||(r.class={}),r.class.arrowMarkerAbsolute=r.arrowMarkerAbsolute},"init")};export{c as diagram};

lightrag/api/webui/assets/clone-D1RenvQh.js

@@ -0,0 +1 @@
+import{b as r}from"./_baseUniq-D5S4RK2K.js";var e=4;function a(o){return r(o,e)}export{a as c};

lightrag/api/webui/assets/clone-Du5yQfgG.js

@@ -1 +0,0 @@
-import{b as r}from"./_baseUniq-CN7ubuxw.js";var e=4;function a(o){return r(o,e)}export{a as c};

lightrag/api/webui/assets/diagram-5UYTHUR4-DvWfhOFV.js

@@ -0,0 +1,24 @@
+import{p as y}from"./chunk-353BL4L5-CG4Wb5Ni.js";import{_ as l,s as B,g as S,t as z,q as F,a as P,b as E,F as v,K as W,e as T,z as D,G as _,H as A,l as w}from"./mermaid-vendor-kG8Trx8h.js";import{p as N}from"./treemap-75Q7IDZK-M3vYzjwI.js";import"./feature-graph-7h-VS-iL.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";import"./_baseUniq-D5S4RK2K.js";import"./_basePickBy-DEiY070O.js";import"./clone-D1RenvQh.js";var x={packet:[]},m=structuredClone(x),L=A.packet,Y=l(()=>{const t=v({...L,..._().packet});return t.showBits&&(t.paddingY+=10),t},"getConfig"),G=l(()=>m.packet,"getPacket"),H=l(t=>{t.length>0&&m.packet.push(t)},"pushWord"),I=l(()=>{D(),m=structuredClone(x)},"clear"),u={pushWord:H,getPacket:G,getConfig:Y,clear:I,setAccTitle:E,getAccTitle:P,setDiagramTitle:F,getDiagramTitle:z,getAccDescription:S,setAccDescription:B},K=1e4,M=l(t=>{y(t,u);let e=-1,o=[],n=1;const{bitsPerRow:i}=u.getConfig();for(let{start:a,end:r,bits:c,label:f}of t.blocks){if(a!==void 0&&r!==void 0&&r<a)throw new Error(`Packet block ${a} - ${r} is invalid. End must be greater than start.`);if(a??(a=e+1),a!==e+1)throw new Error(`Packet block ${a} - ${r??a} is not contiguous. It should start from ${e+1}.`);if(c===0)throw new Error(`Packet block ${a} is invalid. Cannot have a zero bit field.`);for(r??(r=a+(c??1)-1),c??(c=r-a+1),e=r,w.debug(`Packet block ${a} - ${e} with label ${f}`);o.length<=i+1&&u.getPacket().length<K;){const[d,p]=O({start:a,end:r,bits:c,label:f},n,i);if(o.push(d),d.end+1===n*i&&(u.pushWord(o),o=[],n++),!p)break;({start:a,end:r,bits:c,label:f}=p)}}u.pushWord(o)},"populate"),O=l((t,e,o)=>{if(t.start===void 0)throw new Error("start should have been set during first phase");if(t.end===void 0)throw new Error("end should have been set during first phase");if(t.start>t.end)throw new Error(`Block start ${t.start} is greater than block end ${t.end}.`);if(t.end+1<=e*o)return[t,void 0];const n=e*o-1,i=e*o;return[{start:t.start,end:n,label:t.label,bits:n-t.start},{start:i,end:t.end,label:t.label,bits:t.end-i}]},"getNextFittingBlock"),q={parse:l(async t=>{const e=await N("packet",t);w.debug(e),M(e)},"parse")},R=l((t,e,o,n)=>{const i=n.db,a=i.getConfig(),{rowHeight:r,paddingY:c,bitWidth:f,bitsPerRow:d}=a,p=i.getPacket(),s=i.getDiagramTitle(),k=r+c,g=k*(p.length+1)-(s?0:r),b=f*d+2,h=W(e);h.attr("viewbox",`0 0 ${b} ${g}`),T(h,g,b,a.useMaxWidth);for(const[C,$]of p.entries())U(h,$,C,a);h.append("text").text(s).attr("x",b/2).attr("y",g-k/2).attr("dominant-baseline","middle").attr("text-anchor","middle").attr("class","packetTitle")},"draw"),U=l((t,e,o,{rowHeight:n,paddingX:i,paddingY:a,bitWidth:r,bitsPerRow:c,showBits:f})=>{const d=t.append("g"),p=o*(n+a)+a;for(const s of e){const k=s.start%c*r+1,g=(s.end-s.start+1)*r-i;if(d.append("rect").attr("x",k).attr("y",p).attr("width",g).attr("height",n).attr("class","packetBlock"),d.append("text").attr("x",k+g/2).attr("y",p+n/2).attr("class","packetLabel").attr("dominant-baseline","middle").attr("text-anchor","middle").text(s.label),!f)continue;const b=s.end===s.start,h=p-2;d.append("text").attr("x",k+(b?g/2:0)).attr("y",h).attr("class","packetByte start").attr("dominant-baseline","auto").attr("text-anchor",b?"middle":"start").text(s.start),b||d.append("text").attr("x",k+g).attr("y",h).attr("class","packetByte end").attr("dominant-baseline","auto").attr("text-anchor","end").text(s.end)}},"drawWord"),X={draw:R},j={byteFontSize:"10px",startByteColor:"black",endByteColor:"black",labelColor:"black",labelFontSize:"12px",titleColor:"black",titleFontSize:"14px",blockStrokeColor:"black",blockStrokeWidth:"1",blockFillColor:"#efefef"},J=l(({packet:t}={})=>{const e=v(j,t);return`
+	.packetByte {
+		font-size: ${e.byteFontSize};
+	}
+	.packetByte.start {
+		fill: ${e.startByteColor};
+	}
+	.packetByte.end {
+		fill: ${e.endByteColor};
+	}
+	.packetLabel {
+		fill: ${e.labelColor};
+		font-size: ${e.labelFontSize};
+	}
+	.packetTitle {
+		fill: ${e.titleColor};
+		font-size: ${e.titleFontSize};
+	}
+	.packetBlock {
+		stroke: ${e.blockStrokeColor};
+		stroke-width: ${e.blockStrokeWidth};
+		fill: ${e.blockFillColor};
+	}
+	`},"styles"),lt={parser:q,db:u,renderer:X,styles:J};export{lt as diagram};

