cognee 0.2.1.dev7__tar.gz → 0.2.2.dev1__tar.gz

cognee-0.2.2.dev1/.env.template

@@ -0,0 +1,222 @@
+###############################################################################
+# NOTE: With default settings Cognee only needs an OpenAI LLM_API_KEY to be set.
+#       The rest of the settings don't have to be set.
+#       Default relational database: SQLite
+#       Default vector database   : LanceDB
+#       Default graph database    : Kuzu
+#
+#       These default databases are all file-based, so no extra setup is needed
+#       for local use.
+###############################################################################
+
+################################################################################
+#  🧠 LLM Settings
+################################################################################
+# Currently we support BAML and Instructor(using litellm) for structured outputs
+STRUCTURED_OUTPUT_FRAMEWORK="instructor"
+
+LLM_API_KEY="your_api_key"
+LLM_MODEL="openai/gpt-4o-mini"
+LLM_PROVIDER="openai"
+LLM_ENDPOINT=""
+LLM_API_VERSION=""
+LLM_MAX_TOKENS="16384"
+
+EMBEDDING_PROVIDER="openai"
+EMBEDDING_MODEL="openai/text-embedding-3-large"
+EMBEDDING_ENDPOINT=""
+EMBEDDING_API_VERSION=""
+EMBEDDING_DIMENSIONS=3072
+EMBEDDING_MAX_TOKENS=8191
+# If embedding key is not provided same key set for LLM_API_KEY will be used
+#EMBEDDING_API_KEY="your_api_key"
+
+# If using BAML structured output these env variables will be used
+BAML_LLM_PROVIDER=openai
+BAML_LLM_MODEL="gpt-4o-mini"
+BAML_LLM_ENDPOINT=""
+BAML_LLM_API_KEY="your_api_key"
+BAML_LLM_API_VERSION=""
+
+################################################################################
+# 🗄️ Relational database settings
+################################################################################
+
+DB_PROVIDER="sqlite"
+DB_NAME=cognee_db
+
+# -- To switch to Postgres / PGVector, uncomment and fill these: -------------
+#DB_PROVIDER=postgres
+#DB_NAME=cognee_db
+# To use Postgres with the Cognee backend in Docker compose use the following instead: DB_HOST=host.docker.internal
+#DB_HOST=127.0.0.1
+#DB_PORT=5432
+#DB_USERNAME=cognee
+#DB_PASSWORD=cognee
+
+################################################################################
+# 🕸️ Graph Database settings
+################################################################################
+
+# Default (local file-based)
+GRAPH_DATABASE_PROVIDER="kuzu"
+
+# -- To switch to Remote Kuzu uncomment and fill these: -------------------------------------------------------------
+#GRAPH_DATABASE_PROVIDER="kuzu"
+#GRAPH_DATABASE_PROVIDER="kuzu-remote"
+#GRAPH_DATABASE_URL="http://localhost:8000"
+#GRAPH_DATABASE_USERNAME=XXX
+#GRAPH_DATABASE_PASSWORD=YYY
+
+# -- To switch to Neo4j uncomment and fill these: -------------------------------------------------------------------
+#GRAPH_DATABASE_PROVIDER="neo4j"
+#GRAPH_DATABASE_URL=bolt://localhost:7687
+#GRAPH_DATABASE_NAME="neo4j"
+#GRAPH_DATABASE_USERNAME=neo4j
+#GRAPH_DATABASE_PASSWORD=localneo4j
+
+################################################################################
+#  📐 Vector Database settings
+################################################################################
+
+# Supported providers: pgvector | qdrant | weaviate | milvus | lancedb | chromadb
+VECTOR_DB_PROVIDER="lancedb"
+# Not needed if a cloud vector database is not used
+VECTOR_DB_URL=
+VECTOR_DB_KEY=
+
+################################################################################
+#  📂 ROOT DIRECTORY IF USING COGNEE LIB INSIDE A DOCKER
+################################################################################
+# Set up the Cognee system directory. Cognee will store system files and databases here.
+# DATA_ROOT_DIRECTORY='/Users/<user>/Desktop/cognee/.cognee_data/'
+# SYSTEM_ROOT_DIRECTORY='/Users/<user>/Desktop/cognee/.cognee_system/'
+
+################################################################################
+#  🔄  MIGRATION (RELATIONAL → GRAPH) SETTINGS
+################################################################################
+
+MIGRATION_DB_PATH="/path/to/migration/directory"
+MIGRATION_DB_NAME="migration_database.sqlite"
+MIGRATION_DB_PROVIDER="sqlite"
+
+# -- Postgres-specific migration params --------------------------------------
