cognee 0.5.1__tar.gz → 0.5.2__tar.gz

cognee-0.5.2/.coderabbit.yaml

@@ -0,0 +1,127 @@
+# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
+# .coderabbit.yaml
+language: en
+early_access: false
+enable_free_tier: true
+reviews:
+  profile: chill
+  instructions: >-
+    # Code Review Instructions
+
+    - Ensure the code follows best practices and coding standards.
+    - For **Python** code, follow
+      [PEP 20](https://www.python.org/dev/peps/pep-0020/) and
+      [CEP-8](https://gist.github.com/reactive-firewall/b7ee98df9e636a51806e62ef9c4ab161)
+      standards.
+
+    # Documentation Review Instructions
+    - Verify that documentation and comments are clear and comprehensive.
+    - Verify that documentation and comments are free of spelling mistakes.
+
+    # Test Code Review Instructions
+    - Ensure that test code is automated, comprehensive, and follows testing best practices.
+    - Verify that all critical functionality is covered by tests.
+    - Ensure that test code follow
+      [CEP-8](https://gist.github.com/reactive-firewall/d840ee9990e65f302ce2a8d78ebe73f6)
+
+    # Misc.
+    - Confirm that the code meets the project's requirements and objectives.
+    - Confirm that copyright years are up-to date whenever a file is changed.
+  request_changes_workflow: false
+  high_level_summary: true
+  high_level_summary_placeholder: '@coderabbitai summary'
+  auto_title_placeholder: '@coderabbitai'
+  review_status: true
+  poem: false
+  collapse_walkthrough: false
+  sequence_diagrams: false
+  changed_files_summary: true
+  path_filters: ['!*.xc*/**', '!node_modules/**', '!dist/**', '!build/**', '!.git/**', '!venv/**', '!__pycache__/**']
+  path_instructions:
+    - path: README.md
+      instructions: >-
+        1. Consider the file 'README.md' the overview/introduction of the project.
+           Also consider the 'README.md' file the first place to look for project documentation.
+
+        2. When reviewing the file 'README.md' it should be linted with help
+           from the tools `markdownlint` and `languagetool`, pointing out any issues.
+
+        3. You may assume the file 'README.md' will contain GitHub flavor Markdown.
+    - path: '**/*.py'
+      instructions: >-
+        When reviewing Python code for this project:
+
+        1. Prioritize portability over clarity, especially when dealing with cross-Python compatibility. However, with the priority in mind, do still consider improvements to clarity when relevant.
+
+        2. As a general guideline, consider the code style advocated in the PEP 8 standard (excluding the use of spaces for indentation) and evaluate suggested changes for code style compliance.
+
+        3. As a style convention, consider the code style advocated in [CEP-8](https://gist.github.com/reactive-firewall/b7ee98df9e636a51806e62ef9c4ab161) and evaluate suggested changes for code style compliance.
+
+        4. As a general guideline, try to provide any relevant, official, and supporting documentation links to any tool's suggestions in review comments. This guideline is important for posterity.
+
+        5. As a general rule, undocumented function definitions and class definitions in the project's Python code are assumed incomplete. Please consider suggesting a short summary of the code for any of these incomplete definitions as docstrings when reviewing.
+    - path: cognee/tests/*
+      instructions: >-
+        When reviewing test code:
+
+        1. Prioritize portability over clarity, especially when dealing with cross-Python compatibility. However, with the priority in mind, do still consider improvements to clarity when relevant.
+
+        2. As a general guideline, consider the code style advocated in the PEP 8 standard (excluding the use of spaces for indentation) and evaluate suggested changes for code style compliance.
+
+        3. As a style convention, consider the code style advocated in [CEP-8](https://gist.github.com/reactive-firewall/b7ee98df9e636a51806e62ef9c4ab161) and evaluate suggested changes for code style compliance, pointing out any violations discovered.
+
+        4. As a general guideline, try to provide any relevant, official, and supporting documentation links to any tool's suggestions in review comments. This guideline is important for posterity.
+
+        5. As a project rule, Python source files with names prefixed by the string "test_" and located in the project's "tests" directory are the project's unit-testing code. It is safe, albeit a heuristic, to assume these are considered part of the project's minimal acceptance testing unless a justifying exception to this assumption is documented.
+
+        6. As a project rule, any files without extensions and with names prefixed by either the string "check_" or the string "test_", and located in the project's "tests" directory, are the project's non-unit test code. "Non-unit test" in this context refers to any type of testing other than unit testing, such as (but not limited to) functional testing, style linting, regression testing, etc. It can also be assumed that non-unit testing code is usually written as Bash shell scripts.
+    - path: requirements.txt
+      instructions: >-
+        * The project's own Python dependencies are recorded in 'requirements.txt' for production code.
+
+        * The project's testing-specific Python dependencies are recorded in 'tests/requirements.txt' and are used for testing the project.
+
+        * The project's documentation-specific Python dependencies are recorded in 'docs/requirements.txt' and are used only for generating Python-focused documentation for the project. 'docs/requirements.txt' may be absent if not applicable.
+
+        Consider these 'requirements.txt' files the records of truth regarding project dependencies.
+    - path: .github/**
+      instructions: >-
+        * When the project is hosted on GitHub: All GitHub-specific configurations, templates, and tools should be found in the '.github' directory tree.
+
+        * 'actionlint' erroneously generates false positives when dealing with GitHub's `${{ ... }}` syntax in conditionals.
+
+        * 'actionlint' erroneously generates incorrect solutions when suggesting the removal of valid `${{ ... }}` syntax.
+  abort_on_close: true
+  auto_review:
+    enabled: true
+    auto_incremental_review: true
+    ignore_title_keywords: []
+    labels: []
+    drafts: false
+    base_branches:
+      - dev
+      - main
+  tools:
+    shellcheck:
+      enabled: true
+    ruff:
+      enabled: true
+      configuration:
+        extend_select:
+          - E  # Pycodestyle errors (style issues)
+          - F  # PyFlakes codes (logical errors)
+          - W  # Pycodestyle warnings
+          - N  # PEP 8 naming conventions
+        ignore:
+          - W191
+          - W391
+          - E117
+          - D208
+        line_length: 100
+        dummy_variable_rgx: '^(_.*|junk|extra)$'  # Variables starting with '_' or named 'junk' or 'extras', are considered dummy variables
+    markdownlint:
+      enabled: true
+    yamllint:
+      enabled: true
+chat:
+  auto_reply: true