lightrag/api/webui/assets/diagram-SSKATNLV-XtCcf-iZ.js

@@ -1,43 +0,0 @@
-import{p as k}from"./chunk-4BMEZGHF-lnpW8Ujf.js";import{_ as l,s as R,g as F,t as I,q as _,a as E,b as D,K as G,z,F as y,G as C,H as P,l as H,Q as V}from"./mermaid-vendor-CuJcWrH0.js";import{p as W}from"./radar-MK3ICKWK-bzElGvQt.js";import"./feature-graph-CeEpF_Yb.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";import"./_baseUniq-CN7ubuxw.js";import"./_basePickBy-4-C6UZHi.js";import"./clone-Du5yQfgG.js";var h={showLegend:!0,ticks:5,max:null,min:0,graticule:"circle"},w={axes:[],curves:[],options:h},g=structuredClone(w),B=P.radar,j=l(()=>y({...B,...C().radar}),"getConfig"),b=l(()=>g.axes,"getAxes"),q=l(()=>g.curves,"getCurves"),K=l(()=>g.options,"getOptions"),N=l(a=>{g.axes=a.map(t=>({name:t.name,label:t.label??t.name}))},"setAxes"),Q=l(a=>{g.curves=a.map(t=>({name:t.name,label:t.label??t.name,entries:U(t.entries)}))},"setCurves"),U=l(a=>{if(a[0].axis==null)return a.map(e=>e.value);const t=b();if(t.length===0)throw new Error("Axes must be populated before curves for reference entries");return t.map(e=>{const r=a.find(s=>{var o;return((o=s.axis)==null?void 0:o.$refText)===e.name});if(r===void 0)throw new Error("Missing entry for axis "+e.label);return r.value})},"computeCurveEntries"),X=l(a=>{var e,r,s,o,i;const t=a.reduce((n,c)=>(n[c.name]=c,n),{});g.options={showLegend:((e=t.showLegend)==null?void 0:e.value)??h.showLegend,ticks:((r=t.ticks)==null?void 0:r.value)??h.ticks,max:((s=t.max)==null?void 0:s.value)??h.max,min:((o=t.min)==null?void 0:o.value)??h.min,graticule:((i=t.graticule)==null?void 0:i.value)??h.graticule}},"setOptions"),Y=l(()=>{z(),g=structuredClone(w)},"clear"),$={getAxes:b,getCurves:q,getOptions:K,setAxes:N,setCurves:Q,setOptions:X,getConfig:j,clear:Y,setAccTitle:D,getAccTitle:E,setDiagramTitle:_,getDiagramTitle:I,getAccDescription:F,setAccDescription:R},Z=l(a=>{k(a,$);const{axes:t,curves:e,options:r}=a;$.setAxes(t),$.setCurves(e),$.setOptions(r)},"populate"),J={parse:l(async a=>{const t=await W("radar",a);H.debug(t),Z(t)},"parse")},tt=l((a,t,e,r)=>{const s=r.db,o=s.getAxes(),i=s.getCurves(),n=s.getOptions(),c=s.getConfig(),d=s.getDiagramTitle(),u=G(t),p=et(u,c),m=n.max??Math.max(...i.map(f=>Math.max(...f.entries))),x=n.min,v=Math.min(c.width,c.height)/2;at(p,o,v,n.ticks,n.graticule),rt(p,o,v,c),M(p,o,i,x,m,n.graticule,c),T(p,i,n.showLegend,c),p.append("text").attr("class","radarTitle").text(d).attr("x",0).attr("y",-c.height/2-c.marginTop)},"draw"),et=l((a,t)=>{const e=t.width+t.marginLeft+t.marginRight,r=t.height+t.marginTop+t.marginBottom,s={x:t.marginLeft+t.width/2,y:t.marginTop+t.height/2};return a.attr("viewbox",`0 0 ${e} ${r}`).attr("width",e).attr("height",r),a.append("g").attr("transform",`translate(${s.x}, ${s.y})`)},"drawFrame"),at=l((a,t,e,r,s)=>{if(s==="circle")for(let o=0;o<r;o++){const i=e*(o+1)/r;a.append("circle").attr("r",i).attr("class","radarGraticule")}else if(s==="polygon"){const o=t.length;for(let i=0;i<r;i++){const n=e*(i+1)/r,c=t.map((d,u)=>{const