+# MIGRATION_DB_USERNAME=cognee
+# MIGRATION_DB_PASSWORD=cognee
+# MIGRATION_DB_HOST="127.0.0.1"
+# MIGRATION_DB_PORT=5432
+
+################################################################################
+# 🔒 Security Settings
+################################################################################
+
+# When set to false don't allow adding of local system files to Cognee. Should be set to False when Cognee is used as a backend.
+ACCEPT_LOCAL_FILE_PATH=True
+
+# When set to false don't allow HTTP requests to be sent from Cognee.
+# This protects against Server Side Request Forgery when proper infrastructure is not in place.
+ALLOW_HTTP_REQUESTS=True
+
+# When set to False errors during data processing will be returned as info but not raised to allow handling of faulty documents
+RAISE_INCREMENTAL_LOADING_ERRORS=True
+
+# Set this variable to True to enforce usage of backend access control for Cognee
+# Note: This is only currently supported by the following databases:
+#       Relational: SQLite, Postgres
+#       Vector: LanceDB
+#       Graph: KuzuDB
+#
+# It enforces LanceDB and KuzuDB use and uses them to create databases per Cognee user + dataset
+ENABLE_BACKEND_ACCESS_CONTROL=False
+
+################################################################################
+#  🛠️ DEV Settings
+################################################################################
+
+ENV="local"
+
+TOKENIZERS_PARALLELISM="false"
+
+# LITELLM Logging Level. Set to quiet down logging
+LITELLM_LOG="ERROR"
+
+# Set this environment variable to disable sending telemetry data
+# TELEMETRY_DISABLED=1
+
+# Default User Configuration
+# DEFAULT_USER_EMAIL=""
+# DEFAULT_USER_PASSWORD=""
+
+------------------------------- END OF POSSIBLE SETTINGS -------------------------------
+
+
+###############################################################################
+# 🧪  EXAMPLE OVERRIDES (commented out)
+###############################################################################
+# The blocks below show how to configure alternative providers.
+# Uncomment + fill values to switch.
+
+########## Azure OpenAI #######################################################
+#LLM_MODEL="azure/gpt-4o-mini"
+#LLM_ENDPOINT="https://DNS.azure.com/openai/deployments/gpt-4o-mini"
+#LLM_API_KEY="<<TALK TO YOUR AZURE GUY"
+#LLM_API_VERSION="2024-12-01-preview"
+
+## llm api version might not be relevant
+#LLM_MAX_TOKENS="16384"
+
+#EMBEDDING_MODEL="azure/text-embedding-3-large"
+#EMBEDDING_ENDPOINT="https://DNS.openai.azure.com/openai/deployments/text-embedding-3-large"
+#EMBEDDING_API_KEY="<<TALK TO YOUR AZURE GUY>"
+#EMBEDDING_API_VERSION="2024-12-01-preview"
+#EMBEDDING_DIMENSIONS=3072
+#EMBEDDING_MAX_TOKENS=8191
+
+########## Local LLM via Ollama ###############################################
+
+#LLM_API_KEY ="ollama"
+#LLM_MODEL="llama3.1:8b"
+#LLM_PROVIDER="ollama"
+#LLM_ENDPOINT="http://localhost:11434/v1"
+#EMBEDDING_PROVIDER="ollama"
+#EMBEDDING_MODEL="avr/sfr-embedding-mistral:latest"
+#EMBEDDING_ENDPOINT="http://localhost:11434/api/embeddings"
+#EMBEDDING_DIMENSIONS=4096
+#HUGGINGFACE_TOKENIZER="Salesforce/SFR-Embedding-Mistral"
+
+########## OpenRouter (also free) #########################################################
+
+#LLM_API_KEY="<<go-get-one-yourself"
+#LLM_PROVIDER="custom"
+#LLM_MODEL="openrouter/google/gemini-2.0-flash-lite-preview-02-05:free"
+#LLM_ENDPOINT="https://openrouter.ai/api/v1"
+
+########## DeepInfra ##########################################################
+
+#LLM_API_KEY="<<>>"
+#LLM_PROVIDER="custom"
+#LLM_MODEL="deepinfra/meta-llama/Meta-Llama-3-8B-Instruct"
+#LLM_ENDPOINT="https://api.deepinfra.com/v1/openai"
+
+#EMBEDDING_PROVIDER="openai"
+#EMBEDDING_API_KEY="<<>>"
+#EMBEDDING_MODEL="deepinfra/BAAI/bge-base-en-v1.5"
+#EMBEDDING_ENDPOINT=""
+#EMBEDDING_API_VERSION=""
+#EMBEDDING_DIMENSIONS=3072
+#EMBEDDING_MAX_TOKENS=8191
+
+
+########## Release Test ###############################################
+
+#LLM_API_KEY="..."
+
+#OPENAI_API_KEY="..."
+
+#MIGRATION_DB_PATH="~/Downloads/"
+#MIGRATION_DB_NAME="Chinook_Sqlite.sqlite"
+#MIGRATION_DB_PROVIDER="sqlite"
+
+#GRAPH_DATABASE_URL="bolt://54.246.89.112:7687"
+#GRAPH_DATABASE_USERNAME="neo4j"
+#GRAPH_DATABASE_PASSWORD="pleaseletmein"

