Unlike legacy search systems, Chroma is a database you'll want to be on-call for.

Chroma Chroma is the open-source AI application database. Chroma makes it easy to build LLM apps by making knowledge, facts, and skills pluggable for LLMs. New to Chroma? Check out …

Getting Started Chroma is an AI-native open-source vector database. It comes with everything you need to get started built-in, and runs on your machine.

Chroma Cloud enables fast, scalable, & serverless vector, full-text, and metadata search across terabytes of data backed by Chroma's Apache 2.0 distributed database.

Chroma will use the collection's embedding function to embed your text queries, and use the output to run a vector similarity search against your collection. Instead of provided query_texts, …

Chroma’s data model is designed to balance simplicity, flexibility, and scalability. It introduces a few core abstractions— Tenants, Databases, and Collections —that allow you to organize, …

Vector similarity, full-text and metadata search. Maintains a combination of in-memory and on-disk indexes, and coordinates with the Log to serve consistent results.

Chroma provides lightweight wrappers around popular embedding providers, making it easy to use them in your apps. You can set an embedding function when you create a Chroma …

In this mode, the Chroma client connects to a Chroma server running in a separate process. This means that you can deploy single-node Chroma to a Docker container, or a machine hosted …

Chroma is instrumented with OpenTelemetry hooks for observability. OpenTelemetry traces allow you to understand how requests flow through the system and quickly identify bottlenecks.