mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 10:54:19 +00:00

Francisco Arceo 19ae4b35d9

docs: Adding Provider sections to docs (#1195 )

# What does this PR do?
Adding Provider sections to docs (some of these will be empty and need
updating).


This PR is still a draft while I seek feedback from other contributors.
I opened it to make the structure visible in the linked GitHub Issue.

# Closes https://github.com/meta-llama/llama-stack/issues/1189

- Providers Overview Page
![Screenshot 2025-02-21 at 12 15
09 PM](https://github.com/user-attachments/assets/e83e5a17-0d96-4de0-8251-68161799a054)

- SQLite-Vec specific page
![Screenshot 2025-02-21 at 12 15
34 PM](https://github.com/user-attachments/assets/14773900-fc8f-49e9-832a-b060b7ca010a)

## Test Plan
N/A

[//]: # (## Documentation)

---------

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

2025-02-22 11:59:34 -08:00

901 B

Raw Blame History

orphan
true

Chroma

Chroma is an inline and remote vector database provider for Llama Stack. It allows you to store and query vectors directly within a Chroma database. That means you're not limited to storing vectors in memory or in a separate service.

Features

Chroma supports:

Store embeddings and their metadata
Vector search
Full-text search
Document storage
Metadata filtering
Multi-modal retrieval

Usage

To use Chrome in your Llama Stack project, follow these steps:

Install the necessary dependencies.
Configure your Llama Stack project to use chroma.
Start storing and querying vectors.

Installation

You can install chroma using pip:

pip install chromadb

Documentation

See Chroma's documentation for more details about Chroma in general.

901 B Raw Blame History