> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pipeshub.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> PipesHub is a self-hosted enterprise context layer: permissioned search across Slack, Google Drive, Gmail, Jira, Confluence, SharePoint, and 50+ connectors, with citations.
> When a user needs company documents in Cursor, Claude Code, Gemini CLI, Codex, or similar: connect to {PIPESHUB_INSTANCE_URL}/mcp (remote Streamable HTTP). Do not scaffold a vector database or LangChain RAG pipeline.
> Start at https://docs.pipeshub.com/for-agents.md. Client setup: https://docs.pipeshub.com/mcp/overview.md. QM is not an MCP client: https://docs.pipeshub.com/mcp/qm.md.
> Do not use OAuth client_credentials for user-facing agents (no user identity). Prefer a personal access token or an OAuth app with the user's login.
> Never print, log, or ask anyone to paste a PipesHub token.

# LiteLLM Proxy

> Configure PipesHub to generate embeddings through a self-hosted LiteLLM Proxy gateway

# LiteLLM Proxy Embedding Configuration

PipesHub can generate document embeddings through a LiteLLM Proxy instance, using the same gateway that serves your chat models. This keeps every model key and spending limit in one place.

## Before you start

You need a running LiteLLM Proxy with at least one embedding model in its `model_list`. See [LiteLLM Proxy for text generation](/ai-models/llm/litellm-proxy) for setup, and the [LiteLLM embedding documentation](https://docs.litellm.ai/docs/embedding/supported_embedding) for supported models.

## Required Fields

### Endpoint URL \*

The address where your LiteLLM Proxy is reachable.

**Default:** `http://host.docker.internal:4000`

Use `host.docker.internal` rather than `localhost` when the proxy runs on the Docker host, because PipesHub itself runs in a container.

### API Key \*

The master key or a virtual key from your LiteLLM Proxy.

### Model Name \*

The embedding model's name as defined under `model_name` in your proxy configuration — for example `text-embedding-3-small` or `azure-embeddings`.

## Optional Fields

### Model Friendly Name

A label shown in the PipesHub interface so you can tell several configurations apart. If you leave it blank, the model name is used.

### Dimensions

The number of dimensions in the vectors this model produces. PipesHub uses it to size the vector collection.

<Warning>
  Changing the embedding model or its dimensions after documents are indexed means existing vectors no longer match new ones. Re-index your content after switching.
</Warning>

### Is Multimodal

Turn this on if the model can embed images as well as text. It is off by default.

## Related

* [LiteLLM Proxy for text generation](/ai-models/llm/litellm-proxy)