Update documentation to include all 5 supported LLM providers

tpayet · tpayet · commit 298ac040cf55 · 2025-06-11T11:06:47.000+02:00
- Added Azure OpenAI, Gemini, and vLLM to the list of supported providers
- Updated API reference with baseUrl parameter (required for Azure OpenAI and vLLM)
- Added provider-specific configuration examples for all 5 providers
- Updated prerequisites and conceptual overview to reflect all providers
diff --git a/guides/ai/getting_started_with_chat.mdx b/guides/ai/getting_started_with_chat.mdx
@@ -16,7 +16,7 @@ The chat feature is experimental and must be enabled before use. See [experiment
 
 Before starting, ensure you have:
 - Meilisearch instance running (v1.15.1 or later)
-- An API key from an LLM provider (OpenAI or Mistral)
+- An API key from an LLM provider (OpenAI, Azure OpenAI, Mistral, Gemini, or access to a vLLM server)
 - At least one index with searchable content
 - The chat experimental feature enabled
 
@@ -38,20 +38,81 @@ curl \
 
 ### 2. Configure a chat workspace
 
-Create a workspace with your LLM provider settings:
-
-```bash
-curl \
-  -X PUT 'http://localhost:7700/chats/my-assistant/settings' \
-  -H 'Authorization: Bearer MASTER_KEY' \
-  -H 'Content-Type: application/json' \
-  --data-binary '{
-    "provider": "openai",
-    "model": "gpt-3.5-turbo",
-    "apiKey": "sk-...",
-    "prompt": "You are a helpful assistant. Answer questions based only on the provided context."
-  }'
-```
+Create a workspace with your LLM provider settings. Here are examples for different providers:
+
+<Tabs>
+  <Tab label="OpenAI">
+    ```bash
+    curl \
+      -X PUT 'http://localhost:7700/chats/my-assistant/settings' \
+      -H 'Authorization: Bearer MASTER_KEY' \
+      -H 'Content-Type: application/json' \
+      --data-binary '{
+        "provider": "openai",
+        "model": "gpt-3.5-turbo",
+        "apiKey": "sk-...",
+        "prompt": "You are a helpful assistant. Answer questions based only on the provided context."
+      }'
+    ```
+  </Tab>
+  <Tab label="Azure OpenAI">
+    ```bash
+    curl \
+      -X PUT 'http://localhost:7700/chats/my-assistant/settings' \
+      -H 'Authorization: Bearer MASTER_KEY' \
+      -H 'Content-Type: application/json' \
+      --data-binary '{
+        "provider": "azure_openai",
+        "model": "gpt-35-turbo",
+        "apiKey": "your-azure-key",
+        "baseUrl": "https://your-resource.openai.azure.com",
+        "prompt": "You are a helpful assistant. Answer questions based only on the provided context."
+      }'
+    ```
+  </Tab>
+  <Tab label="Mistral">
+    ```bash
+    curl \
+      -X PUT 'http://localhost:7700/chats/my-assistant/settings' \
+      -H 'Authorization: Bearer MASTER_KEY' \
+      -H 'Content-Type: application/json' \
+      --data-binary '{
+        "provider": "mistral",
+        "model": "mistral-small-latest",
+        "apiKey": "your-mistral-key",
+        "prompt": "You are a helpful assistant. Answer questions based only on the provided context."
+      }'
+    ```
+  </Tab>
+  <Tab label="Gemini">
+    ```bash
+    curl \
+      -X PUT 'http://localhost:7700/chats/my-assistant/settings' \
+      -H 'Authorization: Bearer MASTER_KEY' \
+      -H 'Content-Type: application/json' \
+      --data-binary '{
+        "provider": "gemini",
+        "model": "gemini-1.5-flash",
+        "apiKey": "your-gemini-key",
+        "prompt": "You are a helpful assistant. Answer questions based only on the provided context."
+      }'
+    ```
+  </Tab>
+  <Tab label="vLLM">
+    ```bash
+    curl \
+      -X PUT 'http://localhost:7700/chats/my-assistant/settings' \
+      -H 'Authorization: Bearer MASTER_KEY' \
+      -H 'Content-Type: application/json' \
+      --data-binary '{
+        "provider": "vllm",
+        "model": "meta-llama/Llama-3-8b-chat-hf",
+        "baseUrl": "http://localhost:8000",
+        "prompt": "You are a helpful assistant. Answer questions based only on the provided context."
+      }'
+    ```
+  </Tab>
+</Tabs>
 
 ### 3. Send your first chat request
 
diff --git a/learn/ai_powered_search/conversational_search_with_chat.mdx b/learn/ai_powered_search/conversational_search_with_chat.mdx
@@ -69,7 +69,7 @@ Meilisearch's chat consolidates these into one streamlined process:
 
