Merge branch 'dev' into feature/cog-2746-time-graph-to-cognify
This commit is contained in:
hajdul88
GitHub
commit
678173dad4
40 changed files with 8527 additions and 6353 deletions
25
.github/workflows/e2e_tests.yml
vendored
25
.github/workflows/e2e_tests.yml
vendored
|
|
@ -153,31 +153,6 @@ jobs:
|
|||
EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
|
||||
run: uv run python ./cognee/tests/test_deduplication.py
|
||||
|
||||
run-deletion-test:
|
||||
name: Deletion Test
|
||||
runs-on: ubuntu-22.04
|
||||
steps:
|
||||
- name: Check out
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Cognee Setup
|
||||
uses: ./.github/actions/cognee_setup
|
||||
with:
|
||||
python-version: '3.11.x'
|
||||
|
||||
- name: Run Deletion Tests
|
||||
env:
|
||||
ENV: 'dev'
|
||||
LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }} # Test needs OpenAI endpoint to handle multimedia
|
||||
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
|
||||
EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
|
||||
EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
|
||||
EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
|
||||
EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
|
||||
run: uv run python ./cognee/tests/test_deletion.py
|
||||
|
||||
run-s3-bucket-test:
|
||||
name: S3 Bucket Test
|
||||
runs-on: ubuntu-22.04
|
||||
|
|
|
|||
116
.github/workflows/python_version_tests.yml
vendored
116
.github/workflows/python_version_tests.yml
vendored
|
|
@ -1,116 +0,0 @@
|
|||
name: Reusable Python Version Tests
|
||||
|
||||
on:
|
||||
workflow_call:
|
||||
inputs:
|
||||
python-versions:
|
||||
required: false
|
||||
type: string
|
||||
default: '["3.10.x", "3.11.x", "3.12.x"]'
|
||||
secrets:
|
||||
LLM_PROVIDER:
|
||||
required: true
|
||||
LLM_MODEL:
|
||||
required: true
|
||||
LLM_ENDPOINT:
|
||||
required: true
|
||||
LLM_API_KEY:
|
||||
required: true
|
||||
LLM_API_VERSION:
|
||||
required: true
|
||||
EMBEDDING_PROVIDER:
|
||||
required: true
|
||||
EMBEDDING_MODEL:
|
||||
required: true
|
||||
EMBEDDING_ENDPOINT:
|
||||
required: true
|
||||
EMBEDDING_API_KEY:
|
||||
required: true
|
||||
EMBEDDING_API_VERSION:
|
||||
required: true
|
||||
|
||||
env:
|
||||
RUNTIME__LOG_LEVEL: ERROR
|
||||
ENV: 'dev'
|
||||
|
||||
jobs:
|
||||
run-python-version-tests:
|
||||
name: Python ${{ matrix.python-version }} on ${{ matrix.os }}
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
matrix:
|
||||
python-version: ${{ fromJSON(inputs.python-versions) }}
|
||||
os: [ubuntu-22.04, macos-13, macos-15]
|
||||
fail-fast: false
|
||||
steps:
|
||||
- name: Check out
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Cognee Setup
|
||||
uses: ./.github/actions/cognee_setup
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Run unit tests
|
||||
shell: bash
|
||||
run: uv run pytest cognee/tests/unit/
|
||||
env:
|
||||
PYTHONUTF8: 1
|
||||
LLM_PROVIDER: openai
|
||||
LLM_MODEL: ${{ secrets.LLM_MODEL }}
|
||||
LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
|
||||
LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
|
||||
LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
|
||||
|
||||
EMBEDDING_PROVIDER: openai
|
||||
EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
|
||||
EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
|
||||
EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
|
||||
EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
|
||||
|
||||
- name: Run integration tests
|
||||
if: ${{ !contains(matrix.os, 'windows') }}
|
||||
shell: bash
|
||||
run: uv run pytest cognee/tests/integration/
|
||||
env:
|
||||
PYTHONUTF8: 1
|
||||
LLM_PROVIDER: openai
|
||||
LLM_MODEL: ${{ secrets.LLM_MODEL }}
|
||||
LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
|
||||
LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
|
||||
LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
|
||||
|
||||
EMBEDDING_PROVIDER: openai
|
||||
EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
|
||||
EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
|
||||
EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
|
||||
EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
|
||||
|
||||
- name: Run default basic pipeline
|
||||
shell: bash
|
||||
env:
|
||||
PYTHONUTF8: 1
|
||||
LLM_PROVIDER: openai
|
||||
LLM_MODEL: ${{ secrets.LLM_MODEL }}
|
||||
LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
|
||||
LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
|
||||
LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
|
||||
|
||||
EMBEDDING_PROVIDER: openai
|
||||
EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
|
||||
EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
|
||||
EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
|
||||
EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
|
||||
run: uv run python ./cognee/tests/test_library.py
|
||||
|
||||
- name: Build with uv
|
||||
shell: bash
|
||||
run: uv build
|
||||
|
||||
- name: Install Package
|
||||
if: ${{ !contains(matrix.os, 'windows') }}
|
||||
run: |
|
||||
cd dist
|
||||
pip install *.whl
|
||||
235
.github/workflows/test_different_operating_systems.yml
vendored
Normal file
235
.github/workflows/test_different_operating_systems.yml
vendored
Normal file
|
|
@ -0,0 +1,235 @@
|
|||
name: Tests to run on different Operating Systems
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
on:
|
||||
workflow_call:
|
||||
inputs:
|
||||
python-versions:
|
||||
required: false
|
||||
type: string
|
||||
default: '["3.10.x", "3.11.x", "3.12.x"]'
|
||||
secrets:
|
||||
LLM_PROVIDER:
|
||||
required: true
|
||||
LLM_MODEL:
|
||||
required: true
|
||||
LLM_ENDPOINT:
|
||||
required: true
|
||||
LLM_API_KEY:
|
||||
required: true
|
||||
LLM_API_VERSION:
|
||||
required: true
|
||||
EMBEDDING_PROVIDER:
|
||||
required: true
|
||||
EMBEDDING_MODEL:
|
||||
required: true
|
||||
EMBEDDING_ENDPOINT:
|
||||
required: true
|
||||
EMBEDDING_API_KEY:
|
||||
required: true
|
||||
EMBEDDING_API_VERSION:
|
||||
required: true
|
||||
|
||||
env:
|
||||
RUNTIME__LOG_LEVEL: ERROR
|
||||
ENV: 'dev'
|
||||
|
||||
jobs:
|
||||
run-unit-tests:
|
||||
name: Unit tests ${{ matrix.python-version }} on ${{ matrix.os }}
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
matrix:
|
||||
python-version: ${{ fromJSON(inputs.python-versions) }}
|
||||
os: [ubuntu-22.04, macos-13, macos-15, windows-latest]
|
||||
fail-fast: false
|
||||
steps:
|
||||
- name: Check out
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Cognee Setup
|
||||
uses: ./.github/actions/cognee_setup
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Run unit tests
|
||||
shell: bash
|
||||
run: uv run pytest cognee/tests/unit/
|
||||
env:
|
||||
PYTHONUTF8: 1
|
||||
LLM_PROVIDER: openai
|
||||
LLM_MODEL: ${{ secrets.LLM_MODEL }}
|
||||
LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
|
||||
LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
|
||||
LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
|
||||
|
||||
EMBEDDING_PROVIDER: openai
|
||||
EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
|
||||
EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
|
||||
EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
|
||||
EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
|
||||
|
||||
run-integration-tests:
|
||||
name: Integration tests ${{ matrix.python-version }} on ${{ matrix.os }}
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
matrix:
|
||||
python-version: ${{ fromJSON(inputs.python-versions) }}
|
||||
os: [ ubuntu-22.04, macos-13, macos-15, windows-latest ]
|
||||
fail-fast: false
|
||||
steps:
|
||||
- name: Check out
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Cognee Setup
|
||||
uses: ./.github/actions/cognee_setup
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Run integration tests
|
||||
shell: bash
|
||||
run: uv run pytest cognee/tests/integration/
|
||||
env:
|
||||
PYTHONUTF8: 1
|
||||
LLM_PROVIDER: openai
|
||||
LLM_MODEL: ${{ secrets.LLM_MODEL }}
|
||||
LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
|
||||
LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
|
||||
LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
|
||||
|
||||
EMBEDDING_PROVIDER: openai
|
||||
EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
|
||||
EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
|
||||
EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
|
||||
EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
|
||||
|
||||
run-library-test:
|
||||
name: Library test ${{ matrix.python-version }} on ${{ matrix.os }}
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
matrix:
|
||||
python-version: ${{ fromJSON(inputs.python-versions) }}
|
||||
os: [ ubuntu-22.04, macos-13, macos-15, windows-latest ]
|
||||
fail-fast: false
|
||||
steps:
|
||||
- name: Check out
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Cognee Setup
|
||||
uses: ./.github/actions/cognee_setup
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Run default basic pipeline
|
||||
shell: bash
|
||||
env:
|
||||
PYTHONUTF8: 1
|
||||
LLM_PROVIDER: openai
|
||||
LLM_MODEL: ${{ secrets.LLM_MODEL }}
|
||||
LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
|
||||
LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
|
||||
LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
|
||||
|
||||
EMBEDDING_PROVIDER: openai
|
||||
EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
|
||||
EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
|
||||
EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
|
||||
EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
|
||||
run: uv run python ./cognee/tests/test_library.py
|
||||
|
||||
run-build-test:
|
||||
name: Build test ${{ matrix.python-version }} on ${{ matrix.os }}
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
matrix:
|
||||
python-version: ${{ fromJSON(inputs.python-versions) }}
|
||||
os: [ ubuntu-22.04, macos-13, macos-15, windows-latest ]
|
||||
fail-fast: false
|
||||
steps:
|
||||
- name: Check out
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Cognee Setup
|
||||
uses: ./.github/actions/cognee_setup
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Build with uv
|
||||
shell: bash
|
||||
run: uv build
|
||||
|
||||
- name: Install Package
|
||||
if: ${{ !contains(matrix.os, 'windows-latest') }}
|
||||
run: |
|
||||
cd dist
|
||||
pip install *.whl
|
||||
|
||||
run-soft-deletion-test:
|
||||
name: Soft Delete test ${{ matrix.python-version }} on ${{ matrix.os }}
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
matrix:
|
||||
python-version: ${{ fromJSON(inputs.python-versions) }}
|
||||
os: [ ubuntu-22.04, macos-13, macos-15, windows-latest ]
|
||||
fail-fast: false
|
||||
steps:
|
||||
- name: Check out
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Cognee Setup
|
||||
uses: ./.github/actions/cognee_setup
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Run Soft Deletion Tests
|
||||
env:
|
||||
ENV: 'dev'
|
||||
LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }} # Test needs OpenAI endpoint to handle multimedia
|
||||
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
|
||||
EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
|
||||
EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
|
||||
EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
|
||||
EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
|
||||
run: uv run python ./cognee/tests/test_delete_soft.py
|
||||
|
||||
run-hard-deletion-test:
|
||||
name: Hard Delete test ${{ matrix.python-version }} on ${{ matrix.os }}
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
matrix:
|
||||
python-version: ${{ fromJSON(inputs.python-versions) }}
|
||||
os: [ ubuntu-22.04, macos-13, macos-15, windows-latest ]
|
||||
fail-fast: false
|
||||
steps:
|
||||
- name: Check out
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Cognee Setup
|
||||
uses: ./.github/actions/cognee_setup
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Run Hard Deletion Test
|
||||
env:
|
||||
ENV: 'dev'
|
||||
LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }} # Test needs OpenAI endpoint to handle multimedia
|
||||
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
|
||||
EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
|
||||
EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
|
||||
EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
|
||||
EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
|
||||
run: uv run python ./cognee/tests/test_delete_hard.py
|
||||
12
.github/workflows/test_suites.yml
vendored
12
.github/workflows/test_suites.yml
vendored
|
|
@ -68,10 +68,10 @@ jobs:
|
|||
uses: ./.github/workflows/notebooks_tests.yml
|
||||
secrets: inherit
|
||||
|
||||
python-version-tests:
|
||||
name: Python Version Tests
|
||||
different-operating-systems-tests:
|
||||
name: Operating System and Python Tests
|
||||
needs: [basic-tests, e2e-tests, cli-tests]
|
||||
uses: ./.github/workflows/python_version_tests.yml
|
||||
uses: ./.github/workflows/test_different_operating_systems.yml
|
||||
with:
|
||||
python-versions: '["3.10.x", "3.11.x", "3.12.x"]'
|
||||
secrets: inherit
|
||||
|
|
@ -124,7 +124,7 @@ jobs:
|
|||
cli-tests,
|
||||
graph-db-tests,
|
||||
notebook-tests,
|
||||
python-version-tests,
|
||||
different-operating-systems-tests,
|
||||
vector-db-tests,
|
||||
example-tests,
|
||||
gemini-tests,
|
||||
|
|
@ -144,7 +144,7 @@ jobs:
|
|||
cli-tests,
|
||||
graph-db-tests,
|
||||
notebook-tests,
|
||||
python-version-tests,
|
||||
different-operating-systems-tests,
|
||||
vector-db-tests,
|
||||
example-tests,
|
||||
db-examples-tests,
|
||||
|
|
@ -165,7 +165,7 @@ jobs:
|
|||
"${{ needs.cli-tests.result }}" == "success" &&
|
||||
"${{ needs.graph-db-tests.result }}" == "success" &&
|
||||
"${{ needs.notebook-tests.result }}" == "success" &&
|
||||
"${{ needs.python-version-tests.result }}" == "success" &&
|
||||
"${{ needs.different-operating-systems-tests.result }}" == "success" &&
|
||||
"${{ needs.vector-db-tests.result }}" == "success" &&
|
||||
"${{ needs.example-tests.result }}" == "success" &&
|
||||
"${{ needs.db-examples-tests.result }}" == "success" &&
|
||||
|
|
|
|||
|
|
@ -103,23 +103,159 @@ If you’d rather run cognee-mcp in a container, you have two options:
|
|||
3. Run it:
|
||||
```bash
|
||||
# For HTTP transport (recommended for web deployments)
|
||||
docker run --env-file ./.env -p 8000:8000 --rm -it cognee/cognee-mcp:main --transport http
|
||||
docker run -e TRANSPORT_MODE=http --env-file ./.env -p 8000:8000 --rm -it cognee/cognee-mcp:main
|
||||
# For SSE transport
|
||||
docker run --env-file ./.env -p 8000:8000 --rm -it cognee/cognee-mcp:main --transport sse
|
||||
docker run -e TRANSPORT_MODE=sse --env-file ./.env -p 8000:8000 --rm -it cognee/cognee-mcp:main
|
||||
# For stdio transport (default)
|
||||
docker run --env-file ./.env --rm -it cognee/cognee-mcp:main
|
||||
docker run -e TRANSPORT_MODE=stdio --env-file ./.env --rm -it cognee/cognee-mcp:main
|
||||
```
|
||||
2. **Pull from Docker Hub** (no build required):
|
||||
```bash
|
||||
# With HTTP transport (recommended for web deployments)
|
||||
docker run --env-file ./.env -p 8000:8000 --rm -it cognee/cognee-mcp:main --transport http
|
||||
docker run -e TRANSPORT_MODE=http --env-file ./.env -p 8000:8000 --rm -it cognee/cognee-mcp:main
|
||||
# With SSE transport
|
||||
docker run --env-file ./.env -p 8000:8000 --rm -it cognee/cognee-mcp:main --transport sse
|
||||
docker run -e TRANSPORT_MODE=sse --env-file ./.env -p 8000:8000 --rm -it cognee/cognee-mcp:main
|
||||
# With stdio transport (default)
|
||||
docker run --env-file ./.env --rm -it cognee/cognee-mcp:main
|
||||
docker run -e TRANSPORT_MODE=stdio --env-file ./.env --rm -it cognee/cognee-mcp:main
|
||||
```
|
||||
|
||||
### **Important: Docker vs Direct Usage**
|
||||
**Docker uses environment variables**, not command line arguments:
|
||||
- ✅ Docker: `-e TRANSPORT_MODE=http`
|
||||
- ❌ Docker: `--transport http` (won't work)
|
||||
|
||||
**Direct Python usage** uses command line arguments:
|
||||
- ✅ Direct: `python src/server.py --transport http`
|
||||
- ❌ Direct: `-e TRANSPORT_MODE=http` (won't work)
|
||||
|
||||
|
||||
## 💻 Basic Usage
|
||||
## 🔗 MCP Client Configuration
|
||||
|
||||
After starting your Cognee MCP server with Docker, you need to configure your MCP client to connect to it.
|
||||
|
||||
### **SSE Transport Configuration** (Recommended)
|
||||
|
||||
**Start the server with SSE transport:**
|
||||
```bash
|
||||
docker run -e TRANSPORT_MODE=sse --env-file ./.env -p 8000:8000 --rm -it cognee/cognee-mcp:main
|
||||
```
|
||||
|
||||
**Configure your MCP client:**
|
||||
|
||||
#### **Claude CLI (Easiest)**
|
||||
```bash
|
||||
claude mcp add cognee-sse -t sse http://localhost:8000/sse
|
||||
```
|
||||
|
||||
**Verify the connection:**
|
||||
```bash
|
||||
claude mcp list
|
||||
```
|
||||
|
||||
You should see your server connected:
|
||||
```
|
||||
Checking MCP server health...
