cognee 1.1.0.dev1__tar.gz → 1.1.1.dev0__tar.gz

cognee-1.1.1.dev0/.env.template

@@ -0,0 +1,432 @@
+###############################################################################
+# TIER 1 — QUICK START
+# Set this one variable and you're done. Everything else has working defaults.
+# Default databases (SQLite, LanceDB, KuzuDB) are file-based, no setup needed.
+###############################################################################
+LLM_API_KEY="your_api_key"
+
+
+###############################################################################
+# TIER 2 — COMMON OVERRIDES (uncomment to customize)
+# Most users only need a few of these.
+###############################################################################
+
+# -- LLM Provider & Model ----------------------------------------------------
+#LLM_MODEL="openai/gpt-5-mini"
+#LLM_PROVIDER="openai"
+#LLM_ENDPOINT=""
+
+# -- Embedding Provider -------------------------------------------------------
+#EMBEDDING_PROVIDER="openai"
+#EMBEDDING_MODEL="openai/text-embedding-3-large"
+#EMBEDDING_DIMENSIONS=3072
+
+# -- Database Providers (switch from file-based defaults) ---------------------
+#DB_PROVIDER="postgres"
+#DB_HOST=127.0.0.1
+#DB_PORT=5432
+#DB_USERNAME=cognee
+#DB_PASSWORD=cognee
+#DB_NAME=cognee_db
+
+#GRAPH_DATABASE_PROVIDER="neo4j"
+#VECTOR_DB_PROVIDER="lancedb"
+
+
+###############################################################################
+# TIER 3 — ADVANCED (grouped by subsystem)
+# Most users never need to change anything below this line.
+###############################################################################
+
+################################################################################
+#  LLM — Advanced Settings
+#  Tune these when switching providers, adjusting structured output, or
+#  rate-limiting LLM calls.
+################################################################################
+
+# Structured output framework: "instructor" (default, via litellm) or "baml"
+STRUCTURED_OUTPUT_FRAMEWORK="instructor"
+
+# Instructor's mode determines how structured data is extracted from LLM responses.
+# Each LLM has its own default (e.g. gpt-5 models use "json_schema_mode").
+#LLM_INSTRUCTOR_MODE=""
+
+# Cognee uses this to determine optimal chunk size (not forwarded in LLM calls).
+#LLM_MAX_TOKENS="16384"
+
+# LLM API version (needed for Azure OpenAI)
+#LLM_API_VERSION=""
+
+# Extra kwargs passed to every LLM completion call (JSON string).
+# Examples: LLM_ARGS='{"max_tokens": 16384, "temperature": 0.7}'
+#LLM_ARGS='{}'
+
+# LLM rate limiting
+#LLM_RATE_LIMIT_ENABLED=true
+#LLM_RATE_LIMIT_REQUESTS=60
+#LLM_RATE_LIMIT_INTERVAL=60
+
+################################################################################
+#  Embedding — Advanced Settings
+#  Tune these when using non-default embedding providers.
+################################################################################
+
+#EMBEDDING_ENDPOINT=""
+#EMBEDDING_API_VERSION=""
+#EMBEDDING_MAX_TOKENS=8191
+#EMBEDDING_BATCH_SIZE=36
+# If not provided, LLM_API_KEY is used for embeddings too.
+#EMBEDDING_API_KEY="your_api_key"
+
+################################################################################
+#  BAML Structured Output
+#  Only needed when STRUCTURED_OUTPUT_FRAMEWORK="baml".
+################################################################################
+
+#BAML_LLM_PROVIDER=openai
+#BAML_LLM_MODEL="gpt-5-mini"
+#BAML_LLM_ENDPOINT=""
+#BAML_LLM_API_KEY="your_api_key"
+#BAML_LLM_API_VERSION=""
+
+################################################################################
+#  Root Directories
+#  Override where Cognee stores files and databases (default: .venv).
+################################################################################
+
+#DATA_ROOT_DIRECTORY='/Users/<user>/Desktop/cognee/.cognee_data/'
+#SYSTEM_ROOT_DIRECTORY='/Users/<user>/Desktop/cognee/.cognee_system/'
+
+################################################################################
+#  Storage Backend
+#  Switch from local filesystem to S3.