p=2*u*Math.PI/o-Math.PI/2,m=n*Math.cos(p),x=n*Math.sin(p);return`${m},${x}`}).join(" ");a.append("polygon").attr("points",c).attr("class","radarGraticule")}}},"drawGraticule"),rt=l((a,t,e,r)=>{const s=t.length;for(let o=0;o<s;o++){const i=t[o].label,n=2*o*Math.PI/s-Math.PI/2;a.append("line").attr("x1",0).attr("y1",0).attr("x2",e*r.axisScaleFactor*Math.cos(n)).attr("y2",e*r.axisScaleFactor*Math.sin(n)).attr("class","radarAxisLine"),a.append("text").text(i).attr("x",e*r.axisLabelFactor*Math.cos(n)).attr("y",e*r.axisLabelFactor*Math.sin(n)).attr("class","radarAxisLabel")}},"drawAxes");function M(a,t,e,r,s,o,i){const n=t.length,c=Math.min(i.width,i.height)/2;e.forEach((d,u)=>{if(d.entries.length!==n)return;const p=d.entries.map((m,x)=>{const v=2*Math.PI*x/n-Math.PI/2,f=A(m,r,s,c),O=f*Math.cos(v),S=f*Math.sin(v);return{x:O,y:S}});o==="circle"?a.append("path").attr("d",L(p,i.curveTension)).attr("class",`radarCurve-${u}`):o==="polygon"&&a.append("polygon").attr("points",p.map(m=>`${m.x},${m.y}`).join(" ")).attr("class",`radarCurve-${u}`)})}l(M,"drawCurves");function A(a,t,e,r){const s=Math.min(Math.max(a,t),e);return r*(s-t)/(e-t)}l(A,"relativeRadius");function L(a,t){const e=a.length;let r=`M${a[0].x},${a[0].y}`;for(let s=0;s<e;s++){const o=a[(s-1+e)%e],i=a[s],n=a[(s+1)%e],c=a[(s+2)%e],d={x:i.x+(n.x-o.x)*t,y:i.y+(n.y-o.y)*t},u={x:n.x-(c.x-i.x)*t,y:n.y-(c.y-i.y)*t};r+=` C${d.x},${d.y} ${u.x},${u.y} ${n.x},${n.y}`}return`${r} Z`}l(L,"closedRoundCurve");function T(a,t,e,r){if(!e)return;const s=(r.width/2+r.marginRight)*3/4,o=-(r.height/2+r.marginTop)*3/4,i=20;t.forEach((n,c)=>{const d=a.append("g").attr("transform",`translate(${s}, ${o+c*i})`);d.append("rect").attr("width",12).attr("height",12).attr("class",`radarLegendBox-${c}`),d.append("text").attr("x",16).attr("y",0).attr("class","radarLegendText").text(n.label)})}l(T,"drawLegend");var st={draw:tt},nt=l((a,t)=>{let e="";for(let r=0;r<a.THEME_COLOR_LIMIT;r++){const s=a[`cScale${r}`];e+=`
-		.radarCurve-${r} {
-			color: ${s};
-			fill: ${s};
-			fill-opacity: ${t.curveOpacity};
-			stroke: ${s};
-			stroke-width: ${t.curveStrokeWidth};
-		}
-		.radarLegendBox-${r} {
-			fill: ${s};
-			fill-opacity: ${t.curveOpacity};
-			stroke: ${s};
-		}
-		`}return e},"genIndexStyles"),ot=l(a=>{const t=V(),e=C(),r=y(t,e.themeVariables),s=y(r.radar,a);return{themeVariables:r,radarOptions:s}},"buildRadarStyleOptions"),it=l(({radar:a}={})=>{const{themeVariables:t,radarOptions:e}=ot(a);return`
-	.radarTitle {
-		font-size: ${t.fontSize};
-		color: ${t.titleColor};
-		dominant-baseline: hanging;
-		text-anchor: middle;
-	}
-	.radarAxisLine {
-		stroke: ${e.axisColor};
-		stroke-width: ${e.axisStrokeWidth};
-	}
-	.radarAxisLabel {
-		dominant-baseline: middle;
-		text-anchor: middle;
-		font-size: ${e.axisLabelFontSize}px;
-		color: ${e.axisColor};
-	}
-	.radarGraticule {
-		fill: ${e.graticuleColor};
-		fill-opacity: ${e.graticuleOpacity};
-		stroke: ${e.graticuleColor};
-		stroke-width: ${e.graticuleStrokeWidth};
-	}
-	.radarLegendText {
-		text-anchor: start;
-		font-size: ${e.legendFontSize}px;
-		dominant-baseline: hanging;
-	}
-	${nt(t,e)}
-	`},"styles"),ft={parser:J,db:$,renderer:st,styles:it};export{ft as diagram};