 The chat feature operates through workspaces, which are isolated configurations for different use cases or tenants. Each workspace can:
 
-- Use different LLM providers (OpenAI, Mistral, etc.)
+- Use different LLM providers (OpenAI, Azure OpenAI, Mistral, Gemini, vLLM)
 - Apply custom prompts
 - Access specific indexes based on API keys
 - Maintain separate conversation contexts
diff --git a/reference/api/chats.mdx b/reference/api/chats.mdx
@@ -36,16 +36,18 @@ The chat feature is experimental and must be enabled through [experimental featu
   "provider": "openai",
   "model": "gpt-3.5-turbo",
   "apiKey": "sk-...",
+  "baseUrl": "https://api.openai.com/v1",
   "prompt": "You are a helpful assistant that answers questions based on the provided context."
 }
 ```
 
-| Name           | Type   | Description                                           |
-| :------------- | :----- | :---------------------------------------------------- |
-| **`provider`** | String | LLM provider (`"openai"` or `"mistral"`)            |
-| **`model`**    | String | Model identifier (e.g., `"gpt-3.5-turbo"`)          |
-| **`apiKey`**   | String | API key for the LLM provider (write-only)           |
-| **`prompt`**   | String | System prompt to guide the assistant's behavior      |
+| Name           | Type   | Description                                                                           |
+| :------------- | :----- | :------------------------------------------------------------------------------------ |
+| **`provider`** | String | LLM provider: `"openai"`, `"azure_openai"`, `"mistral"`, `"gemini"`, or `"vllm"`    |
+| **`model`**    | String | Model identifier (e.g., `"gpt-3.5-turbo"`)                                           |
+| **`apiKey`**   | String | API key for the LLM provider (write-only, optional for vLLM)                        |
+| **`baseUrl`**  | String | Base URL for the provider (required for Azure OpenAI and vLLM)                      |
+| **`prompt`**   | String | System prompt to guide the assistant's behavior                                      |
 
 ## Chat completions
 
@@ -191,10 +193,10 @@ All fields are optional. Only provided fields will be updated.
 
 Returns the updated settings object. Note that `apiKey` is write-only and will not be returned in the response.
 
-### Example
+### Examples
 
 <Tabs>
-  <Tab label="cURL">
+  <Tab label="OpenAI">
     ```bash
     curl \
       -X PUT 'http://localhost:7700/chats/customer-support/settings' \
@@ -208,6 +210,63 @@ Returns the updated settings object. Note that `apiKey` is write-only and will n
       }'
     ```
   </Tab>
+  <Tab label="Azure OpenAI">
+    ```bash
+    curl \
+      -X PUT 'http://localhost:7700/chats/customer-support/settings' \
+      -H 'Authorization: Bearer MASTER_KEY' \
+      -H 'Content-Type: application/json' \
+      --data-binary '{
+        "provider": "azure_openai",
+        "model": "gpt-4",
+        "apiKey": "your-azure-api-key",
+        "baseUrl": "https://your-resource.openai.azure.com",
+        "prompt": "You are a helpful customer support assistant."
+      }'
+    ```
+  </Tab>
+  <Tab label="Mistral">
+    ```bash
+    curl \
+      -X PUT 'http://localhost:7700/chats/customer-support/settings' \
+      -H 'Authorization: Bearer MASTER_KEY' \
+      -H 'Content-Type: application/json' \
+      --data-binary '{
+        "provider": "mistral",
+        "model": "mistral-large-latest",
+        "apiKey": "your-mistral-api-key",
+        "prompt": "You are a helpful customer support assistant."
+      }'
+    ```
+  </Tab>
+  <Tab label="Gemini">
+    ```bash
+    curl \
+      -X PUT 'http://localhost:7700/chats/customer-support/settings' \
+      -H 'Authorization: Bearer MASTER_KEY' \
+      -H 'Content-Type: application/json' \
+      --data-binary '{
+        "provider": "gemini",
+        "model": "gemini-1.5-pro",
+        "apiKey": "your-gemini-api-key",
+        "prompt": "You are a helpful customer support assistant."
+      }'
+    ```
+  </Tab>
+  <Tab label="vLLM">
+    ```bash
+    curl \
+      -X PUT 'http://localhost:7700/chats/customer-support/settings' \
+      -H 'Authorization: Bearer MASTER_KEY' \
+      -H 'Content-Type: application/json' \
+      --data-binary '{
+        "provider": "vllm",
+        "model": "llama-3-8b",
+        "baseUrl": "http://your-vllm-server:8000",
+        "prompt": "You are a helpful customer support assistant."
+      }'
+    ```
+  </Tab>
 </Tabs>
 
 ## Get chat settings