+################################################################################
+
+#STORAGE_BACKEND="local"
+#STORAGE_BACKEND="s3"
+#STORAGE_BUCKET_NAME="your-bucket-name"
+#AWS_REGION="us-east-1"
+#AWS_ACCESS_KEY_ID="your-access-key"
+#AWS_SECRET_ACCESS_KEY="your-secret-key"
+#DATA_ROOT_DIRECTORY="s3://your-bucket/cognee/data"
+#SYSTEM_ROOT_DIRECTORY="s3://your-bucket/cognee/system"
+#CACHE_ROOT_DIRECTORY="s3://your-bucket/cognee/cache"
+
+################################################################################
+#  Relational Database — Advanced
+#  Connection tuning, pool sizes, SSL.
+################################################################################
+
+DB_PROVIDER="sqlite"
+DB_NAME=cognee_db
+
+# Custom connection arguments (JSON). Useful for SSL, timeouts.
+#DATABASE_CONNECT_ARGS='{"sslmode": "require", "connect_timeout": 10}'
+
+# Connection pool tuning (JSON).
+#POOL_ARGS='{"pool_size": 5, "max_overflow": 10, "pool_recycle": -1, "pool_timeout": 30}'
+
+################################################################################
+#  Graph Database — Advanced
+#  Provider-specific connection details.
+################################################################################
+
+GRAPH_DATABASE_PROVIDER="kuzu"
+# Handler for multi-user access control (per-dataset DB creation).
+GRAPH_DATASET_DATABASE_HANDLER="kuzu"
+
+# Remote Kuzu
+#GRAPH_DATABASE_PROVIDER="kuzu-remote"
+#GRAPH_DATABASE_URL="http://localhost:8000"
+#GRAPH_DATABASE_USERNAME=XXX
+#GRAPH_DATABASE_PASSWORD=YYY
+
+# Neo4j
+#GRAPH_DATABASE_PROVIDER="neo4j"
+#GRAPH_DATABASE_URL=bolt://localhost:7687
+#GRAPH_DATABASE_NAME="neo4j"
+#GRAPH_DATABASE_USERNAME=neo4j
+#GRAPH_DATABASE_PASSWORD=pleaseletmein
+
+################################################################################
+#  Vector Database — Advanced
+#  Provider-specific connection details.
+################################################################################
+
+# Supported: pgvector | qdrant | weaviate | milvus | lancedb | chromadb
+VECTOR_DB_PROVIDER="lancedb"
+#VECTOR_DB_URL=
+#VECTOR_DB_KEY=
+# Handler for multi-user access control (per-dataset DB creation).
+VECTOR_DATASET_DATABASE_HANDLER="lancedb"
+
+################################################################################
+#  Ontology Resolver
+#  Use when grounding extraction against an OWL ontology.
+################################################################################
+
+#ONTOLOGY_RESOLVER=rdflib
+#MATCHING_STRATEGY=fuzzy
+#ONTOLOGY_FILE_PATH=YOUR_FULL_FILE_PATH
+
+################################################################################
+#  Database Adapter Caching
+#  Max graph / vector / relational engine instances held in the LRU cache
+#  (one per unique connection key, e.g. per dataset in multi-tenant mode).
+#  In subprocess mode, this also caps how many child processes (Kuzu/LanceDB
+#  workers) can be alive at once — eviction shuts down the subprocess.
+#  Also the default for DATASET_QUEUE_MAX_CONCURRENT when that is unset.
+#  Lower values save memory; raise when running many datasets concurrently.
+################################################################################
+
+#DATABASE_MAX_LRU_CACHE_SIZE=6
+
+################################################################################
+#  Dataset Queue
+#  Semaphore-backed queue that limits how many datasets can be processed at
+#  once (cognify, search, etc.). Prevents resource exhaustion when many
+#  datasets run in parallel. When the limit is reached, new datasets wait
+#  until a slot is freed.
+################################################################################
+
+#DATASET_QUEUE_ENABLED=true
+# Max concurrent dataset slots. Defaults to DATABASE_MAX_LRU_CACHE_SIZE.
+#DATASET_QUEUE_MAX_CONCURRENT=6
+
+################################################################################
+#  Translation
+#  Use when ingesting non-English content.