lightrag/api/webui/assets/diagram-VNBRO52H-Byk9Fqdy.js

@@ -1,24 +0,0 @@
-import{p as w}from"./chunk-4BMEZGHF-lnpW8Ujf.js";import{_ as n,s as B,g as S,t as F,q as z,a as P,b as W,F as x,K as T,e as D,z as _,G as A,H as E,l as v}from"./mermaid-vendor-CuJcWrH0.js";import{p as N}from"./radar-MK3ICKWK-bzElGvQt.js";import"./feature-graph-CeEpF_Yb.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";import"./_baseUniq-CN7ubuxw.js";import"./_basePickBy-4-C6UZHi.js";import"./clone-Du5yQfgG.js";var C={packet:[]},h=structuredClone(C),L=E.packet,Y=n(()=>{const t=x({...L,...A().packet});return t.showBits&&(t.paddingY+=10),t},"getConfig"),G=n(()=>h.packet,"getPacket"),H=n(t=>{t.length>0&&h.packet.push(t)},"pushWord"),I=n(()=>{_(),h=structuredClone(C)},"clear"),m={pushWord:H,getPacket:G,getConfig:Y,clear:I,setAccTitle:W,getAccTitle:P,setDiagramTitle:z,getDiagramTitle:F,getAccDescription:S,setAccDescription:B},K=1e4,M=n(t=>{w(t,m);let e=-1,o=[],s=1;const{bitsPerRow:i}=m.getConfig();for(let{start:a,end:r,label:p}of t.blocks){if(r&&r<a)throw new Error(`Packet block ${a} - ${r} is invalid. End must be greater than start.`);if(a!==e+1)throw new Error(`Packet block ${a} - ${r??a} is not contiguous. It should start from ${e+1}.`);for(e=r??a,v.debug(`Packet block ${a} - ${e} with label ${p}`);o.length<=i+1&&m.getPacket().length<K;){const[b,c]=O({start:a,end:r,label:p},s,i);if(o.push(b),b.end+1===s*i&&(m.pushWord(o),o=[],s++),!c)break;({start:a,end:r,label:p}=c)}}m.pushWord(o)},"populate"),O=n((t,e,o)=>{if(t.end===void 0&&(t.end=t.start),t.start>t.end)throw new Error(`Block start ${t.start} is greater than block end ${t.end}.`);return t.end+1<=e*o?[t,void 0]:[{start:t.start,end:e*o-1,label:t.label},{start:e*o,end:t.end,label:t.label}]},"getNextFittingBlock"),q={parse:n(async t=>{const e=await N("packet",t);v.debug(e),M(e)},"parse")},R=n((t,e,o,s)=>{const i=s.db,a=i.getConfig(),{rowHeight:r,paddingY:p,bitWidth:b,bitsPerRow:c}=a,u=i.getPacket(),l=i.getDiagramTitle(),g=r+p,d=g*(u.length+1)-(l?0:r),k=b*c+2,f=T(e);f.attr("viewbox",`0 0 ${k} ${d}`),D(f,d,k,a.useMaxWidth);for(const[$,y]of u.entries())U(f,y,$,a);f.append("text").text(l).attr("x",k/2).attr("y",d-g/2).attr("dominant-baseline","middle").attr("text-anchor","middle").attr("class","packetTitle")},"draw"),U=n((t,e,o,{rowHeight:s,paddingX:i,paddingY:a,bitWidth:r,bitsPerRow:p,showBits:b})=>{const c=t.append("g"),u=o*(s+a)+a;for(const l of e){const g=l.start%p*r+1,d=(l.end-l.start+1)*r-i;if(c.append("rect").attr("x",g).attr("y",u).attr("width",d).attr("height",s).attr("class","packetBlock"),c.append("text").attr("x",g+d/2).attr("y",u+s/2).attr("class","packetLabel").attr("dominant-baseline","middle").attr("text-anchor","middle").text(l.label),!b)continue;const k=l.end===l.start,f=u-2;c.append("text").attr("x",g+(k?d/2:0)).attr("y",f).attr("class","packetByte start").attr("dominant-baseline","auto").attr("text-anchor",k?"middle":"start").text(l.start),k||c.append("text").attr("x",g+d).attr("y",f).attr("class","packetByte end").attr("dominant-baseline","auto").attr("text-anchor","end").text(l.end)}},"drawWord"),X={draw:R},j={byteFontSize:"10px",startByteColor:"black",endByteColor:"black",labelColor:"black",labelFontSize:"12px",titleColor:"black",titleFontSize:"14px",blockStrokeColor:"black",blockStrokeWidth:"1",blockFillColor:"#efefef"},J=n(({packet:t}={})=>{const e=x(j,t);return`
-	.packetByte {
-		font-size: ${e.byteFontSize};
-	}
-	.packetByte.start {
-		fill: ${e.startByteColor};
-	}
-	.packetByte.end {
-		fill: ${e.endByteColor};
-	}
-	.packetLabel {
-		fill: ${e.labelColor};
-		font-size: ${e.labelFontSize};
-	}
-	.packetTitle {
-		fill: ${e.titleColor};
-		font-size: ${e.titleFontSize};
-	}
-	.packetBlock {
-		stroke: ${e.blockStrokeColor};
-		stroke-width: ${e.blockStrokeWidth};
-		fill: ${e.blockFillColor};
-	}
-	`},"styles"),it={parser:q,db:m,renderer:X,styles:J};export{it as diagram};