cognee-0.5.2/.env.example

@@ -0,0 +1,9 @@
+# Comma-separated list of allowed origins for CORS (leave empty to block all cross-origin requests)
+# Example:
+# CORS_ALLOWED_ORIGINS="https://yourdomain.com,https://another.com"
+# For local development, you might use:
+# CORS_ALLOWED_ORIGINS="http://localhost:3000"
+
+LLM_API_KEY="your-openai-api-key"
+LLM_MODEL="openai/gpt-4o-mini"
+LLM_PROVIDER="openai"

cognee-0.5.2/.env.template

@@ -0,0 +1,340 @@
+###############################################################################
+# 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"
+# Instructor's modes determine how structured data is requested from and extracted from LLM responses
+# You can change this type (i.e. mode) via this env variable
+# Each LLM has its own default value, e.g. gpt-5 models have "json_schema_mode"
+LLM_INSTRUCTOR_MODE=""
+
+EMBEDDING_PROVIDER="openai"
+EMBEDDING_MODEL="openai/text-embedding-3-large"
+EMBEDDING_ENDPOINT=""
+EMBEDDING_API_VERSION=""
+EMBEDDING_DIMENSIONS=3072
+EMBEDDING_MAX_TOKENS=8191
+EMBEDDING_BATCH_SIZE=36
+# 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-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
+
+# -- Advanced: Custom database connection arguments (optional) ---------------
+# Pass additional connection parameters as JSON. Useful for SSL, timeouts, etc.
+# Examples:
+#   For PostgreSQL with SSL:
+#     DATABASE_CONNECT_ARGS='{"sslmode": "require", "connect_timeout": 10}'
+#   For SQLite with custom timeout:
+#     DATABASE_CONNECT_ARGS='{"timeout": 60}'
+#DATABASE_CONNECT_ARGS='{}'
+
+################################################################################
+# 🕸️ Graph Database settings
+################################################################################
+
+# Default (local file-based)
+GRAPH_DATABASE_PROVIDER="kuzu"
+# Handler for multi-user access control mode, it handles how should the mapping/creation of separate DBs be handled per Cognee dataset
+# Currently Cognee supports "kuzu", "neo4j_aura_dev" on the core repository and "falkor_graph_local" from the community repository.
+GRAPH_DATASET_DATABASE_HANDLER="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=pleaseletmein
+
+################################################################################
+#  📐 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=
+# Handler for multi-user access control mode, it handles how should the mapping/creation of separate DBs be handled per Cognee dataset
+# Currently Cognee supports "lancedb" and "pgvector" as options on the core repo with "qdrant" and "falkor_vector_local" on the community repository.
+VECTOR_DATASET_DATABASE_HANDLER="lancedb"
+
+################################################################################
+# 🧩 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.
+
+################################################################################
+# 🌐 Translation Settings
+################################################################################
+
+# Translation provider: llm (uses configured LLM), google, or azure
+# "llm" uses whichever LLM is configured above (OpenAI, Azure, Ollama, Anthropic, etc.)
+# "google" and "azure" use dedicated translation APIs
+TRANSLATION_PROVIDER="llm"
+
+# Default target language for translations (ISO 639-1 code, e.g., en, es, fr, de)
+TARGET_LANGUAGE="en"
+
+# Minimum confidence threshold for language detection (0.0 to 1.0)
+CONFIDENCE_THRESHOLD=0.8
+
+# -- Google Translate settings (required if using google provider) -----------
+# GOOGLE_TRANSLATE_API_KEY="your-google-api-key"
+# GOOGLE_PROJECT_ID="your-google-project-id"
+
+# -- Azure Translator settings (required if using azure provider) ------------
+# AZURE_TRANSLATOR_KEY="your-azure-translator-key"
+# AZURE_TRANSLATOR_REGION="westeurope"
+# AZURE_TRANSLATOR_ENDPOINT="https://api.cognitive.microsofttranslator.com"
+
+# -- Performance settings ----------------------------------------------------
+# TRANSLATION_BATCH_SIZE=10
+# TRANSLATION_MAX_RETRIES=3
+# TRANSLATION_TIMEOUT_SECONDS=30
+
+################################################################################
+#  🔄  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 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 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="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
+
+
+########## 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-0.5.2/.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)'