> This page is for version v1.3 (default).
> For other versions, use one of these documentation indexes:
> - v1.3 (default): https://docs.twelvelabs.io/v1.3/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.twelvelabs.io/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.twelvelabs.io/_mcp/server.

# Chroma - Multimodal RAG: Chat with Videos

> Build RAG-based video Q&A by combining the TwelveLabs Embed API with Chroma.

![](/_fern-img/ecce9b42bf7a1aaf54f0a5cfb933fa331897ea988b2425df2fd314695e5a1f97.webp)

**Summary**: This integration combines TwelveLabs' [Embed API](/docs/guides/create-embeddings) with [Chroma’s Vector Database](https://www.trychroma.com/) to enable Retrieval-Augmented Generation (RAG) based Q\&A on videos.

**Description**: The integration leverages TwelveLabs' contextual embeddings and Chroma’s efficient vector storage to power a chat application that extracts precise text answers from unstructured video content.

**Code explanation**: Our blog post, [Multimodal RAG: Chat with Videos Using TwelveLabs and Chroma](https://www.twelvelabs.io/blog/twelve-labs-and-chroma), provides a detailed walkthrough of this integration process.

**Colab notebook**: [TwelveLabs\_Chroma\_Chat\_with\_video\_Colab](https://drive.google.com/file/d/1xbW2Ycen4uFaIX-8P8SM8qldgSoBwPVy/view?usp=sharing)