centersl/open-webui-docs
1
0
Fork 0
mirror of https://github.com/open-webui/docs.git synced 2026-03-26 13:18:42 +07:00
Code Issues Packages Projects Releases Wiki Activity

Add missing provider tabs: Llama.cpp, Azure OpenAI, LiteLLM

Browse Source 
- Cloud Providers: Added Azure OpenAI tab (with provider type toggle
  instructions and link to EntraID tutorial) and LiteLLM tab
- Local Servers: Added Llama.cpp tab with quick start command and
  link to the dedicated Llama.cpp guide

https://claude.ai/code/session_01TPoquFdHG6dZxRrZ4Jormh
This commit is contained in:
Claude
2026-02-16 13:25:16 +00:00
parent 9830bc151b
commit a867a681b7
1 changed files with 66 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

67
docs/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible.mdx
View File

@@ -222,13 +222,78 @@ If running Open WebUI in Docker and your model server is on the host machine, re
| **API Key** | `bedrock` (default BAG key — change via `DEFAULT_API_KEYS` in BAG config) |
| **Model IDs** | Auto-detected from your enabled Bedrock models |
</TabItem>
<TabItem value="azure" label="Azure OpenAI">
**Azure OpenAI** provides enterprise-grade OpenAI hosting through Microsoft Azure.
To add an Azure OpenAI connection, you need to **switch the provider type** in the connection dialog:
1. In the connection form, find the **Provider Type** button (it says **OpenAI** by default).
2. **Click it to toggle** it to **Azure OpenAI**.
3. Fill in the settings below.
| Setting | Value |
|---|---|
| **Provider Type** | Click to switch to **Azure OpenAI** |
| **URL** | Your Azure endpoint (e.g., `https://my-resource.openai.azure.com`) |
| **API Version** | e.g., `2024-02-15-preview` |
| **API Key** | Your Azure API Key |
| **Model IDs** | **Required** — add your specific Deployment Names (e.g., `my-gpt4-deployment`) |
:::info
Azure OpenAI uses **deployment names** as model IDs, not standard OpenAI model names. You must add your deployment names to the Model IDs allowlist.
:::
For advanced keyless authentication using Azure Entra ID (RBAC, Workload Identity, Managed Identity), see the [Azure OpenAI with EntraID](/tutorials/integrations/llm-providers/azure-openai) tutorial.
</TabItem>
<TabItem value="litellm" label="LiteLLM">
**LiteLLM** is a proxy server that provides a unified OpenAI-compatible API across 100+ LLM providers (Anthropic, Google, Azure, AWS Bedrock, Cohere, and more). It translates between provider-specific APIs and the OpenAI standard.
| Setting | Value |
|---|---|
| **URL** | `http://localhost:4000/v1` (default LiteLLM proxy port) |
| **API Key** | Your LiteLLM proxy key (if configured) |
| **Model IDs** | Auto-detected from your LiteLLM configuration |
**Quick setup:**
```bash
pip install litellm
litellm --model gpt-4 --port 4000
```
For production deployments, configure models via `litellm_config.yaml`. See the [LiteLLM docs](https://docs.litellm.ai/) for details.
:::tip
LiteLLM is useful as a **universal bridge** when you want to use a provider that doesn't natively support the OpenAI API standard, or when you want to load-balance across multiple providers.
:::
</TabItem>
</Tabs>
### Local Servers
<Tabs>
<TabItem value="lemonade" label="Lemonade" default>
<TabItem value="llamacpp" label="Llama.cpp" default>
**Llama.cpp** runs efficient, quantized GGUF models locally with an OpenAI-compatible API server. See the dedicated **[Llama.cpp guide](/getting-started/quick-start/connect-a-provider/starting-with-llama-cpp)** for full setup instructions (installation, model download, server startup).
| Setting | Value |
|---|---|
| **URL** | `http://localhost:10000/v1` (or your configured port) |
| **API Key** | Leave blank |
**Quick start:**
```bash
./llama-server --model /path/to/model.gguf --port 10000 --ctx-size 1024 --n-gpu-layers 40
```
</TabItem>
<TabItem value="lemonade" label="Lemonade">
**Lemonade** is a plug-and-play ONNX-based OpenAI-compatible server for Windows.