+################################################################################
+
+TRANSLATION_PROVIDER="llm"
+TARGET_LANGUAGE="en"
+CONFIDENCE_THRESHOLD=0.8
+#GOOGLE_TRANSLATE_API_KEY="your-google-api-key"
+#GOOGLE_PROJECT_ID="your-google-project-id"
+#AZURE_TRANSLATOR_KEY="your-azure-translator-key"
+#AZURE_TRANSLATOR_REGION="westeurope"
+#AZURE_TRANSLATOR_ENDPOINT="https://api.cognitive.microsofttranslator.com"
+#TRANSLATION_BATCH_SIZE=10
+#TRANSLATION_MAX_RETRIES=3
+#TRANSLATION_TIMEOUT_SECONDS=30
+
+################################################################################
+#  Migration (Relational -> Graph)
+################################################################################
+
+MIGRATION_DB_PATH="/path/to/migration/directory"
+MIGRATION_DB_NAME="migration_database.sqlite"
+MIGRATION_DB_PROVIDER="sqlite"
+#MIGRATION_DB_USERNAME=cognee
+#MIGRATION_DB_PASSWORD=cognee
+#MIGRATION_DB_HOST="127.0.0.1"
+#MIGRATION_DB_PORT=5432
+
+################################################################################
+#  Security
+################################################################################
+
+# -- JWT Authentication -------------------------------------------------------
+# Secret used to sign and verify JWT tokens. Must be the same across all instances
+# (e.g. all Kubernetes pods) for tokens issued by one instance to be accepted by another.
+# Change this to a long random string in production. Never commit the real value to git.
+FASTAPI_USERS_JWT_SECRET="super_secret"
+
+# How long a JWT token remains valid, in seconds. After expiry the user must log in again.
+# The same lifetime applies to both cookie and bearer token auth.
+# Default: 3600 (1 hour)
+JWT_LIFETIME_SECONDS=3600
+
+# -- API Key Authentication ---------------------------------------------------
+# When HASH_API_KEY=true, API keys are hashed with SHA-256 before being stored in the database.
+# This means the raw key is shown to the user only once at creation time and cannot be recovered.
+#
+# ⚠️  Migration note: if you enable this on a running system that already has API keys stored
+#     in plaintext, those existing keys will stop working immediately because the lookup will
+#     hash the incoming value and find no match. You must either:
+#       1. Delete and re-issue all existing API keys, or
+#       2. Write a one-off migration to SHA-256 hash the existing api_key column values.
+#
+# Default: false (keys are stored in plaintext)
+HASH_API_KEY="False"
+
+# 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
+ALLOW_HTTP_REQUESTS=True
+ALLOW_CYPHER_QUERY=True
+RAISE_INCREMENTAL_LOADING_ERRORS=True
+
+# Authentication & access control.
+#
+# ENABLE_BACKEND_ACCESS_CONTROL is the canonical posture switch:
+#   true  (default) - multi-tenant mode: per-user/dataset isolated DBs AND
+#                     API endpoints require an authenticated user.
+#   false           - single-user mode: shared DB AND auth requirement off.
+#
+# REQUIRE_AUTHENTICATION is an explicit override on the auth requirement only:
+#   unset (default) - follow ENABLE_BACKEND_ACCESS_CONTROL.
+#   true            - force auth on (sane for single-user behind a token).
+#   false           - force auth off — IGNORED if ENABLE_BACKEND_ACCESS_CONTROL
+#                     is true (multi-tenant always requires auth; a warning is
+#                     logged at startup).
+#
+# Startup logs an "auth posture: ..." line with the resolved decision so you
+# can verify what's actually in effect.
+REQUIRE_AUTHENTICATION=False
+
+# 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, pgvector
+#       Graph: KuzuDB, neo4j_aura_dev
+#
+# It enforces creation of databases per Cognee user + dataset. Does not work with some graph and database providers.
+# Disable mode when using not supported graph/vector databases.