|
||||
|
||||
cognee-sse: http://localhost:8000/sse (SSE) - ✓ Connected
|
||||
```
|
||||
|
||||
#### **Manual Configuration**
|
||||
|
||||
**Claude (`~/.claude.json`)**
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"cognee": {
|
||||
"type": "sse",
|
||||
"url": "http://localhost:8000/sse"
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Cursor (`~/.cursor/mcp.json`)**
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"cognee-sse": {
|
||||
"url": "http://localhost:8000/sse"
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### **HTTP Transport Configuration** (Alternative)
|
||||
|
||||
**Start the server with HTTP transport:**
|
||||
```bash
|
||||
docker run -e TRANSPORT_MODE=http --env-file ./.env -p 8000:8000 --rm -it cognee/cognee-mcp:main
|
||||
```
|
||||
|
||||
**Configure your MCP client:**
|
||||
|
||||
#### **Claude CLI (Easiest)**
|
||||
```bash
|
||||
claude mcp add cognee-http -t http http://localhost:8000/mcp
|
||||
```
|
||||
|
||||
**Verify the connection:**
|
||||
```bash
|
||||
claude mcp list
|
||||
```
|
||||
|
||||
You should see your server connected:
|
||||
```
|
||||
Checking MCP server health...
|
||||
|
||||
cognee-http: http://localhost:8000/mcp (HTTP) - ✓ Connected
|
||||
```
|
||||
|
||||
#### **Manual Configuration**
|
||||
|
||||
**Claude (`~/.claude.json`)**
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"cognee": {
|
||||
"type": "http",
|
||||
"url": "http://localhost:8000/mcp"
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Cursor (`~/.cursor/mcp.json`)**
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"cognee-http": {
|
||||
"url": "http://localhost:8000/mcp"
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### **Dual Configuration Example**
|
||||
You can configure both transports simultaneously for testing:
|
||||
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"cognee-sse": {
|
||||
"type": "sse",
|
||||
"url": "http://localhost:8000/sse"
|
||||
},
|
||||
"cognee-http": {
|
||||
"type": "http",
|
||||
"url": "http://localhost:8000/mcp"
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Note:** Only enable the server you're actually running to avoid connection errors.
|
||||
|
||||
## 💻 Basic Usage
|
||||
|
||||
The MCP server exposes its functionality through tools. Call them from any MCP client (Cursor, Claude Desktop, Cline, Roo and more).
|
||||
|
||||
|
|
@ -155,45 +291,6 @@ delete(data_id="data-uuid", dataset_id="dataset-uuid", mode="soft")
|
|||
delete(data_id="data-uuid", dataset_id="dataset-uuid", mode="hard")
|
||||
```
|
||||
|
||||
Remember – use the CODE search type to query your code graph. For huge repos, run codify on modules incrementally and cache results.
|
||||
|
||||
### IDE Example: Cursor
|
||||
|
||||
1. After you run the server as described in the [Quick Start](#-quickstart), create a run script for cognee. Here is a simple example:
|
||||
```
|
||||
#!/bin/bash
|
||||
export ENV=local
|
||||
export TOKENIZERS_PARALLELISM=false
|
||||
export EMBEDDING_PROVIDER="fastembed"
|
||||
export EMBEDDING_MODEL="sentence-transformers/all-MiniLM-L6-v2"
|
||||
export EMBEDDING_DIMENSIONS=384
|
||||
export EMBEDDING_MAX_TOKENS=256
|
||||
export LLM_API_KEY=your-OpenAI-API-key
|
||||
uv --directory /{cognee_root_path}/cognee-mcp run cognee
|
||||
```
|
||||
Remember to replace *your-OpenAI-API-key* and *{cognee_root_path}* with correct values.
|
||||
|
||||
2. Install Cursor and navigate to Settings → MCP Tools → New MCP Server
|
||||
|
||||
3. Cursor will open *mcp.json* file in a new tab. Configure your cognee MCP server by copy-pasting the following:
|
||||
```
|
||||
{
|
||||
"mcpServers": {
|
||||
"cognee": {
|
||||
"command": "sh",
|
||||
"args": [
|
||||
"/{path-to-your-script}/run-cognee.sh"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
Remember to replace *{path-to-your-script}* with the correct value of the path of the script you created in the first step.
|
||||
|
||||
That's it! You can refresh the server from the toggle next to your new cognee server. Check the green dot and the available tools to verify your server is running.
|
||||
|
||||
Now you can open your Cursor Agent and start using cognee tools from it via prompting.
|
||||
|
||||
|
||||
## Development and Debugging
|
||||
|
||||
|
|
@ -211,7 +308,7 @@ Open inspector with timeout passed:
|
|||
|
||||
To apply new changes while developing cognee you need to do:
|
||||
|
||||
1. `poetry lock` in cognee folder
|
||||
1. Update dependencies in cognee folder if needed
|
||||
2. `uv sync --dev --all-extras --reinstall`
|
||||
3. `mcp dev src/server.py`
|
||||
|
||||
|
|
|
|||
|
|
@ -8,7 +8,7 @@ requires-python = ">=3.10"
|
|||
dependencies = [
|
||||
# For local cognee repo usage remove comment bellow and add absolute path to cognee. Then run `uv sync --reinstall` in the mcp folder on local cognee changes.
|
||||
# "cognee[postgres,codegraph,gemini,huggingface,docs,neo4j] @ file:/Users/vasilije/Projects/tiktok/cognee",
|
||||
"cognee[postgres,codegraph,gemini,huggingface,docs,neo4j]==0.2.2",
|
||||
"cognee[postgres,codegraph,gemini,huggingface,docs,neo4j]==0.2.3",
|
||||
"fastmcp>=2.10.0,<3.0.0",
|
||||
"mcp>=1.12.0,<2.0.0",
|
||||
"uv>=0.6.3,<1.0.0",
|
||||
|
|
|
|||
|
|
@ -21,16 +21,16 @@ from cognee.shared.data_models import KnowledgeGraph
|
|||
from cognee.modules.storage.utils import JSONEncoder
|
||||
|
||||
|
||||
try:
|
||||
from codingagents.coding_rule_associations import (
|
||||
add_rule_associations,
|
||||
get_existing_rules,
|
||||
)
|
||||
except ModuleNotFoundError:
|
||||
from .codingagents.coding_rule_associations import (
|
||||
add_rule_associations,
|
||||
get_existing_rules,
|
||||
)
|
||||
# try:
|
||||
# from codingagents.coding_rule_associations import (
|
||||
# add_rule_associations,
|
||||
# get_existing_rules,
|
||||
# )
|
||||
# except ModuleNotFoundError:
|
||||
# from .codingagents.coding_rule_associations import (
|
||||
# add_rule_associations,
|
||||
# get_existing_rules,
|
||||
# )
|
||||
|
||||
|
||||
mcp = FastMCP("Cognee")
|
||||
|
|
@ -121,7 +121,9 @@ async def cognee_add_developer_rules(
|
|||
|
||||
|
||||
@mcp.tool()
|
||||
async def cognify(data: str, graph_model_file: str = None, graph_model_name: str = None) -> list:
|
||||
async def cognify(
|
||||
data: str, graph_model_file: str = None, graph_model_name: str = None, custom_prompt: str = None
|
||||
) -> list:
|
||||
"""
|
||||
Transform ingested data into a structured knowledge graph.
|
||||
|
||||
|
|
@ -169,6 +171,12 @@ async def cognify(data: str, graph_model_file: str = None, graph_model_name: str
|
|||
Required if graph_model_file is specified.
|
||||
Default is None, which uses the default KnowledgeGraph class.
|
||||
|
||||
custom_prompt : str, optional
|
||||
Custom prompt string to use for entity extraction and graph generation.
|
||||
If provided, this prompt will be used instead of the default prompts for
|
||||
knowledge graph extraction. The prompt should guide the LLM on how to
|
||||
extract entities and relationships from the text content.
|
||||
|
||||
Returns
|
||||
-------
|
||||
list
|
||||
|
|
@ -224,7 +232,10 @@ async def cognify(data: str, graph_model_file: str = None, graph_model_name: str
|
|||
"""
|
||||
|
||||
async def cognify_task(
|
||||
data: str, graph_model_file: str = None, graph_model_name: str = None
|
||||
data: str,
|
||||
graph_model_file: str = None,
|
||||
graph_model_name: str = None,
|
||||
custom_prompt: str = None,
|
||||
) -> str:
|
||||
"""Build knowledge graph from the input text"""
|
||||
# NOTE: MCP uses stdout to communicate, we must redirect all output
|
||||
|
|
@ -239,7 +250,7 @@ async def cognify(data: str, graph_model_file: str = None, graph_model_name: str
|
|||
await cognee.add(data)
|
||||
|
||||
try:
|
||||
await cognee.cognify(graph_model=graph_model)
|
||||
await cognee.cognify(graph_model=graph_model, custom_prompt=custom_prompt)
|
||||
logger.info("Cognify process finished.")
|
||||
except Exception as e:
|
||||
logger.error("Cognify process failed.")
|
||||
|
|
@ -250,6 +261,7 @@ async def cognify(data: str, graph_model_file: str = None, graph_model_name: str
|
|||
data=data,
|
||||
graph_model_file=graph_model_file,
|
||||
graph_model_name=graph_model_name,
|
||||
custom_prompt=custom_prompt,
|
||||
)
|
||||
)
|
||||
|
||||
|
|
@ -298,7 +310,7 @@ async def save_interaction(data: str) -> list:
|
|||
logger.info("Save interaction process finished.")
|
||||
logger.info("Generating associated rules from interaction data.")
|
||||
|
||||
await add_rule_associations(data=data, rules_nodeset_name="coding_agent_rules")
|
||||
# await add_rule_associations(data=data, rules_nodeset_name="coding_agent_rules")
|
||||
|
||||
logger.info("Associated rules generated from interaction data.")
|
||||
|
||||
|
|
@ -560,8 +572,10 @@ async def get_developer_rules() -> list:
|
|||
async def fetch_rules_from_cognee() -> str:
|
||||
"""Collect all developer rules from Cognee"""
|
||||
with redirect_stdout(sys.stderr):
|
||||
developer_rules = await get_existing_rules(rules_nodeset_name="coding_agent_rules")
|
||||
return developer_rules
|
||||
note = "This is broken in 0.2.2"
|
||||
return note
|
||||
# developer_rules = await get_existing_rules(rules_nodeset_name="coding_agent_rules")
|
||||
# return developer_rules
|
||||
|
||||
rules_text = await fetch_rules_from_cognee()
|
||||
|
||||
|
|
|
|||
|
|
@ -40,8 +40,14 @@ async def run_code_graph_pipeline(repo_path, include_docs=False):
|
|||
user = await get_default_user()
|
||||
detailed_extraction = True
|
||||
|
||||
# Multi-language support: allow passing supported_languages
|
||||
supported_languages = None # defer to task defaults
|
||||
tasks = [
|
||||
Task(get_repo_file_dependencies, detailed_extraction=detailed_extraction),
|
||||
Task(
|
||||
get_repo_file_dependencies,
|
||||
detailed_extraction=detailed_extraction,
|
||||
supported_languages=supported_languages,
|
||||
),
|
||||
# Task(summarize_code, task_config={"batch_size": 500}), # This task takes a long time to complete
|
||||
Task(add_data_points, task_config={"batch_size": 30}),
|
||||
]
|
||||
|
|
|
|||
|
|
@ -43,6 +43,7 @@ async def cognify(
|
|||
graph_db_config: dict = None,
|
||||
run_in_background: bool = False,
|
||||
incremental_loading: bool = True,
|
||||
custom_prompt: Optional[str] = None,
|
||||
temporal_cognify: bool = False,
|
||||
):
|
||||
"""
|
||||
|
|
@ -106,6 +107,10 @@ async def cognify(
|
|||
If False, waits for completion before returning.
|
||||
Background mode recommended for large datasets (>100MB).
|
||||
Use pipeline_run_id from return value to monitor progress.
|
||||
custom_prompt: Optional custom prompt string to use for entity extraction and graph generation.
|
||||
If provided, this prompt will be used instead of the default prompts for
|
||||
knowledge graph extraction. The prompt should guide the LLM on how to
|
||||
extract entities and relationships from the text content.
|
||||
|
||||
Returns:
|
||||
Union[dict, list[PipelineRunInfo]]:
|
||||
|
|
@ -185,7 +190,7 @@ async def cognify(
|
|||
if temporal_cognify:
|
||||
tasks = await get_temporal_tasks(user, chunker, chunk_size)
|
||||
else:
|
||||
tasks = await get_default_tasks(user, graph_model, chunker, chunk_size, ontology_file_path)
|
||||
tasks = await get_default_tasks(user, graph_model, chunker, chunk_size, ontology_file_path, custom_prompt)
|
||||
|
||||
# By calling get pipeline executor we get a function that will have the run_pipeline run in the background or a function that we will need to wait for
|
||||
pipeline_executor_func = get_pipeline_executor(run_in_background=run_in_background)
|
||||
|
|
@ -209,6 +214,7 @@ async def get_default_tasks( # TODO: Find out a better way to do this (Boris's
|
|||
chunker=TextChunker,
|
||||
chunk_size: int = None,
|
||||
ontology_file_path: Optional[str] = None,
|
||||
custom_prompt: Optional[str] = None,
|
||||
) -> list[Task]:
|
||||
default_tasks = [
|
||||
Task(classify_documents),
|
||||
|
|
@ -222,6 +228,7 @@ async def get_default_tasks( # TODO: Find out a better way to do this (Boris's
|
|||
extract_graph_from_data,
|
||||
graph_model=graph_model,
|
||||
ontology_adapter=OntologyResolver(ontology_file=ontology_file_path),
|
||||
custom_prompt=custom_prompt,
|
||||
task_config={"batch_size": 10},
|
||||
), # Generate knowledge graphs from the document chunks.
|
||||
Task(
|
||||
|
|
|
|||
|
|
@ -37,6 +37,9 @@ class CognifyPayloadDTO(InDTO):
|
|||
datasets: Optional[List[str]] = Field(default=None)
|
||||
dataset_ids: Optional[List[UUID]] = Field(default=None, examples=[[]])
|
||||
run_in_background: Optional[bool] = Field(default=False)
|
||||
custom_prompt: Optional[str] = Field(
|
||||
default=None, description="Custom prompt for entity extraction and graph generation"
|
||||
)
|
||||
|
||||
|
||||
def get_cognify_router() -> APIRouter:
|
||||
|
|
@ -63,6 +66,7 @@ def get_cognify_router() -> APIRouter:
|
|||
- **datasets** (Optional[List[str]]): List of dataset names to process. Dataset names are resolved to datasets owned by the authenticated user.
|
||||
- **dataset_ids** (Optional[List[UUID]]): List of existing dataset UUIDs to process. UUIDs allow processing of datasets not owned by the user (if permitted).
|
||||
- **run_in_background** (Optional[bool]): Whether to execute processing asynchronously. Defaults to False (blocking).
|
||||
- **custom_prompt** (Optional[str]): Custom prompt for entity extraction and graph generation. If provided, this prompt will be used instead of the default prompts for knowledge graph extraction.
|
||||
|
||||
## Response
|
||||
- **Blocking execution**: Complete pipeline run information with entity counts, processing duration, and success/failure status
|
||||
|
|
@ -76,7 +80,8 @@ def get_cognify_router() -> APIRouter:
|
|||
```json
|
||||
{
|
||||
"datasets": ["research_papers", "documentation"],
|
||||
"run_in_background": false
|
||||
"run_in_background": false,
|
||||
"custom_prompt": "Extract entities focusing on technical concepts and their relationships. Identify key technologies, methodologies, and their interconnections."
|
||||
}
|
||||
```
|
||||
|
||||
|
|
@ -106,7 +111,10 @@ def get_cognify_router() -> APIRouter:
|
|||
datasets = payload.dataset_ids if payload.dataset_ids else payload.datasets
|
||||
|
||||
cognify_run = await cognee_cognify(
|
||||
datasets, user, run_in_background=payload.run_in_background
|
||||
datasets,
|
||||
user,
|
||||
run_in_background=payload.run_in_background,
|
||||
custom_prompt=payload.custom_prompt,
|
||||
)
|
||||
|
||||
# If any cognify run errored return JSONResponse with proper error status code
|
||||
|
|
|
|||
|
|
@ -49,6 +49,10 @@ DEFAULT_TOOLS = [
|
|||
"type": "string",
|
||||
"description": "Path to a custom ontology file",
|
||||
},
|
||||
"custom_prompt": {
|
||||
"type": "string",
|
||||
"description": "Custom prompt for entity extraction and graph generation. If provided, this prompt will be used instead of the default prompts.",
|
||||
},
|
||||
},
|
||||
"required": ["text"],
|
||||
},
|
||||
|
|
|
|||
|
|
@ -88,11 +88,16 @@ async def handle_cognify(arguments: Dict[str, Any], user) -> str:
|
|||
"""Handle cognify function call"""
|
||||
text = arguments.get("text")
|
||||
ontology_file_path = arguments.get("ontology_file_path")
|
||||
custom_prompt = arguments.get("custom_prompt")
|
||||
|
||||
if text:
|
||||
await add(data=text, user=user)
|
||||
|
||||
await cognify(user=user, ontology_file_path=ontology_file_path if ontology_file_path else None)
|
||||
await cognify(
|
||||
user=user,
|
||||
ontology_file_path=ontology_file_path if ontology_file_path else None,
|
||||
custom_prompt=custom_prompt,
|
||||
)
|
||||
|
||||
return (
|
||||
"Text successfully converted into knowledge graph."
