Skip to content

armgit / camel

Public Imported from GitHub
0

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

5.3 KB
Raw Blame
<a id="camel.models.sglang_model"></a>

<a id="camel.models.sglang_model.SGLangModel"></a>

## SGLangModel

```python
class SGLangModel(BaseModelBackend):
```

SGLang service interface.

**Parameters:**

- **model_type** (Union[ModelType, str]): Model for which a backend is created.
- **model_config_dict** (Optional[Dict[str, Any]], optional): A dictionary that will be fed into:obj:`openai.ChatCompletion.create()`. If :obj:`None`, :obj:`SGLangConfig().as_dict()` will be used. (default: :obj:`None`)
- **api_key** (Optional[str], optional): The API key for authenticating with the model service. SGLang doesn't need API key, it would be ignored if set. (default: :obj:`None`)
- **url** (Optional[str], optional): The url to the model service. If not provided, :obj:`"http://127.0.0.1:30000/v1"` will be used. (default: :obj:`None`)
- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)
- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)
- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`)
- **client** (Optional[Any], optional): A custom synchronous OpenAI-compatible client instance. If provided, this client will be used instead of creating a new one. Note: When using custom clients with SGLang, server auto-start features will be disabled. (default: :obj:`None`)
- **async_client** (Optional[Any], optional): A custom asynchronous OpenAI-compatible client instance. If provided, this client will be used instead of creating a new one. (default: :obj:`None`) **kwargs (Any): Additional arguments to pass to the client initialization. Ignored if custom clients are provided.
- **Reference**: https://sgl-project.github.io/backend/openai_api_completions. html

<a id="camel.models.sglang_model.SGLangModel.__init__"></a>

### __init__

```python
def __init__(
    self,
    model_type: Union[ModelType, str],
    model_config_dict: Optional[Dict[str, Any]] = None,
    api_key: Optional[str] = None,
    url: Optional[str] = None,
    token_counter: Optional[BaseTokenCounter] = None,
    timeout: Optional[float] = None,
    max_retries: int = 3,
    client: Optional[Any] = None,
    async_client: Optional[Any] = None,
    **kwargs: Any
):
```

<a id="camel.models.sglang_model.SGLangModel._start_server"></a>

### _start_server

```python
def _start_server(self):
```

<a id="camel.models.sglang_model.SGLangModel._ensure_server_running"></a>

### _ensure_server_running

```python
def _ensure_server_running(self):
```

Ensures that the server is running. If not, starts the server.

<a id="camel.models.sglang_model.SGLangModel._monitor_inactivity"></a>

### _monitor_inactivity

```python
def _monitor_inactivity(self):
```

Monitor whether the server process has been inactive for over 10
minutes.

<a id="camel.models.sglang_model.SGLangModel.token_counter"></a>

### token_counter

```python
def token_counter(self):
```

**Returns:**

  BaseTokenCounter: The token counter following the model's
tokenization style.

<a id="camel.models.sglang_model.SGLangModel._run"></a>

### _run

```python
def _run(
    self,
    messages: List[OpenAIMessage],
    response_format: Optional[Type[BaseModel]] = None,
    tools: Optional[List[Dict[str, Any]]] = None
):
```

Runs inference of OpenAI chat completion.

**Parameters:**

- **messages** (List[OpenAIMessage]): Message list with the chat history in OpenAI API format.

**Returns:**

  Union[ChatCompletion, Stream[ChatCompletionChunk]]:
`ChatCompletion` in the non-stream mode, or
`Stream[ChatCompletionChunk]` in the stream mode.

<a id="camel.models.sglang_model.SGLangModel.stream"></a>

### stream

```python
def stream(self):
```

**Returns:**

  bool: Whether the model is in stream mode.

<a id="camel.models.sglang_model.SGLangModel.__del__"></a>

### __del__

```python
def __del__(self):
```

Properly clean up resources when the model is destroyed.

<a id="camel.models.sglang_model.SGLangModel.cleanup"></a>

### cleanup

```python
def cleanup(self):
```

Terminate the server process and clean up resources.

<a id="camel.models.sglang_model._terminate_process"></a>

## _terminate_process

```python
def _terminate_process(process):
```

<a id="camel.models.sglang_model._kill_process_tree"></a>

## _kill_process_tree

```python
def _kill_process_tree(
    parent_pid,
    include_parent: bool = True,
    skip_pid: Optional[int] = None
):
```

Kill the process and all its child processes.

<a id="camel.models.sglang_model._execute_shell_command"></a>

## _execute_shell_command

```python
def _execute_shell_command(command: str):
```

Execute a shell command and return the process handle

**Parameters:**

- **command**: Shell command as a string (can include \\ line continuations)

**Returns:**

  subprocess.Popen: Process handle

<a id="camel.models.sglang_model._wait_for_server"></a>

## _wait_for_server

```python
def _wait_for_server(base_url: str, timeout: Optional[float] = 30):
```

Wait for the server to be ready by polling the /v1/models endpoint.

**Parameters:**

- **base_url** (str): The base URL of the server
- **timeout** (Optional[float]): Maximum time to wait in seconds. (default: :obj:`30`)