lightrag/api/webui/assets/infoDiagram-LHK5PUON-BpkVKBvB.js

@@ -0,0 +1,2 @@
+import{_ as e,l as o,K as i,e as n,L as p}from"./mermaid-vendor-kG8Trx8h.js";import{p as m}from"./treemap-75Q7IDZK-M3vYzjwI.js";import"./feature-graph-7h-VS-iL.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";import"./_baseUniq-D5S4RK2K.js";import"./_basePickBy-DEiY070O.js";import"./clone-D1RenvQh.js";var g={parse:e(async r=>{const a=await m("info",r);o.debug(a)},"parse")},v={version:p.version+""},d=e(()=>v.version,"getVersion"),c={getVersion:d},l=e((r,a,s)=>{o.debug(`rendering info diagram
+`+r);const t=i(a);n(t,100,400,!0),t.append("g").append("text").attr("x",100).attr("y",40).attr("class","version").attr("font-size",32).style("text-anchor","middle").text(`v${s}`)},"draw"),f={draw:l},L={parser:g,db:c,renderer:f};export{L as diagram};

lightrag/api/webui/assets/infoDiagram-PH2N3AL5-CeWhTqE9.js

@@ -1,2 +0,0 @@
-import{_ as e,l as o,K as i,e as n,L as p}from"./mermaid-vendor-CuJcWrH0.js";import{p as m}from"./radar-MK3ICKWK-bzElGvQt.js";import"./feature-graph-CeEpF_Yb.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";import"./_baseUniq-CN7ubuxw.js";import"./_basePickBy-4-C6UZHi.js";import"./clone-Du5yQfgG.js";var g={parse:e(async r=>{const a=await m("info",r);o.debug(a)},"parse")},v={version:p.version},d=e(()=>v.version,"getVersion"),c={getVersion:d},l=e((r,a,s)=>{o.debug(`rendering info diagram
-`+r);const t=i(a);n(t,100,400,!0),t.append("g").append("text").attr("x",100).attr("y",40).attr("class","version").attr("font-size",32).style("text-anchor","middle").text(`v${s}`)},"draw"),f={draw:l},L={parser:g,db:c,renderer:f};export{L as diagram};

lightrag/api/webui/assets/pieDiagram-NIOCPIFQ-KBHyYHBZ.js

@@ -1,4 +1,4 @@
-import{p as N}from"./chunk-4BMEZGHF-lnpW8Ujf.js";import{_ as i,g as B,s as U,a as q,b as H,t as K,q as V,l as C,c as Z,F as j,K as J,M as Q,N as z,O as X,e as Y,z as tt,P as et,H as at}from"./mermaid-vendor-CuJcWrH0.js";import{p as rt}from"./radar-MK3ICKWK-bzElGvQt.js";import"./feature-graph-CeEpF_Yb.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";import"./_baseUniq-CN7ubuxw.js";import"./_basePickBy-4-C6UZHi.js";import"./clone-Du5yQfgG.js";var it=at.pie,D={sections:new Map,showData:!1},f=D.sections,w=D.showData,st=structuredClone(it),ot=i(()=>structuredClone(st),"getConfig"),nt=i(()=>{f=new Map,w=D.showData,tt()},"clear"),lt=i(({label:t,value:a})=>{f.has(t)||(f.set(t,a),C.debug(`added new section: ${t}, with value: ${a}`))},"addSection"),ct=i(()=>f,"getSections"),pt=i(t=>{w=t},"setShowData"),dt=i(()=>w,"getShowData"),F={getConfig:ot,clear:nt,setDiagramTitle:V,getDiagramTitle:K,setAccTitle:H,getAccTitle:q,setAccDescription:U,getAccDescription:B,addSection:lt,getSections:ct,setShowData:pt,getShowData:dt},gt=i((t,a)=>{N(t,a),a.setShowData(t.showData),t.sections.map(a.addSection)},"populateDb"),ut={parse:i(async t=>{const a=await rt("pie",t);C.debug(a),gt(a,F)},"parse")},mt=i(t=>`
+import{p as N}from"./chunk-353BL4L5-CG4Wb5Ni.js";import{_ as i,g as B,s as U,a as q,b as H,t as K,q as V,l as C,c as Z,F as j,K as J,M as Q,N as z,O as X,e as Y,z as tt,P as et,H as at}from"./mermaid-vendor-kG8Trx8h.js";import{p as rt}from"./treemap-75Q7IDZK-M3vYzjwI.js";import"./feature-graph-7h-VS-iL.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";import"./_baseUniq-D5S4RK2K.js";import"./_basePickBy-DEiY070O.js";import"./clone-D1RenvQh.js";var it=at.pie,D={sections:new Map,showData:!1},f=D.sections,w=D.showData,st=structuredClone(it),ot=i(()=>structuredClone(st),"getConfig"),nt=i(()=>{f=new Map,w=D.showData,tt()},"clear"),lt=i(({label:t,value:a})=>{f.has(t)||(f.set(t,a),C.debug(`added new section: ${t}, with value: ${a}`))},"addSection"),ct=i(()=>f,"getSections"),pt=i(t=>{w=t},"setShowData"),dt=i(()=>w,"getShowData"),F={getConfig:ot,clear:nt,setDiagramTitle:V,getDiagramTitle:K,setAccTitle:H,getAccTitle:q,setAccDescription:U,getAccDescription:B,addSection:lt,getSections:ct,setShowData:pt,getShowData:dt},gt=i((t,a)=>{N(t,a),a.setShowData(t.showData),t.sections.map(a.addSection)},"populateDb"),ut={parse:i(async t=>{const a=await rt("pie",t);C.debug(a),gt(a,F)},"parse")},mt=i(t=>`
   .pieCircle{
     stroke: ${t.pieStrokeColor};
     stroke-width : ${t.pieStrokeWidth};