|
||||
|
|
|
|||
|
|
@ -87,12 +87,12 @@ After successful cognify processing, use `cognee search` to query the knowledge
|
|||
async def run_cognify():
|
||||
try:
|
||||
# Import chunker classes here
|
||||
from cognee.modules.chunking import TextChunker
|
||||
from cognee.modules.chunking.TextChunker import TextChunker
|
||||
|
||||
chunker_class = TextChunker # Default
|
||||
if args.chunker == "LangchainChunker":
|
||||
try:
|
||||
from cognee.modules.chunking import LangchainChunker
|
||||
from cognee.modules.chunking.LangchainChunker import LangchainChunker
|
||||
|
||||
chunker_class = LangchainChunker
|
||||
except ImportError:
|
||||
|
|
|
|||
|
|
@ -5,19 +5,24 @@ from urllib.parse import urlparse
|
|||
def get_data_file_path(file_path: str):
|
||||
# Check if this is a file URI BEFORE normalizing (which corrupts URIs)
|
||||
if file_path.startswith("file://"):
|
||||
# Remove first occurrence of file:// prefix
|
||||
pure_file_path = file_path.replace("file://", "", 1)
|
||||
# Normalize the file URI for Windows - replace backslashes with forward slashes
|
||||
normalized_file_uri = os.path.normpath(file_path)
|
||||
normalized_file_uri = os.path.normpath(pure_file_path)
|
||||
|
||||
parsed_url = urlparse(normalized_file_uri)
|
||||
|
||||
# Convert URI path to file system path
|
||||
# Convert path to proper file system path
|
||||
if os.name == "nt": # Windows
|
||||
# Handle Windows drive letters correctly
|
||||
fs_path = parsed_url.path
|
||||
if fs_path.startswith("/") and len(fs_path) > 1 and fs_path[2] == ":":
|
||||
fs_path = fs_path[1:] # Remove leading slash for Windows drive paths
|
||||
else: # Unix-like systems
|
||||
fs_path = parsed_url.path
|
||||
fs_path = normalized_file_uri
|
||||
if (
|
||||
(fs_path.startswith("/") or fs_path.startswith("\\"))
|
||||
and len(fs_path) > 1
|
||||
and fs_path[2] == ":"
|
||||
):
|
||||
fs_path = fs_path[1:]
|
||||
else:
|
||||
# Unix - like systems
|
||||
fs_path = normalized_file_uri
|
||||
|
||||
# Now split the actual filesystem path
|
||||
actual_fs_path = os.path.normpath(fs_path)
|
||||
|
|
|
|||
|
|
@ -1,6 +1,7 @@
|
|||
import io
|
||||
import os.path
|
||||
from typing import BinaryIO, TypedDict
|
||||
from pathlib import Path
|
||||
|
||||
from cognee.shared.logging_utils import get_logger
|
||||
from cognee.infrastructure.files.utils.get_file_content_hash import get_file_content_hash
|
||||
|
|
@ -55,7 +56,7 @@ async def get_file_metadata(file: BinaryIO) -> FileMetadata:
|
|||
file_type = guess_file_type(file)
|
||||
|
||||
file_path = getattr(file, "name", None) or getattr(file, "full_name", None)
|
||||
file_name = str(file_path).split("/")[-1].split(".")[0] if file_path else None
|
||||
file_name = Path(file_path).stem if file_path else None
|
||||
|
||||
# Get file size
|
||||
pos = file.tell() # remember current pointer
|
||||
|
|
|
|||
|
|
@ -1,6 +1,5 @@
|
|||
from typing import Type
|
||||
from typing import Type, Optional, Coroutine
|
||||
from pydantic import BaseModel
|
||||
from typing import Coroutine
|
||||
from cognee.infrastructure.llm import get_llm_config
|
||||
|
||||
|
||||
|
|
@ -79,7 +78,10 @@ class LLMGateway:
|
|||
|
||||
@staticmethod
|
||||
def extract_content_graph(
|
||||
content: str, response_model: Type[BaseModel], mode: str = "simple"
|
||||
content: str,
|
||||
response_model: Type[BaseModel],
|
||||
mode: str = "simple",
|
||||
custom_prompt: Optional[str] = None,
|
||||
) -> Coroutine:
|
||||
llm_config = get_llm_config()
|
||||
if llm_config.structured_output_framework.upper() == "BAML":
|
||||
|
|
@ -87,13 +89,20 @@ class LLMGateway:
|
|||
extract_content_graph,
|
||||
)
|
||||
|
||||
return extract_content_graph(content=content, response_model=response_model, mode=mode)
|
||||
return extract_content_graph(
|
||||
content=content,
|
||||
response_model=response_model,
|
||||
mode=mode,
|
||||
custom_prompt=custom_prompt,
|
||||
)
|
||||
else:
|
||||
from cognee.infrastructure.llm.structured_output_framework.litellm_instructor.extraction import (
|
||||
extract_content_graph,
|
||||
)
|
||||
|
||||
return extract_content_graph(content=content, response_model=response_model)
|
||||
return extract_content_graph(
|
||||
content=content, response_model=response_model, custom_prompt=custom_prompt
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def extract_categories(content: str, response_model: Type[BaseModel]) -> Coroutine:
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
from typing import Type
|
||||
from typing import Type, Optional
|
||||
from pydantic import BaseModel
|
||||
from cognee.infrastructure.llm.config import get_llm_config
|
||||
from cognee.shared.logging_utils import get_logger, setup_logging
|
||||
|
|
@ -6,7 +6,10 @@ from cognee.infrastructure.llm.structured_output_framework.baml.baml_client.asyn
|
|||
|
||||
|
||||
async def extract_content_graph(
|
||||
content: str, response_model: Type[BaseModel], mode: str = "simple"
|
||||
content: str,
|
||||
response_model: Type[BaseModel],
|
||||
mode: str = "simple",
|
||||
custom_prompt: Optional[str] = None,
|
||||
):
|
||||
config = get_llm_config()
|
||||
setup_logging()
|
||||
|
|
@ -26,8 +29,16 @@ async def extract_content_graph(
|
|||
# return graph
|
||||
|
||||
# else:
|
||||
graph = await b.ExtractContentGraphGeneric(
|
||||
content, mode=mode, baml_options={"client_registry": config.baml_registry}
|
||||
)
|
||||
if custom_prompt:
|
||||
graph = await b.ExtractContentGraphGeneric(
|
||||
content,
|
||||
mode="custom",
|
||||
custom_prompt_content=custom_prompt,
|
||||
baml_options={"client_registry": config.baml_registry},
|
||||
)
|
||||
else:
|
||||
graph = await b.ExtractContentGraphGeneric(
|
||||
content, mode=mode, baml_options={"client_registry": config.baml_registry}
|
||||
)
|
||||
|
||||
return graph
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
import os
|
||||
from typing import Type
|
||||
from typing import Type, Optional
|
||||
from pydantic import BaseModel
|
||||
|
||||
from cognee.infrastructure.llm.LLMGateway import LLMGateway
|
||||
|
|
@ -8,21 +8,25 @@ from cognee.infrastructure.llm.config import (
|
|||
)
|
||||
|
||||
|
||||
async def extract_content_graph(content: str, response_model: Type[BaseModel]):
|
||||
llm_config = get_llm_config()
|
||||
|
||||
prompt_path = llm_config.graph_prompt_path
|
||||
|
||||
# Check if the prompt path is an absolute path or just a filename
|
||||
if os.path.isabs(prompt_path):
|
||||
# directory containing the file
|
||||
base_directory = os.path.dirname(prompt_path)
|
||||
# just the filename itself
|
||||
prompt_path = os.path.basename(prompt_path)
|
||||
async def extract_content_graph(
|
||||
content: str, response_model: Type[BaseModel], custom_prompt: Optional[str] = None
|
||||
):
|
||||
if custom_prompt:
|
||||
system_prompt = custom_prompt
|
||||
else:
|
||||
base_directory = None
|
||||
llm_config = get_llm_config()
|
||||
prompt_path = llm_config.graph_prompt_path
|
||||
|
||||
system_prompt = LLMGateway.render_prompt(prompt_path, {}, base_directory=base_directory)
|
||||
# Check if the prompt path is an absolute path or just a filename
|
||||
if os.path.isabs(prompt_path):
|
||||
# directory containing the file
|
||||
base_directory = os.path.dirname(prompt_path)
|
||||
# just the filename itself
|
||||
prompt_path = os.path.basename(prompt_path)
|
||||
else:
|
||||
base_directory = None
|
||||
|
||||
system_prompt = LLMGateway.render_prompt(prompt_path, {}, base_directory=base_directory)
|
||||
|
||||
content_graph = await LLMGateway.acreate_structured_output(
|
||||
content, system_prompt, response_model
|
||||
|
|
|
|||
|
|
@ -266,48 +266,24 @@ async def run_tasks(
|
|||
if incremental_loading:
|
||||
data = await resolve_data_directories(data)
|
||||
|
||||
# TODO: Return to using async.gather for data items after Cognee release
|
||||
# # Create async tasks per data item that will run the pipeline for the data item
|
||||
# data_item_tasks = [
|
||||
# asyncio.create_task(
|
||||
# _run_tasks_data_item(
|
||||
# data_item,
|
||||
# dataset,
|
||||
# tasks,
|
||||
# pipeline_name,
|
||||
# pipeline_id,
|
||||
# pipeline_run_id,
|
||||
# context,
|
||||
# user,
|
||||
# incremental_loading,
|
||||
# )
|
||||
# )
|
||||
# for data_item in data
|
||||
# ]
|
||||
# results = await asyncio.gather(*data_item_tasks)
|
||||
# # Remove skipped data items from results
|
||||
# results = [result for result in results if result]
|
||||
|
||||
### TEMP sync data item handling
|
||||
results = []
|
||||
# Run the pipeline for each data_item sequentially, one after the other
|
||||
for data_item in data:
|
||||
result = await _run_tasks_data_item(
|
||||
data_item,
|
||||
dataset,
|
||||
tasks,
|
||||
pipeline_name,
|
||||
pipeline_id,
|
||||
pipeline_run_id,
|
||||
context,
|
||||
user,
|
||||
incremental_loading,
|
||||
# Create async tasks per data item that will run the pipeline for the data item
|
||||
data_item_tasks = [
|
||||
asyncio.create_task(
|
||||
_run_tasks_data_item(
|
||||
data_item,
|
||||
dataset,
|
||||
tasks,
|
||||
pipeline_name,
|
||||
pipeline_id,
|
||||
pipeline_run_id,
|
||||
context,
|
||||
user,
|
||||
incremental_loading,
|
||||
)
|
||||
)
|
||||
|
||||
# Skip items that returned a false-y value
|
||||
if result:
|
||||
results.append(result)
|
||||
### END
|
||||
for data_item in data
|
||||
]
|
||||
results = await asyncio.gather(*data_item_tasks)
|
||||
|
||||
# Remove skipped data items from results
|
||||
results = [result for result in results if result]
|
||||
|
|
|
|||
|
|
@ -1,37 +0,0 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "initial_id",
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 2
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython2",
|
||||
"version": "2.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
|
|
@ -36,6 +36,7 @@ class ClassDefinition(DataPoint):
|
|||
class CodeFile(DataPoint):
|
||||
name: str
|
||||
file_path: str
|
||||
language: Optional[str] = None # e.g., 'python', 'javascript', 'java', etc.
|
||||
source_code: Optional[str] = None
|
||||
part_of: Optional[Repository] = None
|
||||
depends_on: Optional[List["ImportStatement"]] = []
|
||||
|
|
|
|||
|
|
@ -15,14 +15,43 @@ from typing import Protocol
|
|||
# Configure external library logging
|
||||
def configure_external_library_logging():
|
||||
"""Configure logging for external libraries to reduce verbosity"""
|
||||
# Set environment variables to suppress LiteLLM logging
|
||||
os.environ.setdefault("LITELLM_LOG", "ERROR")
|
||||
os.environ.setdefault("LITELLM_SET_VERBOSE", "False")
|
||||
|
||||
# Configure LiteLLM logging to reduce verbosity
|
||||
try:
|
||||
import litellm
|
||||
|
||||
# Disable verbose logging
|
||||
litellm.set_verbose = False
|
||||
|
||||
# Suppress LiteLLM ERROR logging using standard logging
|
||||
logging.getLogger("litellm").setLevel(logging.CRITICAL)
|
||||
# Set additional LiteLLM configuration
|
||||
if hasattr(litellm, "suppress_debug_info"):
|
||||
litellm.suppress_debug_info = True
|
||||
if hasattr(litellm, "turn_off_message"):
|
||||
litellm.turn_off_message = True
|
||||
if hasattr(litellm, "_turn_on_debug"):
|
||||
litellm._turn_on_debug = False
|
||||
|
||||
# Comprehensive logger suppression
|
||||
loggers_to_suppress = [
|
||||
"litellm",
|
||||
"litellm.litellm_core_utils.logging_worker",
|
||||
"litellm.litellm_core_utils",
|
||||
"litellm.proxy",
|
||||
"litellm.router",
|
||||
"openai._base_client",
|
||||
"LiteLLM", # Capital case variant
|
||||
"LiteLLM.core",
|
||||
"LiteLLM.logging_worker",
|
||||
"litellm.logging_worker",
|
||||
]
|
||||
|
||||
for logger_name in loggers_to_suppress:
|
||||
logging.getLogger(logger_name).setLevel(logging.CRITICAL)
|
||||
logging.getLogger(logger_name).disabled = True
|
||||
|
||||
except ImportError:
|
||||
# LiteLLM not available, skip configuration
|
||||
pass
|
||||
|
|
@ -244,6 +273,75 @@ def setup_logging(log_level=None, name=None):
|
|||
# Configure external library logging early to suppress verbose output
|
||||
configure_external_library_logging()
|
||||
|
||||
# Add custom filter to suppress LiteLLM worker cancellation errors
|
||||
class LiteLLMCancellationFilter(logging.Filter):
|
||||
"""Filter to suppress LiteLLM worker cancellation messages"""
|
||||
|
||||
def filter(self, record):
|
||||
# Check if this is a LiteLLM-related logger
|
||||
if hasattr(record, "name") and "litellm" in record.name.lower():
|
||||
return False
|
||||
|
||||
# Check message content for cancellation errors
|
||||
if hasattr(record, "msg") and record.msg:
|
||||
msg_str = str(record.msg).lower()
|
||||
if any(
|
||||
keyword in msg_str
|
||||
for keyword in [
|
||||
"loggingworker cancelled",
|
||||
"logging_worker.py",
|
||||
"cancellederror",
|
||||
"litellm:error",
|
||||
]
|
||||
):
|
||||
return False
|
||||
|
||||
# Check formatted message
|
||||
try:
|
||||
if hasattr(record, "getMessage"):
|
||||
formatted_msg = record.getMessage().lower()
|
||||
if any(
|
||||
keyword in formatted_msg
|
||||
for keyword in [
|
||||
"loggingworker cancelled",
|
||||
"logging_worker.py",
|
||||
"cancellederror",
|
||||
"litellm:error",
|
||||
]
|
||||
):
|
||||
return False
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return True
|
||||
|
||||
# Apply the filter to root logger and specific loggers
|
||||
cancellation_filter = LiteLLMCancellationFilter()
|
||||
logging.getLogger().addFilter(cancellation_filter)
|
||||
logging.getLogger("litellm").addFilter(cancellation_filter)
|
||||
|
||||
# Add custom filter to suppress LiteLLM worker cancellation errors
|
||||
class LiteLLMFilter(logging.Filter):
|
||||
def filter(self, record):
|
||||
# Suppress LiteLLM worker cancellation errors
|
||||
if hasattr(record, "msg") and isinstance(record.msg, str):
|
||||
msg_lower = record.msg.lower()
|
||||
if any(
|
||||
phrase in msg_lower
|
||||
for phrase in [
|
||||
"loggingworker cancelled",
|
||||
"cancellederror",
|
||||
"logging_worker.py",
|
||||
"loggingerror",
|
||||
]
|
||||
):
|
||||
return False
|
||||
return True
|
||||
|
||||
# Apply filter to root logger
|
||||
litellm_filter = LiteLLMFilter()
|
||||
logging.getLogger().addFilter(litellm_filter)
|
||||
|
||||
def exception_handler(logger, method_name, event_dict):
|
||||
"""Custom processor to handle uncaught exceptions."""
|
||||
# Check if there's an exc_info that needs to be processed
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
import asyncio
|
||||
from typing import Type, List
|
||||
from typing import Type, List, Optional
|
||||
from pydantic import BaseModel
|
||||
|
||||
from cognee.infrastructure.databases.graph import get_graph_engine
|
||||
|
|
@ -71,6 +71,7 @@ async def extract_graph_from_data(
|
|||
data_chunks: List[DocumentChunk],
|
||||
graph_model: Type[BaseModel],
|
||||
ontology_adapter: OntologyResolver = None,
|
||||
custom_prompt: Optional[str] = None,
|
||||
) -> List[DocumentChunk]:
|
||||
"""
|
||||
Extracts and integrates a knowledge graph from the text content of document chunks using a specified graph model.