cognee-0.2.2.dev1/.gitguardian.yml

@@ -0,0 +1,31 @@
+# .gitguardian.yml
+version: v1
+
+secret-scan:
+  # Ignore specific files
+  excluded-paths:
+    - '.env.template'
+    - '.github/workflows/*.yml'
+    - 'examples/**'
+    - 'tests/**'
+
+  # Ignore specific patterns
+  excluded-detectors:
+    - 'Generic Password'
+    - 'Generic High Entropy Secret'
+
+  # Ignore by commit (if needed)
+  excluded-commits:
+    - '782bbb4'
+    - 'f857e07'
+
+  # Custom rules for template files
+  paths-ignore:
+    - path: '.env.template'
+      comment: 'Template file with placeholder values'
+    - path: '.github/workflows/search_db_tests.yml'
+      comment: 'Test workflow with test credentials'
+    - path: 'docker-compose.yml'
+      comment: 'Development docker compose with test credentials (neo4j/pleaseletmein, postgres cognee/cognee)'
+    - path: 'deployment/helm/docker-compose-helm.yml'
+      comment: 'Helm deployment docker compose with test postgres credentials (cognee/cognee)'

cognee-0.2.2.dev1/.gitignore

@@ -0,0 +1,198 @@
+.data
+.env
+.local.env
+.prod.env
+cognee/.data/
+
+code_pipeline_output*/
+
+*.lance/
+.DS_Store
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+full_run.ipynb
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+.python-version
+cognee-mcp/.python-version
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Cognee logs directory - keep directory, ignore contents
+logs/*
+!logs/.gitkeep
+!logs/README.md
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.env.local
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+.vscode/
+cognee/data/
+cognee/cache/
+
+# Default cognee system directory, used in development
+.cognee_system/
+.data_storage/
+.artifacts/
+.anon_id
+
+node_modules/
+
+# Evals
+SWE-bench_testsample/
+
+# ChromaDB Data
+.chromadb_data/