+ENABLE_BACKEND_ACCESS_CONTROL=True
+
+################################################################################
+#  Cloud Sync
+################################################################################
+
+COGNEE_CLOUD_API_URL="http://localhost:8001"
+COGNEE_CLOUD_AUTH_TOKEN="your-api-key"
+
+################################################################################
+#  UI
+################################################################################
+
+UI_APP_URL=http://localhost:3000
+
+################################################################################
+#  DLT Ingestion
+################################################################################
+
+#DLT_MAX_ROWS_PER_TABLE=50
+
+################################################################################
+#  Dev / Debug
+################################################################################
+
+ENV="local"
+#ENABLE_LAST_ACCESSED="false"
+TOKENIZERS_PARALLELISM="false"
+
+# -- Search History ------------------------------------------------------------
+# Set to false to disable search query/result logging (recommended for daemons)
+#COGNEE_LOG_SEARCH_HISTORY="true"
+
+# LITELLM Logging Level. Set to quiet down logging
+LITELLM_LOG="ERROR"
+#TELEMETRY_DISABLED=1
+#DEFAULT_USER_EMAIL=""
+#DEFAULT_USER_PASSWORD=""
+
+# -- Cognee Logging -----------------------------------------------------------
+# Console log level: DEBUG, INFO, WARNING, ERROR, CRITICAL (default: INFO)
+#LOG_LEVEL="INFO"
+# Set to false to disable file logging entirely (console-only)
+#COGNEE_LOG_FILE="true"
+# Override the log directory (default: ~/.cognee/logs)
+#COGNEE_LOGS_DIR="/var/log/cognee"
+# Max size per log file before rotation, in bytes (default: 50 MB)
+#COGNEE_LOG_MAX_BYTES=52428800
+# Number of rotated log files to keep (default: 5 → 300 MB total cap)
+#COGNEE_LOG_BACKUP_COUNT=5
+
+################################################################################
+#  AWS
+################################################################################
+
+#AWS_REGION=""
+#AWS_ENDPOINT_URL=""
+#AWS_ACCESS_KEY_ID=""
+#AWS_SECRET_ACCESS_KEY=""
+#AWS_SESSION_TOKEN=""
+
+################################################################################
+#  Web Scraper
+################################################################################
+
+WEB_SCRAPER_TIMEOUT=15.0
+WEB_SCRAPER_MAX_DELAY=10.0
+
+################################################################################
+#  OpenTelemetry / Tracing
+################################################################################
+
+# -- To export traces to an OTLP-compatible backend (Dash0, Grafana, Jaeger, etc.),
+#    set the endpoint and optional auth headers: ---------------------
+# COGNEE_TRACING_ENABLED=true
+# OTEL_EXPORTER_OTLP_ENDPOINT="https://ingress.eu-west.dash0.com:4317"
+# OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer <your-token>"
+
+# Override the service name reported in traces (default: "cognee")
+# OTEL_SERVICE_NAME="cognee"
+
+# Add extra resource attributes (useful for Kubernetes, multi-instance deployments)
+# OTEL_RESOURCE_ATTRIBUTES="service.namespace=my-team,service.version=1.0"
+
+# Session cache settings
+# To switch to Redis caching check our documentation page sessions-and-caching
+# CACHING=true
+# CACHE_BACKEND=fs
+
+
+###############################################################################
+# TIER 4 — EXAMPLE PROVIDER OVERRIDES (commented out)
+# Uncomment + fill values to switch providers.
+###############################################################################
+
+########## Azure OpenAI (API key auth) ########################################
+#LLM_PROVIDER="azure"
+#LLM_MODEL="azure/gpt-5-mini"
+#LLM_ENDPOINT="https://YOUR-RESOURCE.openai.azure.com"
+#LLM_API_KEY="your-azure-api-key"
+#LLM_API_VERSION="2024-12-01-preview"
+#LLM_MAX_TOKENS="16384"
+
+########## Azure OpenAI (managed identity / DefaultAzureCredential) ###########
+# Uses DefaultAzureCredential - no API key needed (for Azure VMs, App Service, etc.)
+# Requires: pip install azure-identity
+#LLM_PROVIDER="azure"
+#LLM_MODEL="azure/gpt-5-mini"
+#LLM_ENDPOINT="https://YOUR-RESOURCE.openai.azure.com"
+#LLM_API_VERSION="2024-12-01-preview"
+#LLM_AZURE_USE_MANAGED_IDENTITY=true
+
+#EMBEDDING_MODEL="azure/text-embedding-3-large"
+#EMBEDDING_ENDPOINT="https://YOUR-RESOURCE.openai.azure.com/openai/deployments/text-embedding-3-large"
+#EMBEDDING_API_KEY="your-azure-api-key"
+#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="nomic-embed-text:latest"
+#EMBEDDING_ENDPOINT="http://localhost:11434/api/embed"
+#EMBEDDING_DIMENSIONS=768
+#HUGGINGFACE_TOKENIZER="nomic-ai/nomic-embed-text-v1.5"
+
+########## 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

cognee-1.1.1.dev0/.gitignore

@@ -0,0 +1,213 @@
+.data
+.env
+.local.env
+.prod.env
+cognee/.data/
+
+code_pipeline_output*/
+
+# Test output files
+test_outputs/
+
+*.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
+
+# cognee-mcp app bundle (built by `npm run build` under cognee-mcp/apps-src/).
+# Generated artifact — see cognee-mcp/README.md for the build step.
+cognee-mcp/src/app_bundles/
+
+# 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/
+mise.toml
+deployment/helm/values-local.yml
+
+# 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/
+.cognee_cache/
+.artifacts/
+.anon_id
+
+node_modules/
+
+# Evals
+SWE-bench_testsample/
+
+# ChromaDB Data
+.chromadb_data/
+
+deployment/helm/values-local.yml
+
+# Performance test results
+cognee/tests/performance/results