|
||||
|
|
@ -84,7 +85,10 @@ async def extract_graph_from_data(
|
|||
raise InvalidGraphModelError(graph_model)
|
||||
|
||||
chunk_graphs = await asyncio.gather(
|
||||
*[LLMGateway.extract_content_graph(chunk.text, graph_model) for chunk in data_chunks]
|
||||
*[
|
||||
LLMGateway.extract_content_graph(chunk.text, graph_model, custom_prompt=custom_prompt)
|
||||
for chunk in data_chunks
|
||||
]
|
||||
)
|
||||
|
||||
# Note: Filter edges with missing source or target nodes
|
||||
|
|
|
|||
|
|
@ -180,6 +180,7 @@ async def get_local_script_dependencies(
|
|||
name=file_path_relative_to_repo,
|
||||
source_code=source_code,
|
||||
file_path=script_path,
|
||||
language="python",
|
||||
)
|
||||
return code_file_node
|
||||
|
||||
|
|
@ -188,6 +189,7 @@ async def get_local_script_dependencies(
|
|||
name=file_path_relative_to_repo,
|
||||
source_code=None,
|
||||
file_path=script_path,
|
||||
language="python",
|
||||
)
|
||||
|
||||
async for part in extract_code_parts(source_code_tree.root_node, script_path=script_path):
|
||||
|
|
|
|||
|
|
@ -10,50 +10,80 @@ from cognee.infrastructure.engine import DataPoint
|
|||
from cognee.shared.CodeGraphEntities import CodeFile, Repository
|
||||
|
||||
|
||||
async def get_source_code_files(repo_path):
|
||||
async def get_source_code_files(repo_path, language_config: dict[str, list[str]] | None = None):
|
||||
"""
|
||||
Retrieve Python source code files from the specified repository path.
|
||||
|
||||
This function scans the given repository path for files that have the .py extension
|
||||
while excluding test files and files within a virtual environment. It returns a list of
|
||||
absolute paths to the source code files that are not empty.
|
||||
Retrieve source code files from the specified repository path for multiple languages.
|
||||
|
||||
Parameters:
|
||||
-----------
|
||||
|
||||
- repo_path: The file path to the repository to search for Python source files.
|
||||
- repo_path: The file path to the repository to search for source files.
|
||||
- language_config: dict mapping language names to file extensions, e.g.,
|
||||
{'python': ['.py'], 'javascript': ['.js', '.jsx'], ...}
|
||||
|
||||
Returns:
|
||||
--------
|
||||
|
||||
A list of absolute paths to .py files that contain source code, excluding empty
|
||||
files, test files, and files from a virtual environment.
|
||||
A list of (absolute_path, language) tuples for source code files.
|
||||
"""
|
||||
if not os.path.exists(repo_path):
|
||||
return {}
|
||||
|
||||
py_files_paths = (
|
||||
os.path.join(root, file)
|
||||
for root, _, files in os.walk(repo_path)
|
||||
for file in files
|
||||
if (
|
||||
file.endswith(".py")
|
||||
and not file.startswith("test_")
|
||||
and not file.endswith("_test")
|
||||
and ".venv" not in file
|
||||
)
|
||||
)
|
||||
def _get_language_from_extension(file, language_config):
|
||||
for lang, exts in language_config.items():
|
||||
for ext in exts:
|
||||
if file.endswith(ext):
|
||||
return lang
|
||||
return None
|
||||
|
||||
# Default config if not provided
|
||||
if language_config is None:
|
||||
language_config = {
|
||||
"python": [".py"],
|
||||
"javascript": [".js", ".jsx"],
|
||||
"typescript": [".ts", ".tsx"],
|
||||
"java": [".java"],
|
||||
"csharp": [".cs"],
|
||||
"go": [".go"],
|
||||
"rust": [".rs"],
|
||||
"cpp": [".cpp", ".c", ".h", ".hpp"],
|
||||
}
|
||||
|
||||
if not os.path.exists(repo_path):
|
||||
return []
|
||||
|
||||
source_code_files = set()
|
||||
for file_path in py_files_paths:
|
||||
file_path = os.path.abspath(file_path)
|
||||
for root, _, files in os.walk(repo_path):
|
||||
for file in files:
|
||||
lang = _get_language_from_extension(file, language_config)
|
||||
if lang is None:
|
||||
continue
|
||||
# Exclude tests and common build/venv directories
|
||||
excluded_dirs = {
|
||||
".venv",
|
||||
"venv",
|
||||
"env",
|
||||
".env",
|
||||
"site-packages",
|
||||
"node_modules",
|
||||
"dist",
|
||||
"build",
|
||||
".git",
|
||||
"tests",
|
||||
"test",
|
||||
}
|
||||
root_parts = set(os.path.normpath(root).split(os.sep))
|
||||
base_name, _ext = os.path.splitext(file)
|
||||
if (
|
||||
base_name.startswith("test_")
|
||||
or base_name.endswith("_test") # catches Go's *_test.go and similar
|
||||
or ".test." in file
|
||||
or ".spec." in file
|
||||
or (excluded_dirs & root_parts)
|
||||
):
|
||||
continue
|
||||
file_path = os.path.abspath(os.path.join(root, file))
|
||||
if os.path.getsize(file_path) == 0:
|
||||
continue
|
||||
source_code_files.add((file_path, lang))
|
||||
|
||||
if os.path.getsize(file_path) == 0:
|
||||
continue
|
||||
|
||||
source_code_files.add(file_path)
|
||||
|
||||
return list(source_code_files)
|
||||
return sorted(list(source_code_files))
|
||||
|
||||
|
||||
def run_coroutine(coroutine_func, *args, **kwargs):
|
||||
|
|
@ -85,22 +115,23 @@ def run_coroutine(coroutine_func, *args, **kwargs):
|
|||
|
||||
|
||||
async def get_repo_file_dependencies(
|
||||
repo_path: str, detailed_extraction: bool = False
|
||||
repo_path: str, detailed_extraction: bool = False, supported_languages: list = None
|
||||
) -> AsyncGenerator[DataPoint, None]:
|
||||
"""
|
||||
Generate a dependency graph for Python files in the given repository path.
|
||||
Generate a dependency graph for source files (multi-language) in the given repository path.
|
||||
|
||||
Check the validity of the repository path and yield a repository object followed by the
|
||||
dependencies of Python files within that repository. Raise a FileNotFoundError if the
|
||||
dependencies of source files within that repository. Raise a FileNotFoundError if the
|
||||
provided path does not exist. The extraction of detailed dependencies can be controlled
|
||||
via the `detailed_extraction` argument.
|
||||
via the `detailed_extraction` argument. Languages considered can be restricted via
|
||||
the `supported_languages` argument.
|
||||
|
||||
Parameters:
|
||||
-----------
|
||||
|
||||
- repo_path (str): The file path to the repository where Python files are located.
|
||||
- detailed_extraction (bool): A flag indicating whether to perform a detailed
|
||||
extraction of dependencies (default is False). (default False)
|
||||
- repo_path (str): The file path to the repository to process.
|
||||
- detailed_extraction (bool): Whether to perform a detailed extraction of code parts.
|
||||
- supported_languages (list | None): Subset of languages to include; if None, use defaults.
|
||||
"""
|
||||
|
||||
if isinstance(repo_path, list) and len(repo_path) == 1:
|
||||
|
|
@ -109,7 +140,25 @@ async def get_repo_file_dependencies(
|
|||
if not os.path.exists(repo_path):
|
||||
raise FileNotFoundError(f"Repository path {repo_path} does not exist.")
|
||||
|
||||
source_code_files = await get_source_code_files(repo_path)
|
||||
# Build language config from supported_languages
|
||||
default_language_config = {
|
||||
"python": [".py"],
|
||||
"javascript": [".js", ".jsx"],
|
||||
"typescript": [".ts", ".tsx"],
|
||||
"java": [".java"],
|
||||
"csharp": [".cs"],
|
||||
"go": [".go"],
|
||||
"rust": [".rs"],
|
||||
"cpp": [".cpp", ".c", ".h", ".hpp"],
|
||||
}
|
||||
if supported_languages is not None:
|
||||
language_config = {
|
||||
k: v for k, v in default_language_config.items() if k in supported_languages
|
||||
}
|
||||
else:
|
||||
language_config = default_language_config
|
||||
|
||||
source_code_files = await get_source_code_files(repo_path, language_config=language_config)
|
||||
|
||||
repo = Repository(
|
||||
id=uuid5(NAMESPACE_OID, repo_path),
|
||||
|
|
@ -128,19 +177,42 @@ async def get_repo_file_dependencies(
|
|||
for chunk_number in range(number_of_chunks)
|
||||
]
|
||||
|
||||
# Codegraph dependencies are not installed by default, so we import where we use them.
|
||||
# Import dependency extractors for each language (Python for now, extend later)
|
||||
from cognee.tasks.repo_processor.get_local_dependencies import get_local_script_dependencies
|
||||
import aiofiles
|
||||
# TODO: Add other language extractors here
|
||||
|
||||
for start_range, end_range in chunk_ranges:
|
||||
# with ProcessPoolExecutor(max_workers=12) as executor:
|
||||
tasks = [
|
||||
get_local_script_dependencies(repo_path, file_path, detailed_extraction)
|
||||
for file_path in source_code_files[start_range : end_range + 1]
|
||||
]
|
||||
tasks = []
|
||||
for file_path, lang in source_code_files[start_range : end_range + 1]:
|
||||
# For now, only Python is supported; extend with other languages
|
||||
if lang == "python":
|
||||
tasks.append(
|
||||
get_local_script_dependencies(repo_path, file_path, detailed_extraction)
|
||||
)
|
||||
else:
|
||||
# Placeholder: create a minimal CodeFile for other languages
|
||||
async def make_codefile_stub(file_path=file_path, lang=lang):
|
||||
async with aiofiles.open(
|
||||
file_path, "r", encoding="utf-8", errors="replace"
|
||||
) as f:
|
||||
source = await f.read()
|
||||
return CodeFile(
|
||||
id=uuid5(NAMESPACE_OID, file_path),
|
||||
name=os.path.relpath(file_path, repo_path),
|
||||
file_path=file_path,
|
||||
language=lang,
|
||||
source_code=source,
|
||||
)
|
||||
|
||||
tasks.append(make_codefile_stub())
|
||||
|
||||
results: list[CodeFile] = await asyncio.gather(*tasks)
|
||||
|
||||
for source_code_file in results:
|
||||
source_code_file.part_of = repo
|
||||
|
||||
if getattr(
|
||||
source_code_file, "language", None
|
||||
) is None and source_code_file.file_path.endswith(".py"):
|
||||
source_code_file.language = "python"
|
||||
yield source_code_file
|
||||
|
|
|
|||
|
|
@ -83,11 +83,16 @@ class TestCliIntegration:
|
|||
|
||||
# Note: This might fail due to dependencies, but we're testing the CLI structure
|
||||
# The important thing is that it doesn't crash with argument parsing errors
|
||||
assert (
|
||||
"error" not in result.stderr.lower()
|
||||
or "failed to add data" in result.stderr.lower()
|
||||
# Allow litellm logging worker cancellation errors as they're expected during process shutdown
|
||||
stderr_lower = result.stderr.lower()
|
||||
has_error = "error" in stderr_lower
|
||||
has_expected_failure = "failed to add data" in stderr_lower
|
||||
has_litellm_cancellation = (
|
||||
"loggingworker cancelled" in stderr_lower or "cancellederror" in stderr_lower
|
||||
)
|
||||
|
||||
assert not has_error or has_expected_failure or has_litellm_cancellation
|
||||
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
|
|
|||
|
|
@ -2,6 +2,7 @@ import os
|
|||
import sys
|
||||
import uuid
|
||||
import pytest
|
||||
import pathlib
|
||||
from unittest.mock import patch
|
||||
|
||||
from cognee.modules.chunking.TextChunker import TextChunker
|
||||
|
|
@ -24,8 +25,7 @@ GROUND_TRUTH = [
|
|||
@pytest.mark.asyncio
|
||||
async def test_PdfDocument(mock_engine):
|
||||
test_file_path = os.path.join(
|
||||
os.sep,
|
||||
*(os.path.dirname(__file__).split(os.sep)[:-2]),
|
||||
pathlib.Path(__file__).parent.parent.parent,
|
||||
"test_data",
|
||||
"artificial-intelligence.pdf",
|
||||
)
|
||||
|
|
|
|||
|
|
@ -2,6 +2,7 @@ import os
|
|||
import sys
|
||||
import uuid
|
||||
import pytest
|
||||
import pathlib
|
||||
from unittest.mock import patch
|
||||
|
||||
from cognee.modules.chunking.TextChunker import TextChunker
|
||||
|
|
@ -34,10 +35,7 @@ GROUND_TRUTH = {
|
|||
@pytest.mark.asyncio
|
||||
async def test_TextDocument(mock_engine, input_file, chunk_size):
|
||||
test_file_path = os.path.join(
|
||||
os.sep,
|
||||
*(os.path.dirname(__file__).split(os.sep)[:-2]),
|
||||
"test_data",
|
||||
input_file,
|
||||
pathlib.Path(__file__).parent.parent.parent, "test_data", input_file
|
||||
)
|
||||
document = TextDocument(
|
||||
id=uuid.uuid4(),
|
||||
|
|
|
|||
|
|
@ -2,6 +2,7 @@ import os
|
|||
import sys
|
||||
import uuid
|
||||
import pytest
|
||||
import pathlib
|
||||
from unittest.mock import patch
|
||||
|
||||
from cognee.modules.chunking.TextChunker import TextChunker
|
||||
|
|
@ -18,29 +19,25 @@ chunk_by_sentence_module = sys.modules.get("cognee.tasks.chunks.chunk_by_sentenc
|
|||
async def test_UnstructuredDocument(mock_engine):
|
||||
# Define file paths of test data
|
||||
pptx_file_path = os.path.join(
|
||||
os.sep,
|
||||
*(os.path.dirname(__file__).split(os.sep)[:-2]),
|
||||
pathlib.Path(__file__).parent.parent.parent,
|
||||
"test_data",
|
||||
"example.pptx",
|
||||
)
|
||||
|
||||
docx_file_path = os.path.join(
|
||||
os.sep,
|
||||
*(os.path.dirname(__file__).split(os.sep)[:-2]),
|
||||
pathlib.Path(__file__).parent.parent.parent,
|
||||
"test_data",
|
||||
"example.docx",
|
||||
)
|
||||
|
||||
csv_file_path = os.path.join(
|
||||
os.sep,
|
||||
*(os.path.dirname(__file__).split(os.sep)[:-2]),
|
||||
pathlib.Path(__file__).parent.parent.parent,
|
||||
"test_data",
|
||||
"example.csv",
|
||||
)
|
||||
|
||||
xlsx_file_path = os.path.join(
|
||||
os.sep,
|
||||
*(os.path.dirname(__file__).split(os.sep)[:-2]),
|
||||
pathlib.Path(__file__).parent.parent.parent,
|
||||
"test_data",
|
||||
"example.xlsx",
|
||||
)
|
||||
|
|
|
|||
|
|
@ -45,8 +45,6 @@ async def main():
|
|||
Each of these car manufacturer contributes to Germany's reputation as a leader in the global automotive industry, showcasing a blend of innovation, performance, and design excellence.
|
||||
"""
|
||||
|
||||
################### HARD DELETE
|
||||
|
||||
# Add documents and get dataset information
|
||||
add_result = await cognee.add(
|
||||
[
|
||||
|
|
@ -80,41 +78,6 @@ async def main():
|
|||
|
||||
assert len(nodes) == 0 and len(edges) == 0, "Document is not deleted with hard delete."
|
||||
|
||||
################### SOFT DELETE
|
||||
|
||||
# Add documents and get dataset information
|
||||
add_result = await cognee.add(
|
||||
[
|
||||
pdf_document,
|
||||
txt_document,
|
||||
text_document_as_literal,
|
||||
unstructured_document,
|
||||
audio_document,
|
||||
image_document,
|
||||
]
|
||||
)
|
||||
dataset_id = add_result.dataset_id
|
||||
|
||||
await cognee.cognify()
|
||||
|
||||
from cognee.infrastructure.databases.graph import get_graph_engine
|
||||
|
||||
graph_engine = await get_graph_engine()
|
||||
nodes, edges = await graph_engine.get_graph_data()
|
||||
assert len(nodes) > 10 and len(edges) > 10, "Graph database is not loaded."
|
||||
|
||||
# Get the data IDs from the dataset
|
||||
dataset_data = await get_dataset_data(dataset_id)
|
||||
assert len(dataset_data) > 0, "Dataset should contain data"
|
||||
|
||||
# Delete each document using its ID
|
||||
for data_item in dataset_data:
|
||||
await cognee.delete(data_item.id, dataset_id, mode="soft")
|
||||
|
||||
nodes, edges = await graph_engine.get_graph_data()
|
||||
|
||||
assert len(nodes) == 0 and len(edges) == 0, "Document is not deleted with soft delete."
