Loading page
Loading page
AI · Pinecone alternative
Store embeddings and run similarity search for your AI apps with an open-source vector database and a simple API.
Chroma is an open-source embedding database for AI applications. You store pieces of text with their embeddings and metadata. Later you send a query, and Chroma returns the most similar pieces. This is the core step in retrieval-augmented generation, or RAG.
The API is small: create a collection, add documents, query, and get by id. This template runs Chroma as a server with persistent storage, so your app talks to it over HTTP.
Chroma suits developers building chatbots, semantic search and agents that need memory. It is a common first choice because the API is easy to learn and works the same in a notebook and on a server.
Hosted vector databases charge by storage, reads and writes, and your documents sit on their servers. A self-hosted Chroma keeps your embeddings and source text in your own service, and there is no usage meter.
The trade-off is that you run and secure it. The server API has no login in this template, so do not leave it open to the internet with private data. Large collections need memory and disk. You also back up the data volume and update the image yourself.
Containers: chromadb/chroma:1.5.6
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose Chroma, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the Chroma setup screen.