lightrag/api/webui/assets/stateDiagram-v2-5AN5P6BG-Ct4ONjDp.js

@@ -0,0 +1 @@
+import{s as r,b as e,a,S as i}from"./chunk-OW32GOEJ-7_NWvBKK.js";import{_ as s}from"./mermaid-vendor-kG8Trx8h.js";import"./chunk-BFAMUDN2-ILoF6WWe.js";import"./chunk-SKB7J2MH-CCgDhfF0.js";import"./feature-graph-7h-VS-iL.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";var f={parser:a,get db(){return new i(2)},renderer:e,styles:r,init:s(t=>{t.state||(t.state={}),t.state.arrowMarkerAbsolute=t.arrowMarkerAbsolute},"init")};export{f as diagram};

lightrag/api/webui/assets/stateDiagram-v2-YXO3MK2T-sGJiKdqB.js

@@ -1 +0,0 @@
-import{s as r,b as e,a,S as s}from"./chunk-AEK57VVT-6am85ODh.js";import{_ as i}from"./mermaid-vendor-CuJcWrH0.js";import"./chunk-RZ5BOZE2-D3gEMbCJ.js";import"./feature-graph-CeEpF_Yb.js";import"./react-vendor-DEwriMA6.js";import"./graph-vendor-B-X5JegA.js";import"./ui-vendor-CeCm8EER.js";import"./utils-vendor-BysuhMZA.js";var b={parser:a,get db(){return new s(2)},renderer:e,styles:r,init:i(t=>{t.state||(t.state={}),t.state.arrowMarkerAbsolute=t.arrowMarkerAbsolute},"init")};export{b as diagram};

lightrag/api/webui/index.html

@@ -8,18 +8,18 @@
     <link rel="icon" type="image/png" href="favicon.png" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <title>Lightrag</title>
-    <script type="module" crossorigin src="/webui/assets/index-KW-eZWPA.js"></script>
+    <script type="module" crossorigin src="/webui/assets/index-DbjaBP8L.js"></script>
     <link rel="modulepreload" crossorigin href="/webui/assets/react-vendor-DEwriMA6.js">
     <link rel="modulepreload" crossorigin href="/webui/assets/ui-vendor-CeCm8EER.js">
     <link rel="modulepreload" crossorigin href="/webui/assets/graph-vendor-B-X5JegA.js">
     <link rel="modulepreload" crossorigin href="/webui/assets/utils-vendor-BysuhMZA.js">
-    <link rel="modulepreload" crossorigin href="/webui/assets/feature-graph-CeEpF_Yb.js">
-    <link rel="modulepreload" crossorigin href="/webui/assets/feature-documents-DaeP3jJU.js">
-    <link rel="modulepreload" crossorigin href="/webui/assets/mermaid-vendor-CuJcWrH0.js">
-    <link rel="modulepreload" crossorigin href="/webui/assets/markdown-vendor-BKOfNAUO.js">
-    <link rel="modulepreload" crossorigin href="/webui/assets/feature-retrieval-CTawnaAw.js">
+    <link rel="modulepreload" crossorigin href="/webui/assets/feature-graph-7h-VS-iL.js">
+    <link rel="modulepreload" crossorigin href="/webui/assets/feature-documents-Btp1BS17.js">
+    <link rel="modulepreload" crossorigin href="/webui/assets/mermaid-vendor-kG8Trx8h.js">
+    <link rel="modulepreload" crossorigin href="/webui/assets/markdown-vendor-Dv0NSOeH.js">
+    <link rel="modulepreload" crossorigin href="/webui/assets/feature-retrieval-DsN5eBDA.js">
     <link rel="stylesheet" crossorigin href="/webui/assets/feature-graph-BipNuM18.css">
-    <link rel="stylesheet" crossorigin href="/webui/assets/index-BvrNHAMA.css">
+    <link rel="stylesheet" crossorigin href="/webui/assets/index-DzTVXLx_.css">
   </head>
   <body>
     <div id="root"></div>

lightrag/base.py

@@ -11,6 +11,10 @@ from typing import (
     TypedDict,
     TypeVar,
     Callable,
+    Optional,
+    Dict,
+    List,
+    AsyncIterator,
 )
 from .utils import EmbeddingFunc
 from .types import KnowledgeGraph
@@ -132,13 +136,13 @@ class QueryParam:
     ll_keywords: list[str] = field(default_factory=list)
     """List of low-level keywords to refine retrieval focus."""
 
