Connect cognee to model providers, databases, storage services, and development tools. Guides configuration of language models and embeddings, the numerical representations used for search, including the separate settings each requires.
中文简介正在准备中。当前显示英语简介。
Use when the user wants to connect cognee to external services — switching LLM or embedding providers (OpenAI, Azure, Gemini, Anthropic, Ollama, OpenRouter), changing databases (Postgres, PGVector, Neo4j, Neptune, Turso), S3 storage, or the MCP server for IDE integration.
安装前可以查看交给 AI 代理的指令内容。
All integration config is environment variables (.env). The authoritative,
always-current list with commented examples is .env.template at the repo
root — check it before inventing variable names. Install the matching extra
before switching a backend (e.g. pip install cognee[postgres]).
Default is OpenAI (LLM_API_KEY is all you need). To switch, set
LLM_PROVIDER, LLM_MODEL, LLM_API_KEY, and (where relevant)
LLM_ENDPOINT / LLM_API_VERSION:
LLM_PROVIDER=azure, LLM_MODEL=azure/gpt-4o-mini, endpoint + api version required.LLM_PROVIDER=gemini, LLM_MODEL=gemini/gemini-2.0-flash-exp.cognee[anthropic]): LLM_PROVIDER=anthropic, model e.g. claude-3-5-sonnet-20241022.cognee[ollama]): LLM_PROVIDER=ollama, LLM_ENDPOINT=http://localhost:11434/v1, and set the embedding block + HUGGINGFACE_TOKENIZER too.LLM_PROVIDER=custom with the provider's OpenAI-compatible endpoint.cognee[aws]): LLM_PROVIDER=bedrock + AWS credentials/region.The classic trap: LLM and embeddings are configured independently
(EMBEDDING_PROVIDER, EMBEDDING_MODEL, EMBEDDING_ENDPOINT,
EMBEDDING_API_KEY). Configuring only one leaves the other on OpenAI —
either keep a valid OpenAI key or configure both.
DB_PROVIDER): sqlite (default) or postgres
(cognee[postgres]; host/port/user/password/name via DB_* vars).VECTOR_DB_PROVIDER): lancedb (default), pgvector
(cognee[postgres], needs VECTOR_DB_URL), neptune_analytics
(cognee[neptune]), turso (cognee[turso]). Anything else (ChromaDB,
Qdrant, Weaviate, Milvus, …) lives in community adapters — install from
https://github.com/topoteretes/cognee-community and register with
use_vector_adapter before use; setting VECTOR_DB_PROVIDER alone raises
"Unsupported vector database provider".GRAPH_DATABASE_PROVIDER): ladybug (default), neo4j
(cognee[neo4j], bolt URL + credentials), neptune (cognee[neptune]),
ladybug-remote, postgres (no raw Cypher / natural-language search).The repo docker-compose.yml ships ready-to-use postgres (pgvector) and
neo4j profiles with matching default credentials. From a container, reach
host services with DB_HOST=host.docker.internal.
cognee[aws]): STORAGE_BACKEND=s3 + bucket/credentials,
and point DATA_ROOT_DIRECTORY/SYSTEM_ROOT_DIRECTORY at s3:// paths.CACHE_BACKEND = sqlite (default) | postgres | redis | fs | tapes.ONTOLOGY_FILE_PATH to an OWL file, resolver/matching via
ONTOLOGY_RESOLVER / MATCHING_STRATEGY.docker compose --profile mcp up starts the MCP server on port 8001
(Streamable HTTP at http://localhost:8001/mcp), built from cognee-mcp/. Point Cursor / Claude Desktop /
Claude Code at it to use cognee memory from the IDE. Configure its DB_* env
to match the main service so both see the same data.
Embeddings from different models are not comparable — after switching the
embedding provider or model, reset local state (cognee-cli forget --all or
await cognee.forget(everything=True)) and re-ingest with remember().
To drop just the graph and vectors while keeping the ingested files, use
await cognee.forget(dataset="my_project", memory_only=True) — the dataset can
then be rebuilt under the new embedding model without re-uploading anything.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Operate cognee from the terminal to store, retrieve, update, and remove information. Covers dataset and configuration management, ingestion cost estimates, session history access, and commands for inspecting or applying database migrations.
中文简介正在准备中。当前显示英语简介。
Connect cognee to additional databases and data sources through community packages. The skill covers installing and registering adapters, importing data through connectors, configuring monitoring, and developing extension packages with examples and tests.
中文简介正在准备中。当前显示英语简介。
Define custom entities and relationships in cognee, a memory system for AI applications. This skill guides model design, identity matching, searchable fields, and troubleshooting when entities are duplicated or relationships are missing.
中文简介正在准备中。当前显示英语简介。
Build custom cognee processing by chaining Python tasks, defining data types, and saving results to graph and vector databases. Use it to enrich existing data, inspect run status, and troubleshoot how tasks pass data.
中文简介正在准备中。当前显示英语简介。
Run cognee in Docker, starting with a prebuilt image for local document ingestion and questions. It also covers Docker Compose profiles for adding the UI, MCP server, Postgres, and Neo4j, plus persistent data storage.
中文简介正在准备中。当前显示英语简介。
Find and remove stored content from cognee using its SDK, HTTP API, or CLI. Inspect documents before deletion, choose document or dataset removal, or keep raw files while clearing derived graph relationships and search vectors.
中文简介正在准备中。当前显示英语简介。