cognee-0.2.2.dev1/CONTRIBUTING.md

@@ -0,0 +1,141 @@
+> [!IMPORTANT]
+> **Note for contributors:** When branching out, create a new branch from the `dev` branch.
+
+# 🎉 Welcome to **cognee**! 
+
+We're excited that you're interested in contributing to our project! 
+We want to ensure that every user and contributor feels welcome, included and supported to participate in cognee community. 
+This guide will help you get started and ensure your contributions can be efficiently integrated into the project.
+
+## 🌟 Quick Links
+
+- [Code of Conduct](CODE_OF_CONDUCT.md)
+- [Discord Community](https://discord.gg/bcy8xFAtfd)  
+- [Issue Tracker](https://github.com/topoteretes/cognee/issues)
+- [Cognee Docs](https://docs.cognee.ai)
+
+## 1. 🚀 Ways to Contribute
+
+You can contribute to **cognee** in many ways:
+
+- 📝 Submitting bug reports or feature requests
+- 💡 Improving documentation
+- 🔍 Reviewing pull requests
+- 🛠️ Contributing code or tests
+- 🌐 Helping other users
+
+## 📫 Get in Touch
+
+There are several ways to connect with the **cognee** team and community:
+
+### GitHub Collaboration
+- [Open an issue](https://github.com/topoteretes/cognee/issues) for bug reports, feature requests, or discussions
+- Submit pull requests to contribute code or documentation
+- Join ongoing discussions in existing issues and PRs
+
+### Community Channels
+- Join our [Discord community](https://discord.gg/bcy8xFAtfd) for real-time discussions
+- Participate in community events and discussions
+- Get help from other community members
+
+### Direct Contact
+- Email: vasilije@cognee.ai
+- For business inquiries or sensitive matters, please reach out via email
+- For general questions, prefer public channels like GitHub issues or Discord
+
+We aim to respond to all communications within 2 business days. For faster responses, consider using our Discord channel where the whole community can help!
+
+## Issue Labels
+
+To help you find the most appropriate issues to work on, we use the following labels:
+
+- `good first issue` - Perfect for newcomers to the project
+- `bug` - Something isn't working as expected
+- `documentation` - Improvements or additions to documentation
+- `enhancement` - New features or improvements
+- `help wanted` - Extra attention or assistance needed
+- `question` - Further information is requested
+- `wontfix` - This will not be worked on
+
+Looking for a place to start? Try filtering for [good first issues](https://github.com/topoteretes/cognee/labels/good%20first%20issue)!
+
+
+## 2. 🛠️ Development Setup
+
+### Fork and Clone
+
+1. Fork the [**cognee**](https://github.com/topoteretes/cognee) repository
+2. Clone your fork:
+```shell
+git clone https://github.com/<your-github-username>/cognee.git
+cd cognee
+```
+In case you are working on Vector and Graph Adapters
+1. Fork the [**cognee**](https://github.com/topoteretes/cognee-community) repository
+2. Clone your fork:
+```shell
+git clone https://github.com/<your-github-username>/cognee-community.git
+cd cognee-community
+```
+
+### Create a Branch
+
+Create a new branch for your work:
+```shell
+git checkout -b feature/your-feature-name
+```
+
+## 3. 🎯 Making Changes
+
+1. **Code Style**: Follow the project's coding standards
+2. **Documentation**: Update relevant documentation
+3. **Tests**: Add tests for new features
+4. **Commits**: Write clear commit messages
+
+### Running Tests
+```shell
+python cognee/cognee/tests/test_library.py
+```
+
+## 4. 📤 Submitting Changes
+
+1. Install ruff on your system
+2. Run ```ruff format .``` and ``` ruff check ``` and fix the issues
+3. Push your changes:
+```shell
+git add .
+git commit -s -m "Description of your changes"
+git push origin feature/your-feature-name
+```
+
+2. Create a Pull Request:
+   - Go to the [**cognee** repository](https://github.com/topoteretes/cognee) or [cognee community repository](https://github.com/topoteretes/cognee-community)
+   - Click "Compare & Pull Request" and open a PR against dev branch
+   - Fill in the PR template with details about your changes
+
+## 5. 📜 Developer Certificate of Origin (DCO)
+
+All contributions must be signed-off to indicate agreement with our DCO:
+
+```shell
+git config alias.cos "commit -s"  # Create alias for signed commits
+```
+
+When your PR is ready, please include:
+> "I affirm that all code in every commit of this pull request conforms to the terms of the Topoteretes Developer Certificate of Origin"
+
+## 6. 🤝 Community Guidelines
+
+- Be respectful and inclusive
+- Help others learn and grow
+- Follow our [Code of Conduct](CODE_OF_CONDUCT.md)
+- Provide constructive feedback
+- Ask questions when unsure
+
+## 7. 📫 Getting Help
+
+- Open an [issue](https://github.com/topoteretes/cognee/issues)
+- Join our Discord community
+- Check existing documentation
+
+Thank you for contributing to **cognee**! 🌟

cognee-0.2.2.dev1/Dockerfile

@@ -0,0 +1,68 @@
+# Use a Python image with uv pre-installed
+FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim AS uv
+
+# Install the project into `/app`
+WORKDIR /app
+
+# Enable bytecode compilation
+# ENV UV_COMPILE_BYTECODE=1
+
+# Copy from the cache instead of linking since it's a mounted volume
+ENV UV_LINK_MODE=copy
+
+# Set build argument
+ARG DEBUG
+
+# Set environment variable based on the build argument
+ENV DEBUG=${DEBUG}
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    gcc \
+    libpq-dev \
+    git \
+    curl \
+    clang \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy pyproject.toml and lockfile first for better caching
+COPY README.md pyproject.toml uv.lock entrypoint.sh ./
+
+# Install the project's dependencies using the lockfile and settings
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --extra debug --extra api --extra postgres --extra neo4j --extra llama-index --extra gemini --extra ollama --extra mistral --extra groq --extra anthropic --frozen --no-install-project --no-dev --no-editable
+
+# Copy Alembic configuration
+COPY alembic.ini /app/alembic.ini
+COPY alembic/ /app/alembic
+
+# Then, add the rest of the project source code and install it
+# Installing separately from its dependencies allows optimal layer caching
+COPY ./cognee /app/cognee
+COPY ./distributed /app/distributed
+RUN --mount=type=cache,target=/root/.cache/uv \
+uv sync --extra debug --extra api --extra postgres --extra neo4j --extra llama-index --extra gemini --extra ollama --extra mistral --extra groq --extra anthropic --frozen --no-dev --no-editable
+
+FROM python:3.12-slim-bookworm
+
+RUN apt-get update && apt-get install -y \
+    libpq5 \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY --from=uv /app /app
+# COPY --from=uv /app/.venv /app/.venv
+# COPY --from=uv /root/.local /root/.local
+
+RUN chmod +x /app/entrypoint.sh
+
+# Place executables in the environment at the front of the path
+ENV PATH="/app/.venv/bin:$PATH"
+
+ENV PYTHONPATH=/app
+# ENV LOG_LEVEL=ERROR
+ENV PYTHONUNBUFFERED=1
+
+ENTRYPOINT ["/app/entrypoint.sh"]