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import asyncio
|
||||
85
cognee/tests/test_delete_soft.py
Normal file
85
cognee/tests/test_delete_soft.py
Normal file
|
|
@ -0,0 +1,85 @@
|
|||
import os
|
||||
import shutil
|
||||
import cognee
|
||||
import pathlib
|
||||
from cognee.shared.logging_utils import get_logger
|
||||
from cognee.modules.data.methods import get_dataset_data
|
||||
|
||||
logger = get_logger()
|
||||
|
||||
|
||||
async def main():
|
||||
await cognee.prune.prune_data()
|
||||
await cognee.prune.prune_system(metadata=True)
|
||||
|
||||
pdf_document = os.path.join(
|
||||
pathlib.Path(__file__).parent, "test_data/artificial-intelligence.pdf"
|
||||
)
|
||||
|
||||
txt_document = os.path.join(
|
||||
pathlib.Path(__file__).parent, "test_data/Natural_language_processing_copy.txt"
|
||||
)
|
||||
|
||||
audio_document = os.path.join(pathlib.Path(__file__).parent, "test_data/text_to_speech.mp3")
|
||||
|
||||
image_document = os.path.join(pathlib.Path(__file__).parent, "test_data/example.png")
|
||||
|
||||
unstructured_document = os.path.join(pathlib.Path(__file__).parent, "test_data/example.pptx")
|
||||
|
||||
text_document_as_literal = """
|
||||
1. Audi
|
||||
Audi is known for its modern designs and advanced technology. Founded in the early 1900s, the brand has earned a reputation for precision engineering and innovation. With features like the Quattro all-wheel-drive system, Audi offers a range of vehicles from stylish sedans to high-performance sports cars.
|
||||
|
||||
2. BMW
|
||||
BMW, short for Bayerische Motoren Werke, is celebrated for its focus on performance and driving pleasure. The company's vehicles are designed to provide a dynamic and engaging driving experience, and their slogan, "The Ultimate Driving Machine," reflects that commitment. BMW produces a variety of cars that combine luxury with sporty performance.
|
||||
|
||||
3. Mercedes-Benz
|
||||
Mercedes-Benz is synonymous with luxury and quality. With a history dating back to the early 20th century, the brand is known for its elegant designs, innovative safety features, and high-quality engineering. Mercedes-Benz manufactures not only luxury sedans but also SUVs, sports cars, and commercial vehicles, catering to a wide range of needs.
|
||||
|
||||
4. Porsche
|
||||
Porsche is a name that stands for high-performance sports cars. Founded in 1931, the brand has become famous for models like the iconic Porsche 911. Porsche cars are celebrated for their speed, precision, and distinctive design, appealing to car enthusiasts who value both performance and style.
|
||||
|
||||
5. Volkswagen
|
||||
Volkswagen, which means "people's car" in German, was established with the idea of making affordable and reliable vehicles accessible to everyone. Over the years, Volkswagen has produced several iconic models, such as the Beetle and the Golf. Today, it remains one of the largest car manufacturers in the world, offering a wide range of vehicles that balance practicality with quality.
|
||||
|
||||
Each of these car manufacturer contributes to Germany's reputation as a leader in the global automotive industry, showcasing a blend of innovation, performance, and design excellence.
|
||||
"""
|
||||
|
||||
# Add documents and get dataset information
|
||||
add_result = await cognee.add(
|
||||
[
|
||||
pdf_document,
|
||||
txt_document,
|
||||
text_document_as_literal,
|
||||
unstructured_document,
|
||||
audio_document,
|
||||
image_document,
|
||||
]
|
||||
)
|
||||
dataset_id = add_result.dataset_id
|
||||
|
||||
await cognee.cognify()
|
||||
|
||||
from cognee.infrastructure.databases.graph import get_graph_engine
|
||||
|
||||
graph_engine = await get_graph_engine()
|
||||
nodes, edges = await graph_engine.get_graph_data()
|
||||
assert len(nodes) > 10 and len(edges) > 10, "Graph database is not loaded."
|
||||
|
||||
# Get the data IDs from the dataset
|
||||
dataset_data = await get_dataset_data(dataset_id)
|
||||
assert len(dataset_data) > 0, "Dataset should contain data"
|
||||
|
||||
# Delete each document using its ID
|
||||
for data_item in dataset_data:
|
||||
await cognee.delete(data_item.id, dataset_id, mode="soft")
|
||||
|
||||
nodes, edges = await graph_engine.get_graph_data()
|
||||
|
||||
assert len(nodes) == 0 and len(edges) == 0, "Document is not deleted with soft delete."
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import asyncio
|
||||
|
||||
asyncio.run(main())
|
||||
|
|
@ -229,7 +229,7 @@ class TestCognifyCommand:
|
|||
|
||||
mock_asyncio_run.assert_called_once()
|
||||
assert asyncio.iscoroutine(mock_asyncio_run.call_args[0][0])
|
||||
from cognee.modules.chunking import TextChunker
|
||||
from cognee.modules.chunking.TextChunker import TextChunker
|
||||
|
||||
mock_cognee.cognify.assert_awaited_once_with(
|
||||
datasets=None,
|
||||
|
|
|
|||
|
|
@ -253,7 +253,7 @@ class TestCognifyCommandEdgeCases:
|
|||
|
||||
mock_asyncio_run.assert_called_once()
|
||||
assert asyncio.iscoroutine(mock_asyncio_run.call_args[0][0])
|
||||
from cognee.modules.chunking import TextChunker
|
||||
from cognee.modules.chunking.TextChunker import TextChunker
|
||||
|
||||
mock_cognee.cognify.assert_awaited_once_with(
|
||||
datasets=None,
|
||||
|
|
@ -286,7 +286,7 @@ class TestCognifyCommandEdgeCases:
|
|||
|
||||
mock_asyncio_run.assert_called_once()
|
||||
assert asyncio.iscoroutine(mock_asyncio_run.call_args[0][0])
|
||||
from cognee.modules.chunking import TextChunker
|
||||
from cognee.modules.chunking.TextChunker import TextChunker
|
||||
|
||||
mock_cognee.cognify.assert_awaited_once_with(
|
||||
datasets=None,
|
||||
|
|
@ -306,9 +306,17 @@ class TestCognifyCommandEdgeCases:
|
|||
def mock_import_func(name, fromlist=None, *args, **kwargs):
|
||||
if name == "cognee":
|
||||
return mock_cognee
|
||||
elif name == "cognee.modules.chunking" and fromlist and "LangchainChunker" in fromlist:
|
||||
elif (
|
||||
name == "cognee.modules.chunking.LangchainChunker"
|
||||
and fromlist
|
||||
and "LangchainChunker" in fromlist
|
||||
):
|
||||
raise ImportError("LangchainChunker not available")
|
||||
elif name == "cognee.modules.chunking":
|
||||
elif (
|
||||
name == "cognee.modules.chunking.TextChunker"
|
||||
and fromlist
|
||||
and "TextChunker" in fromlist
|
||||
):
|
||||
module = MagicMock()
|
||||
module.TextChunker = MagicMock()
|
||||
return module
|
||||
|
|
@ -356,7 +364,7 @@ class TestCognifyCommandEdgeCases:
|
|||
|
||||
mock_asyncio_run.assert_called_once()
|
||||
assert asyncio.iscoroutine(mock_asyncio_run.call_args[0][0])
|
||||
from cognee.modules.chunking import TextChunker
|
||||
from cognee.modules.chunking.TextChunker import TextChunker
|
||||
|
||||
mock_cognee.cognify.assert_awaited_once_with(
|
||||
datasets=None,
|
||||
|
|
|
|||
1257
notebooks/cognee_demo.ipynb
vendored
1257
notebooks/cognee_demo.ipynb
vendored
File diff suppressed because it is too large
Load diff
363
notebooks/cognee_multimedia_demo.ipynb
vendored
363
notebooks/cognee_multimedia_demo.ipynb
vendored
|
|
@ -21,13 +21,15 @@
|
|||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-06-30T11:54:44.613431Z",
|
||||
"start_time": "2025-06-30T11:54:44.606687Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import pathlib\n",
|
||||
|
|
@ -44,9 +46,7 @@
|
|||
" \"../\",\n",
|
||||
" \"examples/data/multimedia/example.png\",\n",
|
||||
")"
|
||||
],
|
||||
"outputs": [],
|
||||
"execution_count": 1
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
|
|
@ -57,12 +57,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-06-30T11:54:46.739157Z",
|
||||
"start_time": "2025-06-30T11:54:46.734808Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
|
|
@ -93,9 +95,7 @@
|
|||
"# os.environ[\"DB_PORT\"]=\"5432\"\n",
|
||||
"# os.environ[\"DB_USERNAME\"]=\"cognee\"\n",
|
||||
"# os.environ[\"DB_PASSWORD\"]=\"cognee\""
|
||||
],
|
||||
"outputs": [],
|
||||
"execution_count": 2
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
|
|
@ -106,12 +106,213 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-06-30T11:55:01.959946Z",
|
||||
"start_time": "2025-06-30T11:54:50.569659Z"
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:41.256195\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mDeleted old log file: /Users/daulet/Desktop/dev/cognee-claude/logs/2025-08-27_14-00-27.log\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
|
||||
"/Users/daulet/Desktop/dev/cognee-claude/.venv/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
|
||||
" from .autonotebook import tqdm as notebook_tqdm\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:42.133224\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mLogging initialized \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m \u001b[36mcognee_version\u001b[0m=\u001b[35m0.2.4-local\u001b[0m \u001b[36mdatabase_path\u001b[0m=\u001b[35m/Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m \u001b[36mgraph_database_name\u001b[0m=\u001b[35m\u001b[0m \u001b[36mos_info\u001b[0m=\u001b[35m'Darwin 24.5.0 (Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:43 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8132)'\u001b[0m \u001b[36mpython_version\u001b[0m=\u001b[35m3.12.7\u001b[0m \u001b[36mrelational_config\u001b[0m=\u001b[35mcognee_db\u001b[0m \u001b[36mstructlog_version\u001b[0m=\u001b[35m25.4.0\u001b[0m \u001b[36mvector_config\u001b[0m=\u001b[35mlancedb\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:42.133667\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mDatabase storage: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:43.785214\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mDeleted Kuzu database files at /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases/cognee_graph_kuzu\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:44.215920\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mDatabase deleted successfully.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1mLangfuse client is disabled since no public_key was provided as a parameter or environment variable 'LANGFUSE_PUBLIC_KEY'. See our docs: https://langfuse.com/docs/sdk/python/low-level-sdk#initialize-client\u001b[0m\n",
|
||||
"\u001b[92m15:33:44 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
|
||||
"LiteLLM completion() model= gpt-5-mini; provider = openai\n",
|
||||
"\n",
|
||||
"\u001b[1m\n",
|
||||
"LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"User 37ea34fa-cae7-4bea-8cb3-1ba234688771 has registered.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\u001b[1mEmbeddingRateLimiter initialized: enabled=False, requests_limit=60, interval_seconds=60\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:50.440270\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run started: `017311b3-90e5-53ce-9974-00c4d9551248`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:50.690756\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:50.996600\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:51.287352\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mRegistered loader: pypdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:51.287759\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mRegistered loader: text_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:51.288078\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mRegistered loader: image_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:51.288341\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mRegistered loader: audio_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:51.288576\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mRegistered loader: unstructured_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
|
||||
"\u001b[92m15:33:52 - LiteLLM:INFO\u001b[0m: utils.py:1274 - Wrapper: Completed Call, calling success_handler\n",
|
||||
"\n",
|
||||
"\u001b[1mWrapper: Completed Call, calling success_handler\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:52.455447\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:52.599686\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:52.806593\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run completed: `017311b3-90e5-53ce-9974-00c4d9551248`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:53.075106\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run started: `017311b3-90e5-53ce-9974-00c4d9551248`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:53.209912\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:53.355890\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\u001b[92m15:33:53 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
|
||||
"LiteLLM completion() model= gpt-5-mini; provider = openai\n",
|
||||
"\n",
|
||||
"\u001b[1m\n",
|
||||
"LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
|
||||
"\u001b[92m15:33:57 - LiteLLM:INFO\u001b[0m: utils.py:1274 - Wrapper: Completed Call, calling success_handler\n",
|
||||
"\n",
|
||||
"\u001b[1mWrapper: Completed Call, calling success_handler\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:57.407561\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:57.560808\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:57.713507\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run completed: `017311b3-90e5-53ce-9974-00c4d9551248`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:57.897060\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:57.938027\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run started: `9bd0d908-8e9e-5780-b4c2-09fc8d471f1b`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:58.093101\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:58.255165\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:58.428623\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:33:58.588682\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\u001b[92m15:33:58 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
|
||||
"LiteLLM completion() model= gpt-5-mini; provider = openai\n",
|
||||
"\n",
|
||||
"\u001b[1m\n",
|
||||
"LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:19.706892\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:19.707703\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'programmer' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:19.708083\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'object' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:19.708440\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'light bulb' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:19.708802\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:19.709129\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'hardware problem' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:19.709475\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'how many programmers does it take to change a light bulb? none, thats a hardware problem.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:24.553989\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\u001b[92m15:34:24 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
|
||||
"LiteLLM completion() model= gpt-5-mini; provider = openai\n",
|
||||
"\n",
|
||||
"\u001b[1m\n",
|
||||
"LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:32.883579\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:35.680233\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:35.825933\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:35.975352\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:36.126720\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:36.275404\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:36.424984\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:36.576258\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run completed: `9bd0d908-8e9e-5780-b4c2-09fc8d471f1b`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:36.754472\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run started: `9bd0d908-8e9e-5780-b4c2-09fc8d471f1b`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:36.912219\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:37.053036\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:37.220157\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:34:37.388094\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\u001b[92m15:34:37 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
|
||||
"LiteLLM completion() model= gpt-5-mini; provider = openai\n",
|
||||
"\n",
|
||||
"\u001b[1m\n",
|
||||
"LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:00.010321\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:00.012394\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'programmers' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:00.012794\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'object' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:00.013111\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'light bulb' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:00.013378\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:00.013598\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'hardware problem' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:00.013914\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'joke' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:00.014215\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mNo close match found for 'programmer joke' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:02.040520\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\u001b[92m15:35:02 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
|
||||
"LiteLLM completion() model= gpt-5-mini; provider = openai\n",
|
||||
"\n",
|
||||
"\u001b[1m\n",
|
||||
"LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:11.589828\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:14.446614\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:14.622281\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:14.820192\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:15.004173\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:15.518803\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:15.756519\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:35:15.978364\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mPipeline run completed: `9bd0d908-8e9e-5780-b4c2-09fc8d471f1b`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{UUID('a08926db-6319-5cd9-adc9-2cf9dfbc75e0'): PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('69b78d3d-4d27-5d9f-918f-57e77b3cb10a'), dataset_id=UUID('a08926db-6319-5cd9-adc9-2cf9dfbc75e0'), dataset_name='main_dataset', payload=None, data_ingestion_info=[{'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('69b78d3d-4d27-5d9f-918f-57e77b3cb10a'), dataset_id=UUID('a08926db-6319-5cd9-adc9-2cf9dfbc75e0'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('17b5c469-a8ce-5347-bea5-ab3dba767d13')}, {'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('69b78d3d-4d27-5d9f-918f-57e77b3cb10a'), dataset_id=UUID('a08926db-6319-5cd9-adc9-2cf9dfbc75e0'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('5b1e3c7e-d837-5704-a3b3-53abdda3a84f')}])}"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
},
|
||||
],
|
||||
"source": [
|
||||
"import cognee\n",
|
||||
"\n",
|
||||
|
|
@ -124,75 +325,7 @@
|
|||
"\n",
|
||||
"# Create knowledge graph with cognee\n",
|
||||
"await cognee.cognify()"
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/Users/vasilije/cognee/.venv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
|
||||
" from .autonotebook import tqdm as notebook_tqdm\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"ename": "OperationalError",
|
||||
"evalue": "(sqlite3.OperationalError) database is locked\n[SQL: \nCREATE TABLE data (\n\tid UUID NOT NULL, \n\tname VARCHAR, \n\textension VARCHAR, \n\tmime_type VARCHAR, \n\traw_data_location VARCHAR, \n\towner_id UUID, \n\tcontent_hash VARCHAR, \n\texternal_metadata JSON, \n\tnode_set JSON, \n\ttoken_count INTEGER, \n\tcreated_at DATETIME, \n\tupdated_at DATETIME, \n\tPRIMARY KEY (id)\n)\n\n]\n(Background on this error at: https://sqlalche.me/e/20/e3q8)",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001B[31m---------------------------------------------------------------------------\u001B[39m",
|
||||
"\u001B[31mOperationalError\u001B[39m Traceback (most recent call last)",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/engine/base.py:1964\u001B[39m, in \u001B[36mConnection._exec_single_context\u001B[39m\u001B[34m(self, dialect, context, statement, parameters)\u001B[39m\n\u001B[32m 1963\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m evt_handled:\n\u001B[32m-> \u001B[39m\u001B[32m1964\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[43m.\u001B[49m\u001B[43mdialect\u001B[49m\u001B[43m.\u001B[49m\u001B[43mdo_execute\u001B[49m\u001B[43m(\u001B[49m\n\u001B[32m 1965\u001B[39m \u001B[43m \u001B[49m\u001B[43mcursor\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mstr_statement\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43meffective_parameters\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcontext\u001B[49m\n\u001B[32m 1966\u001B[39m \u001B[43m \u001B[49m\u001B[43m)\u001B[49m\n\u001B[32m 1968\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m._has_events \u001B[38;5;129;01mor\u001B[39;00m \u001B[38;5;28mself\u001B[39m.engine._has_events:\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/engine/default.py:942\u001B[39m, in \u001B[36mDefaultDialect.do_execute\u001B[39m\u001B[34m(self, cursor, statement, parameters, context)\u001B[39m\n\u001B[32m 941\u001B[39m \u001B[38;5;28;01mdef\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[34mdo_execute\u001B[39m(\u001B[38;5;28mself\u001B[39m, cursor, statement, parameters, context=\u001B[38;5;28;01mNone\u001B[39;00m):\n\u001B[32m--> \u001B[39m\u001B[32m942\u001B[39m \u001B[43mcursor\u001B[49m\u001B[43m.\u001B[49m\u001B[43mexecute\u001B[49m\u001B[43m(\u001B[49m\u001B[43mstatement\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mparameters\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/dialects/sqlite/aiosqlite.py:172\u001B[39m, in \u001B[36mAsyncAdapt_aiosqlite_cursor.execute\u001B[39m\u001B[34m(self, operation, parameters)\u001B[39m\n\u001B[32m 171\u001B[39m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m error:\n\u001B[32m--> \u001B[39m\u001B[32m172\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[43m.\u001B[49m\u001B[43m_adapt_connection\u001B[49m\u001B[43m.\u001B[49m\u001B[43m_handle_exception\u001B[49m\u001B[43m(\u001B[49m\u001B[43merror\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/dialects/sqlite/aiosqlite.py:323\u001B[39m, in \u001B[36mAsyncAdapt_aiosqlite_connection._handle_exception\u001B[39m\u001B[34m(self, error)\u001B[39m\n\u001B[32m 322\u001B[39m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[32m--> \u001B[39m\u001B[32m323\u001B[39m \u001B[38;5;28;01mraise\u001B[39;00m error\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/dialects/sqlite/aiosqlite.py:154\u001B[39m, in \u001B[36mAsyncAdapt_aiosqlite_cursor.execute\u001B[39m\u001B[34m(self, operation, parameters)\u001B[39m\n\u001B[32m 153\u001B[39m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[32m--> \u001B[39m\u001B[32m154\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[43m.\u001B[49m\u001B[43mawait_\u001B[49m\u001B[43m(\u001B[49m\u001B[43m_cursor\u001B[49m\u001B[43m.\u001B[49m\u001B[43mexecute\u001B[49m\u001B[43m(\u001B[49m\u001B[43moperation\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mparameters\u001B[49m\u001B[43m)\u001B[49m\u001B[43m)\u001B[49m\n\u001B[32m 156\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m _cursor.description:\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/util/_concurrency_py3k.py:132\u001B[39m, in \u001B[36mawait_only\u001B[39m\u001B[34m(awaitable)\u001B[39m\n\u001B[32m 128\u001B[39m \u001B[38;5;66;03m# returns the control to the driver greenlet passing it\u001B[39;00m\n\u001B[32m 129\u001B[39m \u001B[38;5;66;03m# a coroutine to run. Once the awaitable is done, the driver greenlet\u001B[39;00m\n\u001B[32m 130\u001B[39m \u001B[38;5;66;03m# switches back to this greenlet with the result of awaitable that is\u001B[39;00m\n\u001B[32m 131\u001B[39m \u001B[38;5;66;03m# then returned to the caller (or raised as error)\u001B[39;00m\n\u001B[32m--> \u001B[39m\u001B[32m132\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mcurrent\u001B[49m\u001B[43m.\u001B[49m\u001B[43mparent\u001B[49m\u001B[43m.\u001B[49m\u001B[43mswitch\u001B[49m\u001B[43m(\u001B[49m\u001B[43mawaitable\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/util/_concurrency_py3k.py:196\u001B[39m, in \u001B[36mgreenlet_spawn\u001B[39m\u001B[34m(fn, _require_await, *args, **kwargs)\u001B[39m\n\u001B[32m 193\u001B[39m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[32m 194\u001B[39m \u001B[38;5;66;03m# wait for a coroutine from await_only and then return its\u001B[39;00m\n\u001B[32m 195\u001B[39m \u001B[38;5;66;03m# result back to it.\u001B[39;00m\n\u001B[32m--> \u001B[39m\u001B[32m196\u001B[39m value = \u001B[38;5;28;01mawait\u001B[39;00m result\n\u001B[32m 197\u001B[39m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mBaseException\u001B[39;00m:\n\u001B[32m 198\u001B[39m \u001B[38;5;66;03m# this allows an exception to be raised within\u001B[39;00m\n\u001B[32m 199\u001B[39m \u001B[38;5;66;03m# the moderated greenlet so that it can continue\u001B[39;00m\n\u001B[32m 200\u001B[39m \u001B[38;5;66;03m# its expected flow.\u001B[39;00m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/aiosqlite/cursor.py:48\u001B[39m, in \u001B[36mCursor.execute\u001B[39m\u001B[34m(self, sql, parameters)\u001B[39m\n\u001B[32m 47\u001B[39m parameters = []\n\u001B[32m---> \u001B[39m\u001B[32m48\u001B[39m \u001B[38;5;28;01mawait\u001B[39;00m \u001B[38;5;28mself\u001B[39m._execute(\u001B[38;5;28mself\u001B[39m._cursor.execute, sql, parameters)\n\u001B[32m 49\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/aiosqlite/cursor.py:40\u001B[39m, in \u001B[36mCursor._execute\u001B[39m\u001B[34m(self, fn, *args, **kwargs)\u001B[39m\n\u001B[32m 39\u001B[39m \u001B[38;5;250m\u001B[39m\u001B[33;03m\"\"\"Execute the given function on the shared connection's thread.\"\"\"\u001B[39;00m\n\u001B[32m---> \u001B[39m\u001B[32m40\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;01mawait\u001B[39;00m \u001B[38;5;28mself\u001B[39m._conn._execute(fn, *args, **kwargs)\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/aiosqlite/core.py:132\u001B[39m, in \u001B[36mConnection._execute\u001B[39m\u001B[34m(self, fn, *args, **kwargs)\u001B[39m\n\u001B[32m 130\u001B[39m \u001B[38;5;28mself\u001B[39m._tx.put_nowait((future, function))\n\u001B[32m--> \u001B[39m\u001B[32m132\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;01mawait\u001B[39;00m future\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/aiosqlite/core.py:115\u001B[39m, in \u001B[36mConnection.run\u001B[39m\u001B[34m(self)\u001B[39m\n\u001B[32m 114\u001B[39m LOG.debug(\u001B[33m\"\u001B[39m\u001B[33mexecuting \u001B[39m\u001B[38;5;132;01m%s\u001B[39;00m\u001B[33m\"\u001B[39m, function)\n\u001B[32m--> \u001B[39m\u001B[32m115\u001B[39m result = \u001B[43mfunction\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[32m 116\u001B[39m LOG.debug(\u001B[33m\"\u001B[39m\u001B[33moperation \u001B[39m\u001B[38;5;132;01m%s\u001B[39;00m\u001B[33m completed\u001B[39m\u001B[33m\"\u001B[39m, function)\n",
|
||||
"\u001B[31mOperationalError\u001B[39m: database is locked",
|
||||
"\nThe above exception was the direct cause of the following exception:\n",
|
||||
"\u001B[31mOperationalError\u001B[39m Traceback (most recent call last)",
|
||||
"\u001B[36mCell\u001B[39m\u001B[36m \u001B[39m\u001B[32mIn[3]\u001B[39m\u001B[32m, line 8\u001B[39m\n\u001B[32m 5\u001B[39m \u001B[38;5;28;01mawait\u001B[39;00m cognee.prune.prune_system(metadata=\u001B[38;5;28;01mTrue\u001B[39;00m)\n\u001B[32m 7\u001B[39m \u001B[38;5;66;03m# Add multimedia files and make them available for cognify\u001B[39;00m\n\u001B[32m----> \u001B[39m\u001B[32m8\u001B[39m \u001B[38;5;28;01mawait\u001B[39;00m cognee.add([mp3_file_path, png_file_path])\n\u001B[32m 10\u001B[39m \u001B[38;5;66;03m# Create knowledge graph with cognee\u001B[39;00m\n\u001B[32m 11\u001B[39m \u001B[38;5;28;01mawait\u001B[39;00m cognee.cognify()\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/Projects/release_test/cognee/cognee/api/v1/add/add.py:26\u001B[39m, in \u001B[36madd\u001B[39m\u001B[34m(data, dataset_name, user, node_set, vector_db_config, graph_db_config, dataset_id)\u001B[39m\n\u001B[32m 19\u001B[39m tasks = [\n\u001B[32m 20\u001B[39m Task(resolve_data_directories),\n\u001B[32m 21\u001B[39m Task(ingest_data, dataset_name, user, node_set, dataset_id),\n\u001B[32m 22\u001B[39m ]\n\u001B[32m 24\u001B[39m pipeline_run_info = \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[32m---> \u001B[39m\u001B[32m26\u001B[39m \u001B[38;5;28;01masync\u001B[39;00m \u001B[38;5;28;01mfor\u001B[39;00m run_info \u001B[38;5;129;01min\u001B[39;00m cognee_pipeline(\n\u001B[32m 27\u001B[39m tasks=tasks,\n\u001B[32m 28\u001B[39m datasets=dataset_id \u001B[38;5;28;01mif\u001B[39;00m dataset_id \u001B[38;5;28;01melse\u001B[39;00m dataset_name,\n\u001B[32m 29\u001B[39m data=data,\n\u001B[32m 30\u001B[39m user=user,\n\u001B[32m 31\u001B[39m pipeline_name=\u001B[33m\"\u001B[39m\u001B[33madd_pipeline\u001B[39m\u001B[33m\"\u001B[39m,\n\u001B[32m 32\u001B[39m vector_db_config=vector_db_config,\n\u001B[32m 33\u001B[39m graph_db_config=graph_db_config,\n\u001B[32m 34\u001B[39m ):\n\u001B[32m 35\u001B[39m pipeline_run_info = run_info\n\u001B[32m 37\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m pipeline_run_info\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/Projects/release_test/cognee/cognee/modules/pipelines/operations/pipeline.py:63\u001B[39m, in \u001B[36mcognee_pipeline\u001B[39m\u001B[34m(tasks, data, datasets, user, pipeline_name, vector_db_config, graph_db_config)\u001B[39m\n\u001B[32m 60\u001B[39m context_graph_db_config.set(graph_db_config)\n\u001B[32m 62\u001B[39m \u001B[38;5;66;03m# Create tables for databases\u001B[39;00m\n\u001B[32m---> \u001B[39m\u001B[32m63\u001B[39m \u001B[38;5;28;01mawait\u001B[39;00m create_relational_db_and_tables()\n\u001B[32m 64\u001B[39m \u001B[38;5;28;01mawait\u001B[39;00m create_pgvector_db_and_tables()\n\u001B[32m 66\u001B[39m \u001B[38;5;66;03m# Initialize first_run attribute if it doesn't exist\u001B[39;00m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/Projects/release_test/cognee/cognee/infrastructure/databases/relational/create_db_and_tables.py:13\u001B[39m, in \u001B[36mcreate_db_and_tables\u001B[39m\u001B[34m()\u001B[39m\n\u001B[32m 5\u001B[39m \u001B[38;5;250m\u001B[39m\u001B[33;03m\"\"\"\u001B[39;00m\n\u001B[32m 6\u001B[39m \u001B[33;03mCreate a database and its tables.\u001B[39;00m\n\u001B[32m 7\u001B[39m \n\u001B[32m 8\u001B[39m \u001B[33;03mThis asynchronous function retrieves the relational engine and calls its method to\u001B[39;00m\n\u001B[32m 9\u001B[39m \u001B[33;03mcreate a database.\u001B[39;00m\n\u001B[32m 10\u001B[39m \u001B[33;03m\"\"\"\u001B[39;00m\n\u001B[32m 11\u001B[39m relational_engine = get_relational_engine()\n\u001B[32m---> \u001B[39m\u001B[32m13\u001B[39m \u001B[38;5;28;01mawait\u001B[39;00m relational_engine.create_database()\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/.pyenv/versions/3.11.0/lib/python3.11/contextlib.py:222\u001B[39m, in \u001B[36m_AsyncGeneratorContextManager.__aexit__\u001B[39m\u001B[34m(self, typ, value, traceback)\u001B[39m\n\u001B[32m 220\u001B[39m value = typ()\n\u001B[32m 221\u001B[39m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[32m--> \u001B[39m\u001B[32m222\u001B[39m \u001B[38;5;28;01mawait\u001B[39;00m \u001B[38;5;28mself\u001B[39m.gen.athrow(typ, value, traceback)\n\u001B[32m 223\u001B[39m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mStopAsyncIteration\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m exc:\n\u001B[32m 224\u001B[39m \u001B[38;5;66;03m# Suppress StopIteration *unless* it's the same exception that\u001B[39;00m\n\u001B[32m 225\u001B[39m \u001B[38;5;66;03m# was passed to throw(). This prevents a StopIteration\u001B[39;00m\n\u001B[32m 226\u001B[39m \u001B[38;5;66;03m# raised inside the \"with\" statement from being suppressed.