-    # TODO: Deprecated - history message have negtive effect on query performance
+    # History mesages is only send to LLM for context, not used for retrieval
     conversation_history: list[dict[str, str]] = field(default_factory=list)
     """Stores past conversation history to maintain context.
     Format: [{"role": "user/assistant", "content": "message"}].
     """
 
-    # TODO: Deprecated - history message have negtive effect on query performance
+    # TODO: deprecated. No longer used in the codebase, all conversation_history messages is send to LLM
     history_turns: int = int(os.getenv("HISTORY_TURNS", str(DEFAULT_HISTORY_TURNS)))
     """Number of complete conversation turns (user-assistant pairs) to consider in the response context."""
 
@@ -150,7 +154,8 @@ class QueryParam:
 
     user_prompt: str | None = None
     """User-provided prompt for the query.
-    If proivded, this will be use instead of the default vaulue from prompt template.
+    Addition instructions for LLM. If provided, this will be inject into the prompt template.
+    It's purpose is the let user customize the way LLM generate the response.
     """
 
     enable_rerank: bool = os.getenv("RERANK_BY_DEFAULT", "true").lower() == "true"
@@ -158,6 +163,12 @@ class QueryParam:
     Default is True to enable reranking when rerank model is available.
     """
 
+    include_references: bool = False
+    """If True, includes reference list in the response for supported endpoints.
+    This parameter controls whether the API response includes a references field
+    containing citation information for the retrieved content.
+    """
+
 
 @dataclass
 class StorageNameSpace(ABC):
@@ -629,6 +640,7 @@ class BaseGraphStorage(StorageNameSpace, ABC):
             edges: List of edges to be deleted, each edge is a (source, target) tuple
         """
 
+    # TODO: deprecated
     @abstractmethod
     async def get_all_labels(self) -> list[str]:
         """Get all labels in the graph.
@@ -671,6 +683,29 @@ class BaseGraphStorage(StorageNameSpace, ABC):
             A list of all edges, where each edge is a dictionary of its properties
         """
 
+    @abstractmethod
+    async def get_popular_labels(self, limit: int = 300) -> list[str]:
+        """Get popular labels by node degree (most connected entities)
+
+        Args:
+            limit: Maximum number of labels to return
+
+        Returns:
+            List of labels sorted by degree (highest first)
+        """
+
+    @abstractmethod
+    async def search_labels(self, query: str, limit: int = 50) -> list[str]:
+        """Search labels with fuzzy matching
+
+        Args:
+            query: Search query string
+            limit: Maximum number of results to return
+
+        Returns:
+            List of matching labels sorted by relevance
+        """
+
 
 class DocStatus(str, Enum):
     """Document processing status"""
@@ -759,6 +794,18 @@ class DocStatusStorage(BaseKVStorage, ABC):
             Dictionary mapping status names to counts
         """
 
+    @abstractmethod
+    async def get_doc_by_file_path(self, file_path: str) -> dict[str, Any] | None:
+        """Get document by file path
+
+        Args:
+            file_path: The file path to search for
+
+        Returns:
+            dict[str, Any] | None: Document data if found, None otherwise
+            Returns the same format as get_by_ids method
+        """
+
 
 class StoragesStatus(str, Enum):
     """Storages status"""
@@ -778,3 +825,68 @@ class DeletionResult:
     message: str
     status_code: int = 200
     file_path: str | None = None
+
+
+# Unified Query Result Data Structures for Reference List Support
+
+
+@dataclass
+class QueryResult:
+    """
+    Unified query result data structure for all query modes.
+
+    Attributes:
+        content: Text content for non-streaming responses
+        response_iterator: Streaming response iterator for streaming responses
+        raw_data: Complete structured data including references and metadata
+        is_streaming: Whether this is a streaming result
+    """
+
+    content: Optional[str] = None
+    response_iterator: Optional[AsyncIterator[str]] = None
+    raw_data: Optional[Dict[str, Any]] = None
+    is_streaming: bool = False
+
+    @property
+    def reference_list(self) -> List[Dict[str, str]]:
+        """
+        Convenient property to extract reference list from raw_data.
+
+        Returns:
+            List[Dict[str, str]]: Reference list in format:
+            [{"reference_id": "1", "file_path": "/path/to/file.pdf"}, ...]
+        """
+        if self.raw_data:
+            return self.raw_data.get("data", {}).get("references", [])
+        return []
+
+    @property
+    def metadata(self) -> Dict[str, Any]:
+        """
+        Convenient property to extract metadata from raw_data.
+
+        Returns:
+            Dict[str, Any]: Query metadata including query_mode, keywords, etc.
+        """
+        if self.raw_data:
+            return self.raw_data.get("metadata", {})
+        return {}
+
+
+@dataclass
+class QueryContextResult:
+    """
+    Unified query context result data structure.
+
+    Attributes:
+        context: LLM context string
+        raw_data: Complete structured data including reference_list
+    """
+
+    context: str
+    raw_data: Dict[str, Any]
+
+    @property
+    def reference_list(self) -> List[Dict[str, str]]:
+        """Convenient property to extract reference list from raw_data."""
+        return self.raw_data.get("data", {}).get("references", [])

