Open-source embedding database for local, self-hosted, and Chroma Cloud vector search
Chroma documents an open-source embedding database at docs.trychroma.com for storing and querying vectors, metadata, and full-text fields in Python and JavaScript clients. Official guides cover ephemeral in-memory collections, persistent local storage, self-hosted server deployments, and Chroma Cloud at trychroma.com with authentication tokens. The docs describe collection CRUD, `add`/`query`/`get`/`update`/`delete` APIs, embedding functions (default and third-party), hybrid search, and multitenancy patterns for RAG and agent memory workloads per the documentation index.
Use cases
- Prototyping RAG pipelines with local persistent collections before cloud scale-up
- Storing agent conversation memory with metadata filters for per-user namespaces
- Running embedding search in CI with ephemeral in-memory Chroma clients
- Pairing Chroma Cloud with production agents that need managed vector storage
- Teaching vector DB concepts without standing up a full Postgres/pgvector cluster
Key features
- Local persistent and in-memory clients documented in docs.trychroma.com quickstarts
- Collection APIs for vector, metadata, and document storage with filtering
- Embedding function integrations (default, Cohere, OpenAI, Jina, Voyage, Roboflow) per Chroma docs
- Self-hosted HTTP server and Chroma Cloud hosted option with API keys
- Hybrid and full-text search capabilities described for agent memory and RAG catalogs
Who Is It For?
- ML engineers building RAG or recommendation prototypes
- Agent developers needing lightweight persistent memory stores
- Teams evaluating open-source vector DBs before managed cloud migration
Frequently Asked Questions
- Is Chroma only a Python library?
- No—Chroma documents Python and JavaScript/TypeScript clients plus HTTP server and Chroma Cloud APIs at docs.trychroma.com.
- How do agents connect to Chroma?
- Chroma documents an official MCP server (chroma-mcp via uvx) and HTTP clients for self-hosted or Cloud deployments—see docs.trychroma.com integrations.
- Where are pricing details?
- Self-hosted Chroma is open source; Chroma Cloud plan tiers are published at trychroma.com/pricing.
Related
Related
3 Indexed items
Milvus
Milvus documents a high-performance vector database at milvus.io/docs for storing, indexing, and searching embedding vectors with metadata filtering and hybrid search. Deployment options include Milvus Lite (`pip install pymilvus` for notebooks/edge), Milvus Standalone (single Docker image), and Milvus Distributed on Kubernetes per milvus.io/docs/v2.6.x/install-overview. Official SDKs include PyMilvus, Go, Java, Node.js, and C#; Zilliz Cloud offers managed Milvus. Architecture separates access, coordinator, worker, and storage layers with object storage backends (MinIO, S3, Azure Blob) per milvus.io/docs/architecture_overview.
Weaviate
Weaviate documents an open-source vector database at docs.weaviate.io/weaviate for storing objects and vector embeddings with semantic, keyword, and hybrid search, RAG, reranking, and agent workflows. The ecosystem includes self-hosted Docker/Kubernetes installs, Weaviate Cloud (console.weaviate.cloud), Query Agent, and Weaviate Embeddings for managed inference. Client libraries include Python (`weaviate-client` v4, requires Weaviate 1.23.7+), TypeScript, Go, and Java with REST, gRPC, and GraphQL APIs per the official documentation.
LanceDB
LanceDB documents a multimodal lakehouse for AI at docs.lancedb.com, built on the open-source Lance columnar format for storing vectors, metadata, raw bytes, and embeddings in unified tables. LanceDB OSS is an embedded library with Python, TypeScript, and Rust SDKs for local development; LanceDB Enterprise is a distributed managed lakehouse for search, curation, feature engineering, and training workflows per docs.lancedb.com. Features include vector/semantic search, BM25 full-text search, hybrid search with SQL filters, versioning, and cloud object-store integration (S3, GCS, Azure).