### Create Response with OpenAI SDK

Source: https://llama-stack.readthedocs.io

Example of using the OpenAI Python SDK to create a response from a specified model with tool definitions. Ensure the `base_url` is set to your Llama Stack server endpoint.

```python
from openai import OpenAI


client = OpenAI(base_url="http://localhost:8321/v1", api_key="fake")
response = client.responses.create(
    model="llama-3.3-70b",
    input="Summarize this repository",
    tools=[{"type": "web_search"}],
)


```

--------------------------------

### Run Llama Stack Starter

Source: https://llama-stack.readthedocs.io

Use the `uvx` command to run the Llama Stack starter configuration. This command initializes and runs the starter stack.

```bash
uvx --from 'ogx[starter]' ogx stack run starter
```

--------------------------------

### Tools API

Source: https://llama-stack.readthedocs.io

Manages and configures tools for AI agents.

```APIDOC
## /v1/admin/tools

### Description
This endpoint provides administrative functions for managing and configuring tools available to AI agents.

### Method
GET, POST, PUT, DELETE

### Endpoint
/v1/admin/tools
```

--------------------------------

### Models API

Source: https://llama-stack.readthedocs.io

Retrieves information about available AI models.

```APIDOC
## /v1/models

### Description
This endpoint lists the available AI models that can be used for inference.

### Method
GET

### Endpoint
/v1/models
```

--------------------------------

### Chat Completions API

Source: https://llama-stack.readthedocs.io

Provides an interface for chat-based interactions with AI models.

```APIDOC
## /v1/chat/completions

### Description
This endpoint facilitates chat completions, enabling conversational interactions with AI models.

### Method
POST

### Endpoint
/v1/chat/completions
```

--------------------------------

### Responses API

Source: https://llama-stack.readthedocs.io

Handles AI responses, allowing users to create responses with specified models, inputs, and tools.

```APIDOC
## POST /v1/responses

### Description
This endpoint is used to generate responses from AI models. It supports various configurations including model selection, input prompts, and tool usage.

### Method
POST

### Endpoint
/v1/responses

### Request Body
- **model** (string) - Required - The AI model to use for generating the response.
- **input** (string) - Required - The input prompt or query for the AI model.
- **tools** (array) - Optional - A list of tools the AI model can use, e.g., `[{ "type": "web_search" }]`.

### Request Example
```json
{
  "model": "llama-3.3-70b",
  "input": "Summarize this repository",
  "tools": [
    {
      "type": "web_search"
    }
  ]
}
```

### Response
#### Success Response (200)
- **response** (string) - The generated response from the AI model.
```

--------------------------------

### Interactions API

Source: https://llama-stack.readthedocs.io

Provides an interface for interactions, potentially for specific providers like Google.

```APIDOC
## /v1alpha/interactions

### Description
This endpoint handles interactions, designed for compatibility with APIs such as Google's.

### Method
POST

### Endpoint
/v1alpha/interactions
```

--------------------------------

### Files API

Source: https://llama-stack.readthedocs.io

Handles file uploads and management.

```APIDOC
## /v1/files

### Description
This endpoint manages file operations, including uploading and retrieving files.

### Method
GET, POST, DELETE

### Endpoint
/v1/files
```

--------------------------------

### Batches API

Source: https://llama-stack.readthedocs.io

Manages batch operations.

```APIDOC
## /v1/batches

### Description
This endpoint is used for managing batch operations.

### Method
GET, POST

### Endpoint
/v1/batches
```

--------------------------------

### Connectors API

Source: https://llama-stack.readthedocs.io

Manages connectors for integrating with external services.

```APIDOC
## /v1/connectors

### Description
This endpoint manages connectors, facilitating integration with various external services.

### Method
GET, POST, PUT, DELETE

### Endpoint
/v1/connectors
```

--------------------------------

### Vector Stores API

Source: https://llama-stack.readthedocs.io

Manages vector stores for storing and retrieving vector embeddings.

```APIDOC
## /v1/vector_stores

### Description
This API manages vector stores, which are used for storing and querying vector embeddings.

### Method
GET, POST, PUT, DELETE

### Endpoint
/v1/vector_stores
```

--------------------------------

### Embeddings API

Source: https://llama-stack.readthedocs.io

Generates embeddings for given text inputs.

```APIDOC
## /v1/embeddings

### Description
This endpoint is used to generate vector embeddings for text data, useful for semantic search and other NLP tasks.

### Method
POST

### Endpoint
/v1/embeddings
```

--------------------------------

### Messages API

Source: https://llama-stack.readthedocs.io

Handles message-based interactions, potentially for specific providers like Anthropic.

```APIDOC
## /v1/messages

### Description
This endpoint manages message-based interactions, compatible with APIs like Anthropic's.

### Method
POST

### Endpoint
/v1/messages
```

--------------------------------

### Moderations API

Source: https://llama-stack.readthedocs.io

Performs content moderation checks.

```APIDOC
## /v1/moderations

### Description
This endpoint performs content moderation checks on provided text.

### Method
POST

### Endpoint
/v1/moderations
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.