\u001B[39;00m\n\u001B[32m 227\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m exc \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m value\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/ext/asyncio/engine.py:1066\u001B[39m, in \u001B[36mAsyncEngine.begin\u001B[39m\u001B[34m(self)\u001B[39m\n\u001B[32m 1064\u001B[39m \u001B[38;5;28;01masync\u001B[39;00m \u001B[38;5;28;01mwith\u001B[39;00m conn:\n\u001B[32m 1065\u001B[39m \u001B[38;5;28;01masync\u001B[39;00m \u001B[38;5;28;01mwith\u001B[39;00m conn.begin():\n\u001B[32m-> \u001B[39m\u001B[32m1066\u001B[39m \u001B[38;5;28;01myield\u001B[39;00m conn\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/Projects/release_test/cognee/cognee/infrastructure/databases/relational/sqlalchemy/SqlAlchemyAdapter.py:445\u001B[39m, in \u001B[36mSQLAlchemyAdapter.create_database\u001B[39m\u001B[34m(self)\u001B[39m\n\u001B[32m 443\u001B[39m \u001B[38;5;28;01masync\u001B[39;00m \u001B[38;5;28;01mwith\u001B[39;00m \u001B[38;5;28mself\u001B[39m.engine.begin() \u001B[38;5;28;01mas\u001B[39;00m connection:\n\u001B[32m 444\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mlen\u001B[39m(Base.metadata.tables.keys()) > \u001B[32m0\u001B[39m:\n\u001B[32m--> \u001B[39m\u001B[32m445\u001B[39m \u001B[38;5;28;01mawait\u001B[39;00m connection.run_sync(Base.metadata.create_all)\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/ext/asyncio/engine.py:887\u001B[39m, in \u001B[36mAsyncConnection.run_sync\u001B[39m\u001B[34m(self, fn, *arg, **kw)\u001B[39m\n\u001B[32m 819\u001B[39m \u001B[38;5;28;01masync\u001B[39;00m \u001B[38;5;28;01mdef\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[34mrun_sync\u001B[39m(\n\u001B[32m 820\u001B[39m \u001B[38;5;28mself\u001B[39m,\n\u001B[32m 821\u001B[39m fn: Callable[Concatenate[Connection, _P], _T],\n\u001B[32m 822\u001B[39m *arg: _P.args,\n\u001B[32m 823\u001B[39m **kw: _P.kwargs,\n\u001B[32m 824\u001B[39m ) -> _T:\n\u001B[32m 825\u001B[39m \u001B[38;5;250m \u001B[39m\u001B[33;03m'''Invoke the given synchronous (i.e. not async) callable,\u001B[39;00m\n\u001B[32m 826\u001B[39m \u001B[33;03m passing a synchronous-style :class:`_engine.Connection` as the first\u001B[39;00m\n\u001B[32m 827\u001B[39m \u001B[33;03m argument.\u001B[39;00m\n\u001B[32m (...)\u001B[39m\u001B[32m 884\u001B[39m \n\u001B[32m 885\u001B[39m \u001B[33;03m '''\u001B[39;00m \u001B[38;5;66;03m# noqa: E501\u001B[39;00m\n\u001B[32m--> \u001B[39m\u001B[32m887\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;01mawait\u001B[39;00m greenlet_spawn(\n\u001B[32m 888\u001B[39m fn, \u001B[38;5;28mself\u001B[39m._proxied, *arg, _require_await=\u001B[38;5;28;01mFalse\u001B[39;00m, **kw\n\u001B[32m 889\u001B[39m )\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/util/_concurrency_py3k.py:201\u001B[39m, in \u001B[36mgreenlet_spawn\u001B[39m\u001B[34m(fn, _require_await, *args, **kwargs)\u001B[39m\n\u001B[32m 196\u001B[39m value = \u001B[38;5;28;01mawait\u001B[39;00m result\n\u001B[32m 197\u001B[39m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mBaseException\u001B[39;00m:\n\u001B[32m 198\u001B[39m \u001B[38;5;66;03m# this allows an exception to be raised within\u001B[39;00m\n\u001B[32m 199\u001B[39m \u001B[38;5;66;03m# the moderated greenlet so that it can continue\u001B[39;00m\n\u001B[32m 200\u001B[39m \u001B[38;5;66;03m# its expected flow.\u001B[39;00m\n\u001B[32m--> \u001B[39m\u001B[32m201\u001B[39m result = \u001B[43mcontext\u001B[49m\u001B[43m.\u001B[49m\u001B[43mthrow\u001B[49m\u001B[43m(\u001B[49m\u001B[43m*\u001B[49m\u001B[43msys\u001B[49m\u001B[43m.\u001B[49m\u001B[43mexc_info\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\u001B[43m)\u001B[49m\n\u001B[32m 202\u001B[39m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[32m 203\u001B[39m result = context.switch(value)\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/sql/schema.py:5907\u001B[39m, in \u001B[36mMetaData.create_all\u001B[39m\u001B[34m(self, bind, tables, checkfirst)\u001B[39m\n\u001B[32m 5883\u001B[39m \u001B[38;5;28;01mdef\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[34mcreate_all\u001B[39m(\n\u001B[32m 5884\u001B[39m \u001B[38;5;28mself\u001B[39m,\n\u001B[32m 5885\u001B[39m bind: _CreateDropBind,\n\u001B[32m 5886\u001B[39m tables: Optional[_typing_Sequence[Table]] = \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[32m 5887\u001B[39m checkfirst: \u001B[38;5;28mbool\u001B[39m = \u001B[38;5;28;01mTrue\u001B[39;00m,\n\u001B[32m 5888\u001B[39m ) -> \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[32m 5889\u001B[39m \u001B[38;5;250m \u001B[39m\u001B[33;03m\"\"\"Create all tables stored in this metadata.\u001B[39;00m\n\u001B[32m 5890\u001B[39m \n\u001B[32m 5891\u001B[39m \u001B[33;03m Conditional by default, will not attempt to recreate tables already\u001B[39;00m\n\u001B[32m (...)\u001B[39m\u001B[32m 5905\u001B[39m \n\u001B[32m 5906\u001B[39m \u001B[33;03m \"\"\"\u001B[39;00m\n\u001B[32m-> \u001B[39m\u001B[32m5907\u001B[39m \u001B[43mbind\u001B[49m\u001B[43m.\u001B[49m\u001B[43m_run_ddl_visitor\u001B[49m\u001B[43m(\u001B[49m\n\u001B[32m 5908\u001B[39m \u001B[43m \u001B[49m\u001B[43mddl\u001B[49m\u001B[43m.\u001B[49m\u001B[43mSchemaGenerator\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcheckfirst\u001B[49m\u001B[43m=\u001B[49m\u001B[43mcheckfirst\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mtables\u001B[49m\u001B[43m=\u001B[49m\u001B[43mtables\u001B[49m\n\u001B[32m 5909\u001B[39m \u001B[43m \u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/engine/base.py:2456\u001B[39m, in \u001B[36mConnection._run_ddl_visitor\u001B[39m\u001B[34m(self, visitorcallable, element, **kwargs)\u001B[39m\n\u001B[32m 2444\u001B[39m \u001B[38;5;28;01mdef\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[34m_run_ddl_visitor\u001B[39m(\n\u001B[32m 2445\u001B[39m \u001B[38;5;28mself\u001B[39m,\n\u001B[32m 2446\u001B[39m visitorcallable: Type[Union[SchemaGenerator, SchemaDropper]],\n\u001B[32m 2447\u001B[39m element: SchemaItem,\n\u001B[32m 2448\u001B[39m **kwargs: Any,\n\u001B[32m 2449\u001B[39m ) -> \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[32m 2450\u001B[39m \u001B[38;5;250m \u001B[39m\u001B[33;03m\"\"\"run a DDL visitor.\u001B[39;00m\n\u001B[32m 2451\u001B[39m \n\u001B[32m 2452\u001B[39m \u001B[33;03m This method is only here so that the MockConnection can change the\u001B[39;00m\n\u001B[32m 2453\u001B[39m \u001B[33;03m options given to the visitor so that \"checkfirst\" is skipped.\u001B[39;00m\n\u001B[32m 2454\u001B[39m \n\u001B[32m 2455\u001B[39m \u001B[33;03m \"\"\"\u001B[39;00m\n\u001B[32m-> \u001B[39m\u001B[32m2456\u001B[39m \u001B[43mvisitorcallable\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[43m.\u001B[49m\u001B[43mdialect\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43m*\u001B[49m\u001B[43m*\u001B[49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\u001B[43m.\u001B[49m\u001B[43mtraverse_single\u001B[49m\u001B[43m(\u001B[49m\u001B[43melement\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/sql/visitors.py:664\u001B[39m, in \u001B[36mExternalTraversal.traverse_single\u001B[39m\u001B[34m(self, obj, **kw)\u001B[39m\n\u001B[32m 662\u001B[39m meth = \u001B[38;5;28mgetattr\u001B[39m(v, \u001B[33m\"\u001B[39m\u001B[33mvisit_\u001B[39m\u001B[38;5;132;01m%s\u001B[39;00m\u001B[33m\"\u001B[39m % obj.__visit_name__, \u001B[38;5;28;01mNone\u001B[39;00m)\n\u001B[32m 663\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m meth:\n\u001B[32m--> \u001B[39m\u001B[32m664\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mmeth\u001B[49m\u001B[43m(\u001B[49m\u001B[43mobj\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43m*\u001B[49m\u001B[43m*\u001B[49m\u001B[43mkw\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/sql/ddl.py:978\u001B[39m, in \u001B[36mSchemaGenerator.visit_metadata\u001B[39m\u001B[34m(self, metadata)\u001B[39m\n\u001B[32m 976\u001B[39m \u001B[38;5;28;01mfor\u001B[39;00m table, fkcs \u001B[38;5;129;01min\u001B[39;00m collection:\n\u001B[32m 977\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m table \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[32m--> \u001B[39m\u001B[32m978\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[43m.\u001B[49m\u001B[43mtraverse_single\u001B[49m\u001B[43m(\u001B[49m\n\u001B[32m 979\u001B[39m \u001B[43m \u001B[49m\u001B[43mtable\u001B[49m\u001B[43m,\u001B[49m\n\u001B[32m 980\u001B[39m \u001B[43m \u001B[49m\u001B[43mcreate_ok\u001B[49m\u001B[43m=\u001B[49m\u001B[38;5;28;43;01mTrue\u001B[39;49;00m\u001B[43m,\u001B[49m\n\u001B[32m 981\u001B[39m \u001B[43m \u001B[49m\u001B[43minclude_foreign_key_constraints\u001B[49m\u001B[43m=\u001B[49m\u001B[43mfkcs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[32m 982\u001B[39m \u001B[43m \u001B[49m\u001B[43m_is_metadata_operation\u001B[49m\u001B[43m=\u001B[49m\u001B[38;5;28;43;01mTrue\u001B[39;49;00m\u001B[43m,\u001B[49m\n\u001B[32m 983\u001B[39m \u001B[43m \u001B[49m\u001B[43m)\u001B[49m\n\u001B[32m 984\u001B[39m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[32m 985\u001B[39m \u001B[38;5;28;01mfor\u001B[39;00m fkc \u001B[38;5;129;01min\u001B[39;00m fkcs:\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/sql/visitors.py:664\u001B[39m, in \u001B[36mExternalTraversal.traverse_single\u001B[39m\u001B[34m(self, obj, **kw)\u001B[39m\n\u001B[32m 662\u001B[39m meth = \u001B[38;5;28mgetattr\u001B[39m(v, \u001B[33m\"\u001B[39m\u001B[33mvisit_\u001B[39m\u001B[38;5;132;01m%s\u001B[39;00m\u001B[33m\"\u001B[39m % obj.__visit_name__, \u001B[38;5;28;01mNone\u001B[39;00m)\n\u001B[32m 663\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m meth:\n\u001B[32m--> \u001B[39m\u001B[32m664\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mmeth\u001B[49m\u001B[43m(\u001B[49m\u001B[43mobj\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43m*\u001B[49m\u001B[43m*\u001B[49m\u001B[43mkw\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/sql/ddl.py:1016\u001B[39m, in \u001B[36mSchemaGenerator.visit_table\u001B[39m\u001B[34m(self, table, create_ok, include_foreign_key_constraints, _is_metadata_operation)\u001B[39m\n\u001B[32m 1007\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28mself\u001B[39m.dialect.supports_alter:\n\u001B[32m 1008\u001B[39m \u001B[38;5;66;03m# e.g., don't omit any foreign key constraints\u001B[39;00m\n\u001B[32m 1009\u001B[39m include_foreign_key_constraints = \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[32m 1011\u001B[39m \u001B[43mCreateTable\u001B[49m\u001B[43m(\u001B[49m\n\u001B[32m 1012\u001B[39m \u001B[43m \u001B[49m\u001B[43mtable\u001B[49m\u001B[43m,\u001B[49m\n\u001B[32m 1013\u001B[39m \u001B[43m \u001B[49m\u001B[43minclude_foreign_key_constraints\u001B[49m\u001B[43m=\u001B[49m\u001B[43m(\u001B[49m\n\u001B[32m 1014\u001B[39m \u001B[43m \u001B[49m\u001B[43minclude_foreign_key_constraints\u001B[49m\n\u001B[32m 1015\u001B[39m \u001B[43m \u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[32m-> \u001B[39m\u001B[32m1016\u001B[39m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\u001B[43m.\u001B[49m\u001B[43m_invoke_with\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[43m.\u001B[49m\u001B[43mconnection\u001B[49m\u001B[43m)\u001B[49m\n\u001B[32m 1018\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mhasattr\u001B[39m(table, \u001B[33m\"\u001B[39m\u001B[33mindexes\u001B[39m\u001B[33m\"\u001B[39m):\n\u001B[32m 1019\u001B[39m \u001B[38;5;28;01mfor\u001B[39;00m index \u001B[38;5;129;01min\u001B[39;00m table.indexes:\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/sql/ddl.py:314\u001B[39m, in \u001B[36mExecutableDDLElement._invoke_with\u001B[39m\u001B[34m(self, bind)\u001B[39m\n\u001B[32m 312\u001B[39m \u001B[38;5;28;01mdef\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[34m_invoke_with\u001B[39m(\u001B[38;5;28mself\u001B[39m, bind):\n\u001B[32m 313\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m._should_execute(\u001B[38;5;28mself\u001B[39m.target, bind):\n\u001B[32m--> \u001B[39m\u001B[32m314\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mbind\u001B[49m\u001B[43m.\u001B[49m\u001B[43mexecute\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/engine/base.py:1416\u001B[39m, in \u001B[36mConnection.execute\u001B[39m\u001B[34m(self, statement, parameters, execution_options)\u001B[39m\n\u001B[32m 1414\u001B[39m \u001B[38;5;28;01mraise\u001B[39;00m exc.ObjectNotExecutableError(statement) \u001B[38;5;28;01mfrom\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[34;01merr\u001B[39;00m\n\u001B[32m 1415\u001B[39m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[32m-> \u001B[39m\u001B[32m1416\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mmeth\u001B[49m\u001B[43m(\u001B[49m\n\u001B[32m 1417\u001B[39m \u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[32m 1418\u001B[39m \u001B[43m \u001B[49m\u001B[43mdistilled_parameters\u001B[49m\u001B[43m,\u001B[49m\n\u001B[32m 1419\u001B[39m \u001B[43m \u001B[49m\u001B[43mexecution_options\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;129;43;01mor\u001B[39;49;00m\u001B[43m \u001B[49m\u001B[43mNO_OPTIONS\u001B[49m\u001B[43m,\u001B[49m\n\u001B[32m 1420\u001B[39m \u001B[43m \u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/sql/ddl.py:180\u001B[39m, in \u001B[36mExecutableDDLElement._execute_on_connection\u001B[39m\u001B[34m(self, connection, distilled_params, execution_options)\u001B[39m\n\u001B[32m 177\u001B[39m \u001B[38;5;28;01mdef\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[34m_execute_on_connection\u001B[39m(\n\u001B[32m 178\u001B[39m \u001B[38;5;28mself\u001B[39m, connection, distilled_params, execution_options\n\u001B[32m 179\u001B[39m ):\n\u001B[32m--> \u001B[39m\u001B[32m180\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mconnection\u001B[49m\u001B[43m.\u001B[49m\u001B[43m_execute_ddl\u001B[49m\u001B[43m(\u001B[49m\n\u001B[32m 181\u001B[39m \u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mdistilled_params\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mexecution_options\u001B[49m\n\u001B[32m 182\u001B[39m \u001B[43m \u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/engine/base.py:1527\u001B[39m, in \u001B[36mConnection._execute_ddl\u001B[39m\u001B[34m(self, ddl, distilled_parameters, execution_options)\u001B[39m\n\u001B[32m 1522\u001B[39m dialect = \u001B[38;5;28mself\u001B[39m.dialect\n\u001B[32m 1524\u001B[39m compiled = ddl.compile(\n\u001B[32m 1525\u001B[39m dialect=dialect, schema_translate_map=schema_translate_map\n\u001B[32m 1526\u001B[39m )\n\u001B[32m-> \u001B[39m\u001B[32m1527\u001B[39m ret = \u001B[38;5;28;43mself\u001B[39;49m\u001B[43m.\u001B[49m\u001B[43m_execute_context\u001B[49m\u001B[43m(\u001B[49m\n\u001B[32m 1528\u001B[39m \u001B[43m \u001B[49m\u001B[43mdialect\u001B[49m\u001B[43m,\u001B[49m\n\u001B[32m 1529\u001B[39m \u001B[43m \u001B[49m\u001B[43mdialect\u001B[49m\u001B[43m.\u001B[49m\u001B[43mexecution_ctx_cls\u001B[49m\u001B[43m.\u001B[49m\u001B[43m_init_ddl\u001B[49m\u001B[43m,\u001B[49m\n\u001B[32m 1530\u001B[39m \u001B[43m \u001B[49m\u001B[43mcompiled\u001B[49m\u001B[43m,\u001B[49m\n\u001B[32m 1531\u001B[39m \u001B[43m \u001B[49m\u001B[38;5;28;43;01mNone\u001B[39;49;00m\u001B[43m,\u001B[49m\n\u001B[32m 1532\u001B[39m \u001B[43m \u001B[49m\u001B[43mexec_opts\u001B[49m\u001B[43m,\u001B[49m\n\u001B[32m 1533\u001B[39m \u001B[43m \u001B[49m\u001B[43mcompiled\u001B[49m\u001B[43m,\u001B[49m\n\u001B[32m 1534\u001B[39m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\n\u001B[32m 1535\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m._has_events \u001B[38;5;129;01mor\u001B[39;00m \u001B[38;5;28mself\u001B[39m.engine._has_events:\n\u001B[32m 1536\u001B[39m \u001B[38;5;28mself\u001B[39m.dispatch.after_execute(\n\u001B[32m 1537\u001B[39m \u001B[38;5;28mself\u001B[39m,\n\u001B[32m 1538\u001B[39m ddl,\n\u001B[32m (...)\u001B[39m\u001B[32m 1542\u001B[39m ret,\n\u001B[32m 1543\u001B[39m )\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/engine/base.py:1843\u001B[39m, in \u001B[36mConnection._execute_context\u001B[39m\u001B[34m(self, dialect, constructor, statement, parameters, execution_options, *args, **kw)\u001B[39m\n\u001B[32m 1841\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m._exec_insertmany_context(dialect, context)\n\u001B[32m 1842\u001B[39m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[32m-> \u001B[39m\u001B[32m1843\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[43m.\u001B[49m\u001B[43m_exec_single_context\u001B[49m\u001B[43m(\u001B[49m\n\u001B[32m 1844\u001B[39m \u001B[43m \u001B[49m\u001B[43mdialect\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcontext\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mstatement\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mparameters\u001B[49m\n\u001B[32m 1845\u001B[39m \u001B[43m \u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/engine/base.py:1983\u001B[39m, in \u001B[36mConnection._exec_single_context\u001B[39m\u001B[34m(self, dialect, context, statement, parameters)\u001B[39m\n\u001B[32m 1980\u001B[39m result = context._setup_result_proxy()\n\u001B[32m 1982\u001B[39m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mBaseException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[32m-> \u001B[39m\u001B[32m1983\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[43m.