cognee 0.3.4.dev4__tar.gz → 0.3.5__tar.gz

cognee-0.3.5/.env.template

@@ -0,0 +1,291 @@
+###############################################################################
+# 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. The data by default will be stored in your .venv
+###############################################################################
+
+################################################################################
+#  🧠 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-5-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"
+# Note: OpenAI support up to 2048 elements and Gemini supports a maximum of 100 elements in an embedding batch,
+#       Cognee sets the optimal batch size for OpenAI and Gemini, but a custom size can be defined if necessary for other models
+#EMBEDDING_BATCH_SIZE=2048
+
+# If using BAML structured output these env variables will be used
+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 DIRECTORY FOR DATABASES
+################################################################################
+# Set up the Cognee system directory. Cognee will store system files and databases here.
+# Useful for setting root directory inside docker and also to avoid storing the databases in .venv
+# DATA_ROOT_DIRECTORY='/Users/<user>/Desktop/cognee/.cognee_data/'
+# SYSTEM_ROOT_DIRECTORY='/Users/<user>/Desktop/cognee/.cognee_system/'
+
+################################################################################
+# ☁️ Storage Backend Settings
+################################################################################
+# Configure storage backend (local filesystem or S3)
+# STORAGE_BACKEND="local"  # Default: uses local filesystem
+#
+# -- To switch to S3 storage, uncomment and fill these: ---------------------
+# 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"
+#
+# -- S3 Root Directories (optional) -----------------------------------------
+# DATA_ROOT_DIRECTORY="s3://your-bucket/cognee/data"
+# SYSTEM_ROOT_DIRECTORY="s3://your-bucket/cognee/system"
+#
+# -- Cache Directory (auto-configured for S3) -------------------------------
+# When STORAGE_BACKEND=s3, cache automatically uses S3: s3://BUCKET/cognee/cache
+# To override the automatic S3 cache location, uncomment:
+# CACHE_ROOT_DIRECTORY="s3://your-bucket/cognee/cache"
+
+################################################################################
+# 🗄️ 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=
+
+################################################################################
+# 🧩 Ontology resolver settings
+################################################################################
+
+# -- Ontology resolver params --------------------------------------
+# ONTOLOGY_RESOLVER=rdflib  # Default: uses rdflib and owl file to read ontology structures
+# MATCHING_STRATEGY=fuzzy # Default: uses fuzzy matching with 80% similarity threshold
+# ONTOLOGY_FILE_PATH=YOUR_FULL_FULE_PATH # Default: empty
+# To add ontology resolvers, either set them as it is set in ontology_example or add full_path and settings as envs.
+
+################################################################################
+#  🔄  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 don't allow cypher search to be used in Cognee.
+ALLOW_CYPHER_QUERY=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
+
+# When set to True, the Cognee backend will require authentication for requests to the API.
+# If you're disabling this, make sure to also disable ENABLE_BACKEND_ACCESS_CONTROL.
+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
+#       Graph: KuzuDB
+#
+# It enforces LanceDB and KuzuDB use and uses them to create databases per Cognee user + dataset
+ENABLE_BACKEND_ACCESS_CONTROL=False
+
+################################################################################
+# ☁️ Cloud Sync Settings
+################################################################################
+
+# Cognee Cloud API settings for syncing data to/from cloud infrastructure
+COGNEE_CLOUD_API_URL="http://localhost:8001"
+COGNEE_CLOUD_AUTH_TOKEN="your-api-key"
+
+################################################################################
+# UI Settings
+################################################################################
+
+# URL where the frontend is served, defaults to http://localhost:3000
+UI_APP_URL=http://localhost:3000
+
+################################################################################
+#  🛠️ DEV Settings
+################################################################################
+
+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=""
+
+################################################################################
+#  📂 AWS Settings
+################################################################################
+
+#AWS_REGION=""
+#AWS_ENDPOINT_URL=""
+#AWS_ACCESS_KEY_ID=""
+#AWS_SECRET_ACCESS_KEY=""
+#AWS_SESSION_TOKEN=""
+
+------------------------------- 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-5-mini"
+#LLM_ENDPOINT="https://DNS.azure.com/openai/deployments/gpt-5-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-0.3.5/Dockerfile

@@ -0,0 +1,69 @@
+# 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=${DEBUG}
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    gcc \
+    libpq-dev \
+    git \
+    curl \
+    cmake \
+    clang \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy pyproject.toml and lockfile first for better caching
+COPY README.md pyproject.toml uv.lock entrypoint.sh ./
+
+# Install the project's dependencies using the lockfile and settings
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --extra debug --extra api --extra postgres --extra neo4j --extra llama-index --extra ollama --extra mistral --extra groq --extra anthropic --frozen --no-install-project --no-dev --no-editable
+
+# Copy Alembic configuration
+COPY alembic.ini /app/alembic.ini
+COPY alembic/ /app/alembic
+
+# Then, add the rest of the project source code and install it
+# Installing separately from its dependencies allows optimal layer caching
+COPY ./cognee /app/cognee
+COPY ./distributed /app/distributed
+RUN --mount=type=cache,target=/root/.cache/uv \
+uv sync --extra debug --extra api --extra postgres --extra neo4j --extra llama-index --extra ollama --extra mistral --extra groq --extra anthropic --frozen --no-dev --no-editable
+
+FROM python:3.12-slim-bookworm
+
+RUN apt-get update && apt-get install -y \
+    libpq5 \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY --from=uv /app /app
+# COPY --from=uv /app/.venv /app/.venv
+# COPY --from=uv /root/.local /root/.local
+
+RUN chmod +x /app/entrypoint.sh
+
+# Place executables in the environment at the front of the path
+ENV PATH="/app/.venv/bin:$PATH"
+
+ENV PYTHONPATH=/app
+# ENV LOG_LEVEL=ERROR
+ENV PYTHONUNBUFFERED=1
+
+ENTRYPOINT ["/app/entrypoint.sh"]