lightrag/constants.py

@@ -25,6 +25,7 @@ DEFAULT_SUMMARY_CONTEXT_SIZE = 12000
 # Default entities to extract if ENTITY_TYPES is not specified in .env
 DEFAULT_ENTITY_TYPES = [
     "Person",
+    "Creature",
     "Organization",
     "Location",
     "Event",
@@ -48,7 +49,8 @@ DEFAULT_MAX_TOTAL_TOKENS = 30000
 DEFAULT_COSINE_THRESHOLD = 0.2
 DEFAULT_RELATED_CHUNK_NUMBER = 5
 DEFAULT_KG_CHUNK_PICK_METHOD = "VECTOR"
-# Deprated: history message have negtive effect on query performance
+
+# TODO: Deprated. All conversation_history messages is send to LLM.
 DEFAULT_HISTORY_TURNS = 0
 
 # Rerank configuration defaults

lightrag/kg/json_doc_status_impl.py

@@ -323,6 +323,27 @@ class JsonDocStatusStorage(DocStatusStorage):
             if any_deleted:
                 await set_all_update_flags(self.final_namespace)
 
+    async def get_doc_by_file_path(self, file_path: str) -> Union[dict[str, Any], None]:
+        """Get document by file path
+
+        Args:
+            file_path: The file path to search for
+
+        Returns:
+            Union[dict[str, Any], None]: Document data if found, None otherwise
+            Returns the same format as get_by_ids method
+        """
+        if self._storage_lock is None:
+            raise StorageNotInitializedError("JsonDocStatusStorage")
+
+        async with self._storage_lock:
+            for doc_id, doc_data in self._data.items():
+                if doc_data.get("file_path") == file_path:
+                    # Return complete document data, consistent with get_by_ids method
+                    return doc_data
+
+        return None
+
     async def drop(self) -> dict[str, str]:
         """Drop all document status data from storage and clean up resources
 

lightrag/kg/memgraph_impl.py

@@ -1089,3 +1089,100 @@ class MemgraphStorage(BaseGraphStorage):
                 edges.append(edge_properties)
             await result.consume()
             return edges
+
+    async def get_popular_labels(self, limit: int = 300) -> list[str]:
+        """Get popular labels by node degree (most connected entities)
+
+        Args:
+            limit: Maximum number of labels to return
+
+        Returns:
+            List of labels sorted by degree (highest first)
+        """
+        if self._driver is None:
+            raise RuntimeError(
+                "Memgraph driver is not initialized. Call 'await initialize()' first."
+            )
+
+        try:
+            workspace_label = self._get_workspace_label()
+            async with self._driver.session(
+                database=self._DATABASE, default_access_mode="READ"
+            ) as session:
+                query = f"""
+                MATCH (n:`{workspace_label}`)
+                WHERE n.entity_id IS NOT NULL
+                OPTIONAL MATCH (n)-[r]-()
+                WITH n.entity_id AS label, count(r) AS degree
+                ORDER BY degree DESC, label ASC
+                LIMIT {limit}
+                RETURN label
+                """
+                result = await session.run(query)
+                labels = []
+                async for record in result:
+                    labels.append(record["label"])
+                await result.consume()
+
+                logger.debug(
+                    f"[{self.workspace}] Retrieved {len(labels)} popular labels (limit: {limit})"
+                )
+                return labels
+        except Exception as e:
+            logger.error(f"[{self.workspace}] Error getting popular labels: {str(e)}")
+            return []
+
+    async def search_labels(self, query: str, limit: int = 50) -> list[str]:
+        """Search labels with fuzzy matching
+
+        Args:
+            query: Search query string
+            limit: Maximum number of results to return
+
+        Returns:
+            List of matching labels sorted by relevance
+        """
+        if self._driver is None:
+            raise RuntimeError(
+                "Memgraph driver is not initialized. Call 'await initialize()' first."
+            )
+
+        query_lower = query.lower().strip()
+
+        if not query_lower:
+            return []
+
+        try:
+            workspace_label = self._get_workspace_label()
+            async with self._driver.session(
+                database=self._DATABASE, default_access_mode="READ"
+            ) as session:
+                cypher_query = f"""
+                MATCH (n:`{workspace_label}`)
+                WHERE n.entity_id IS NOT NULL
+                WITH n.entity_id AS label, toLower(n.entity_id) AS label_lower
+                WHERE label_lower CONTAINS $query_lower
+                WITH label, label_lower,
+                     CASE
+                         WHEN label_lower = $query_lower THEN 1000
+                         WHEN label_lower STARTS WITH $query_lower THEN 500
+                         ELSE 100 - size(label)
+                     END AS score
+                ORDER BY score DESC, label ASC
+                LIMIT {limit}
+                RETURN label
+                """
+
+                result = await session.run(cypher_query, query_lower=query_lower)
+                labels = []
+                async for record in result:
+                    labels.append(record["label"])
+                await result.consume()
+
+                logger.debug(
+                    f"[{self.workspace}] Search query '{query}' returned {len(labels)} results (limit: {limit})"
+                )
+                return labels
+        except Exception as e:
+            logger.error(f"[{self.workspace}] Error searching labels: {str(e)}")
+            return []