\u001B[49m\u001B[43m_handle_dbapi_exception\u001B[49m\u001B[43m(\u001B[49m\n\u001B[32m 1984\u001B[39m \u001B[43m \u001B[49m\u001B[43me\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mstr_statement\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43meffective_parameters\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcursor\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcontext\u001B[49m\n\u001B[32m 1985\u001B[39m \u001B[43m \u001B[49m\u001B[43m)\u001B[49m\n\u001B[32m 1987\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m result\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/engine/base.py:2352\u001B[39m, in \u001B[36mConnection._handle_dbapi_exception\u001B[39m\u001B[34m(self, e, statement, parameters, cursor, context, is_sub_exec)\u001B[39m\n\u001B[32m 2350\u001B[39m \u001B[38;5;28;01melif\u001B[39;00m should_wrap:\n\u001B[32m 2351\u001B[39m \u001B[38;5;28;01massert\u001B[39;00m sqlalchemy_exception \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[32m-> \u001B[39m\u001B[32m2352\u001B[39m \u001B[38;5;28;01mraise\u001B[39;00m sqlalchemy_exception.with_traceback(exc_info[\u001B[32m2\u001B[39m]) \u001B[38;5;28;01mfrom\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[34;01me\u001B[39;00m\n\u001B[32m 2353\u001B[39m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[32m 2354\u001B[39m \u001B[38;5;28;01massert\u001B[39;00m exc_info[\u001B[32m1\u001B[39m] \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/engine/base.py:1964\u001B[39m, in \u001B[36mConnection._exec_single_context\u001B[39m\u001B[34m(self, dialect, context, statement, parameters)\u001B[39m\n\u001B[32m 1962\u001B[39m \u001B[38;5;28;01mbreak\u001B[39;00m\n\u001B[32m 1963\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m evt_handled:\n\u001B[32m-> \u001B[39m\u001B[32m1964\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[43m.\u001B[49m\u001B[43mdialect\u001B[49m\u001B[43m.\u001B[49m\u001B[43mdo_execute\u001B[49m\u001B[43m(\u001B[49m\n\u001B[32m 1965\u001B[39m \u001B[43m \u001B[49m\u001B[43mcursor\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mstr_statement\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43meffective_parameters\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcontext\u001B[49m\n\u001B[32m 1966\u001B[39m \u001B[43m \u001B[49m\u001B[43m)\u001B[49m\n\u001B[32m 1968\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m._has_events \u001B[38;5;129;01mor\u001B[39;00m \u001B[38;5;28mself\u001B[39m.engine._has_events:\n\u001B[32m 1969\u001B[39m \u001B[38;5;28mself\u001B[39m.dispatch.after_cursor_execute(\n\u001B[32m 1970\u001B[39m \u001B[38;5;28mself\u001B[39m,\n\u001B[32m 1971\u001B[39m cursor,\n\u001B[32m (...)\u001B[39m\u001B[32m 1975\u001B[39m context.executemany,\n\u001B[32m 1976\u001B[39m )\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/engine/default.py:942\u001B[39m, in \u001B[36mDefaultDialect.do_execute\u001B[39m\u001B[34m(self, cursor, statement, parameters, context)\u001B[39m\n\u001B[32m 941\u001B[39m \u001B[38;5;28;01mdef\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[34mdo_execute\u001B[39m(\u001B[38;5;28mself\u001B[39m, cursor, statement, parameters, context=\u001B[38;5;28;01mNone\u001B[39;00m):\n\u001B[32m--> \u001B[39m\u001B[32m942\u001B[39m \u001B[43mcursor\u001B[49m\u001B[43m.\u001B[49m\u001B[43mexecute\u001B[49m\u001B[43m(\u001B[49m\u001B[43mstatement\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mparameters\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/dialects/sqlite/aiosqlite.py:172\u001B[39m, in \u001B[36mAsyncAdapt_aiosqlite_cursor.execute\u001B[39m\u001B[34m(self, operation, parameters)\u001B[39m\n\u001B[32m 170\u001B[39m \u001B[38;5;28mself\u001B[39m._cursor = _cursor\n\u001B[32m 171\u001B[39m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m error:\n\u001B[32m--> \u001B[39m\u001B[32m172\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[43m.\u001B[49m\u001B[43m_adapt_connection\u001B[49m\u001B[43m.\u001B[49m\u001B[43m_handle_exception\u001B[49m\u001B[43m(\u001B[49m\u001B[43merror\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/dialects/sqlite/aiosqlite.py:323\u001B[39m, in \u001B[36mAsyncAdapt_aiosqlite_connection._handle_exception\u001B[39m\u001B[34m(self, error)\u001B[39m\n\u001B[32m 319\u001B[39m \u001B[38;5;28;01mraise\u001B[39;00m \u001B[38;5;28mself\u001B[39m.dbapi.sqlite.OperationalError(\n\u001B[32m 320\u001B[39m \u001B[33m\"\u001B[39m\u001B[33mno active connection\u001B[39m\u001B[33m\"\u001B[39m\n\u001B[32m 321\u001B[39m ) \u001B[38;5;28;01mfrom\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[34;01merror\u001B[39;00m\n\u001B[32m 322\u001B[39m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[32m--> \u001B[39m\u001B[32m323\u001B[39m \u001B[38;5;28;01mraise\u001B[39;00m error\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/dialects/sqlite/aiosqlite.py:154\u001B[39m, in \u001B[36mAsyncAdapt_aiosqlite_cursor.execute\u001B[39m\u001B[34m(self, operation, parameters)\u001B[39m\n\u001B[32m 152\u001B[39m \u001B[38;5;28mself\u001B[39m.await_(_cursor.execute(operation))\n\u001B[32m 153\u001B[39m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[32m--> \u001B[39m\u001B[32m154\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[43m.\u001B[49m\u001B[43mawait_\u001B[49m\u001B[43m(\u001B[49m\u001B[43m_cursor\u001B[49m\u001B[43m.\u001B[49m\u001B[43mexecute\u001B[49m\u001B[43m(\u001B[49m\u001B[43moperation\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mparameters\u001B[49m\u001B[43m)\u001B[49m\u001B[43m)\u001B[49m\n\u001B[32m 156\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m _cursor.description:\n\u001B[32m 157\u001B[39m \u001B[38;5;28mself\u001B[39m.description = _cursor.description\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/util/_concurrency_py3k.py:132\u001B[39m, in \u001B[36mawait_only\u001B[39m\u001B[34m(awaitable)\u001B[39m\n\u001B[32m 123\u001B[39m \u001B[38;5;28;01mraise\u001B[39;00m exc.MissingGreenlet(\n\u001B[32m 124\u001B[39m \u001B[33m\"\u001B[39m\u001B[33mgreenlet_spawn has not been called; can\u001B[39m\u001B[33m'\u001B[39m\u001B[33mt call await_only() \u001B[39m\u001B[33m\"\u001B[39m\n\u001B[32m 125\u001B[39m \u001B[33m\"\u001B[39m\u001B[33mhere. Was IO attempted in an unexpected place?\u001B[39m\u001B[33m\"\u001B[39m\n\u001B[32m 126\u001B[39m )\n\u001B[32m 128\u001B[39m \u001B[38;5;66;03m# returns the control to the driver greenlet passing it\u001B[39;00m\n\u001B[32m 129\u001B[39m \u001B[38;5;66;03m# a coroutine to run. Once the awaitable is done, the driver greenlet\u001B[39;00m\n\u001B[32m 130\u001B[39m \u001B[38;5;66;03m# switches back to this greenlet with the result of awaitable that is\u001B[39;00m\n\u001B[32m 131\u001B[39m \u001B[38;5;66;03m# then returned to the caller (or raised as error)\u001B[39;00m\n\u001B[32m--> \u001B[39m\u001B[32m132\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mcurrent\u001B[49m\u001B[43m.\u001B[49m\u001B[43mparent\u001B[49m\u001B[43m.\u001B[49m\u001B[43mswitch\u001B[49m\u001B[43m(\u001B[49m\u001B[43mawaitable\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/sqlalchemy/util/_concurrency_py3k.py:196\u001B[39m, in \u001B[36mgreenlet_spawn\u001B[39m\u001B[34m(fn, _require_await, *args, **kwargs)\u001B[39m\n\u001B[32m 192\u001B[39m switch_occurred = \u001B[38;5;28;01mTrue\u001B[39;00m\n\u001B[32m 193\u001B[39m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[32m 194\u001B[39m \u001B[38;5;66;03m# wait for a coroutine from await_only and then return its\u001B[39;00m\n\u001B[32m 195\u001B[39m \u001B[38;5;66;03m# result back to it.\u001B[39;00m\n\u001B[32m--> \u001B[39m\u001B[32m196\u001B[39m value = \u001B[38;5;28;01mawait\u001B[39;00m result\n\u001B[32m 197\u001B[39m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mBaseException\u001B[39;00m:\n\u001B[32m 198\u001B[39m \u001B[38;5;66;03m# this allows an exception to be raised within\u001B[39;00m\n\u001B[32m 199\u001B[39m \u001B[38;5;66;03m# the moderated greenlet so that it can continue\u001B[39;00m\n\u001B[32m 200\u001B[39m \u001B[38;5;66;03m# its expected flow.\u001B[39;00m\n\u001B[32m 201\u001B[39m result = context.throw(*sys.exc_info())\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/aiosqlite/cursor.py:48\u001B[39m, in \u001B[36mCursor.execute\u001B[39m\u001B[34m(self, sql, parameters)\u001B[39m\n\u001B[32m 46\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m parameters \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[32m 47\u001B[39m parameters = []\n\u001B[32m---> \u001B[39m\u001B[32m48\u001B[39m \u001B[38;5;28;01mawait\u001B[39;00m \u001B[38;5;28mself\u001B[39m._execute(\u001B[38;5;28mself\u001B[39m._cursor.execute, sql, parameters)\n\u001B[32m 49\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/aiosqlite/cursor.py:40\u001B[39m, in \u001B[36mCursor._execute\u001B[39m\u001B[34m(self, fn, *args, **kwargs)\u001B[39m\n\u001B[32m 38\u001B[39m \u001B[38;5;28;01masync\u001B[39;00m \u001B[38;5;28;01mdef\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[34m_execute\u001B[39m(\u001B[38;5;28mself\u001B[39m, fn, *args, **kwargs):\n\u001B[32m 39\u001B[39m \u001B[38;5;250m \u001B[39m\u001B[33;03m\"\"\"Execute the given function on the shared connection's thread.\"\"\"\u001B[39;00m\n\u001B[32m---> \u001B[39m\u001B[32m40\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;01mawait\u001B[39;00m \u001B[38;5;28mself\u001B[39m._conn._execute(fn, *args, **kwargs)\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/aiosqlite/core.py:132\u001B[39m, in \u001B[36mConnection._execute\u001B[39m\u001B[34m(self, fn, *args, **kwargs)\u001B[39m\n\u001B[32m 128\u001B[39m future = asyncio.get_event_loop().create_future()\n\u001B[32m 130\u001B[39m \u001B[38;5;28mself\u001B[39m._tx.put_nowait((future, function))\n\u001B[32m--> \u001B[39m\u001B[32m132\u001B[39m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;01mawait\u001B[39;00m future\n",
|
||||
"\u001B[36mFile \u001B[39m\u001B[32m~/cognee/.venv/lib/python3.11/site-packages/aiosqlite/core.py:115\u001B[39m, in \u001B[36mConnection.run\u001B[39m\u001B[34m(self)\u001B[39m\n\u001B[32m 113\u001B[39m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[32m 114\u001B[39m LOG.debug(\u001B[33m\"\u001B[39m\u001B[33mexecuting \u001B[39m\u001B[38;5;132;01m%s\u001B[39;00m\u001B[33m\"\u001B[39m, function)\n\u001B[32m--> \u001B[39m\u001B[32m115\u001B[39m result = \u001B[43mfunction\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[32m 116\u001B[39m LOG.debug(\u001B[33m\"\u001B[39m\u001B[33moperation \u001B[39m\u001B[38;5;132;01m%s\u001B[39;00m\u001B[33m completed\u001B[39m\u001B[33m\"\u001B[39m, function)\n\u001B[32m 117\u001B[39m future.get_loop().call_soon_threadsafe(set_result, future, result)\n",
|
||||
"\u001B[31mOperationalError\u001B[39m: (sqlite3.OperationalError) database is locked\n[SQL: \nCREATE TABLE data (\n\tid UUID NOT NULL, \n\tname VARCHAR, \n\textension VARCHAR, \n\tmime_type VARCHAR, \n\traw_data_location VARCHAR, \n\towner_id UUID, \n\tcontent_hash VARCHAR, \n\texternal_metadata JSON, \n\tnode_set JSON, \n\ttoken_count INTEGER, \n\tcreated_at DATETIME, \n\tupdated_at DATETIME, \n\tPRIMARY KEY (id)\n)\n\n]\n(Background on this error at: https://sqlalche.me/e/20/e3q8)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"execution_count": 3
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
|
|
@ -203,12 +336,39 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-06-30T11:44:56.372628Z",
|
||||
"start_time": "2025-06-30T11:44:55.978258Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:36:09.273837\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mStarting completion generation for query: 'What is in the multimedia files?'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:36:09.275355\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mStarting summary retrieval for query: 'What is in the multimedia files?'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:36:09.691101\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mFound 2 summaries from vector search\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:36:09.691827\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mReturning 2 summary payloads \u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[2m2025-08-27T14:36:09.692207\u001b[0m [\u001b[32m\u001b[1minfo \u001b[0m] \u001b[1mReturning context with 2 item(s)\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'id': 'facab42e-12fc-557e-aaf4-09c02ae1cd4f', 'created_at': 1756305273061, 'updated_at': 1756305273061, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': \"Programmers won't change a light bulb — it's considered a hardware issue.\"}\n",
|
||||
"{'id': '958f2bc9-060b-5500-b14a-19b300cc99aa', 'created_at': 1756305311791, 'updated_at': 1756305311791, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'One-line programmer joke: changing a light bulb is labeled a hardware issue.'}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from cognee.api.v1.search import SearchType\n",
|
||||
"\n",
|
||||
|
|
@ -221,25 +381,36 @@
|
|||
"# Display search results\n",
|
||||
"for result_text in search_results:\n",
|
||||
" print(result_text)"
|
||||
],
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'id': '3b530220-7e7c-52a2-8b62-ce5adce1a46c', 'created_at': 1751283883122, 'updated_at': 1751283883122, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': \"The joke queries the number of programmers required to change a light bulb and answers, 'None. That’s a hardware issue.' This humor highlights the divide between software and hardware challenges in programming.\"}\n",
|
||||
"{'id': '128eb96e-fd36-53ef-ab6d-d4884ecbfee9', 'created_at': 1751283883122, 'updated_at': 1751283883122, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': \"Changing a light bulb doesn't require programmers.\"}\n"
|
||||
"ename": "",
|
||||
"evalue": "",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
|
||||
"\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
|
||||
"\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n",
|
||||
"\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
|
||||
]
|
||||
}
|
||||
],
|
||||
"execution_count": 5
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "code",
|
||||
"outputs": [],
|
||||
"execution_count": null,
|
||||
"source": ""
|
||||
"source": [
|
||||
"# Only exit in interactive mode, not during GitHub Actions\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"# Skip exit if we're running in GitHub Actions\n",
|
||||
"if not os.environ.get('GITHUB_ACTIONS'):\n",
|
||||
" print(\"Exiting kernel to clean up resources...\")\n",
|
||||
" os._exit(0)\n",
|
||||
"else:\n",
|
||||
" print(\"Skipping kernel exit - running in GitHub Actions\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
|
@ -258,7 +429,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.6"
|
||||
"version": "3.12.7"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
|
|
|||
881
notebooks/cognee_simple_demo.ipynb
vendored
881
notebooks/cognee_simple_demo.ipynb
vendored
File diff suppressed because it is too large
Load diff
1407
notebooks/ontology_demo.ipynb
vendored
1407
notebooks/ontology_demo.ipynb
vendored
File diff suppressed because one or more lines are too long
1968
poetry.lock
generated
1968
poetry.lock
generated
File diff suppressed because it is too large
Load diff
|
|
@ -1,7 +1,7 @@
|
|||
[project]
|
||||
name = "cognee"
|
||||
|
||||
version = "0.2.3.dev1"
|
||||
version = "0.2.4"
|
||||
description = "Cognee - is a library for enriching LLM context with a semantic layer for better understanding and reasoning."
|
||||
authors = [
|
||||
{ name = "Vasilije Markovic" },
|
||||
|
|
@ -34,7 +34,7 @@ dependencies = [
|
|||
"sqlalchemy>=2.0.39,<3.0.0",
|
||||
"aiosqlite>=0.20.0,<1.0.0",
|
||||
"tiktoken>=0.8.0,<1.0.0",
|
||||
"litellm>=1.57.4, <1.71.0",
|
||||
"litellm>=1.71.0, <2.0.0",
|
||||
"instructor>=1.9.1,<2.0.0",
|
||||
"langfuse>=2.32.0,<3",
|
||||
"filetype>=1.2.0,<2.0.0",
|
||||
|
|
@ -60,7 +60,8 @@ dependencies = [
|
|||
"pympler>=1.1,<2.0.0",
|
||||
"onnxruntime>=1.0.0,<2.0.0",
|
||||
"pylance>=0.22.0,<1.0.0",
|
||||
"kuzu (==0.11.0)"
|
||||
"kuzu (==0.11.0)",
|
||||
"python-magic-bin<0.5 ; platform_system == 'Windows'", # Only needed for Windows
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
|
|
@ -145,6 +146,9 @@ debug = ["debugpy>=1.8.9,<2.0.0"]
|
|||
Homepage = "https://www.cognee.ai"
|
||||
Repository = "https://github.com/topoteretes/cognee"
|
||||
|
||||
[project.scripts]
|
||||
cognee = "cognee.cli._cognee:main"
|
||||
|
||||
[build-system]
|
||||
requires = ["hatchling"]
|
||||
build-backend = "hatchling.build"
|
||||
|
|
@ -186,4 +190,4 @@ exclude = [
|
|||
]
|
||||
|
||||
[tool.ruff.lint]
|
||||
ignore = ["F401"]
|
||||
ignore = ["F401"]
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue