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

# langchain.Tracer

> Tracing and instrumentation utilities for Langchain integration.

[View module source on GitHub](https://github.com/maximhq/maxim-py/blob/main/maxim/logger/langchain/tracer.py)

## [MaximLangchainTracer](/sdk/python/references/logger/langchain/tracer)

```python theme={null}
class MaximLangchainTracer(BaseCallbackHandler)
```

A callback handler that logs langchain outputs to [Maxim](/sdk/python/references/maxim) logger

**Arguments**:

| Name     | Description                                                                                                                                                    |
| -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `logger` | \[[Logger](/sdk/python/references/logger/logger)]\(/sdk/python/references/logger/logger): [Maxim](/sdk/python/references/maxim) Logger instance to log outputs |

#### \_\_init\_\_

```python theme={null}
def __init__(logger: Logger,
             metadata: Optional[Dict[str, Any]] = None,
             eval_config: Optional[Dict[str, List[str]]] = None) -> None
```

Initializes the Langchain Tracer

**Arguments**:

| Name     | Description                                                                                                                                                    |
| -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `logger` | \[[Logger](/sdk/python/references/logger/logger)]\(/sdk/python/references/logger/logger): [Maxim](/sdk/python/references/maxim) Logger instance to log outputs |

#### on\_llm\_start

```python theme={null}
def on_llm_start(serialized: dict[str, Any],
                 prompts: list[str],
                 *,
                 run_id: UUID,
                 parent_run_id: Optional[UUID] = None,
                 tags: Optional[list[str]] = None,
                 metadata: Optional[dict[str, Any]] = None,
                 **kwargs: Any) -> Any
```

Runs when LLM starts

#### on\_chat\_model\_start

```python theme={null}
def on_chat_model_start(serialized: Dict[str, Any],
                        messages: List[List[BaseMessage]],
                        metadata: Optional[Dict[str, Any]] = None,
                        **kwargs: Any) -> Any
```

Runs when a chat model call starts

#### on\_llm\_new\_token

```python theme={null}
def on_llm_new_token(token: str, **kwargs: Any) -> Any
```

Run on new LLM token. Only available when streaming is enabled.

#### on\_llm\_end

```python theme={null}
def on_llm_end(response: LLMResult, **kwargs: Any) -> Any
```

Run when LLM ends running.

#### on\_llm\_error

```python theme={null}
def on_llm_error(error: Union[Exception, BaseException, KeyboardInterrupt],
                 **kwargs: Any) -> Any
```

Run when LLM errors.

#### on\_retriever\_start

```python theme={null}
def on_retriever_start(serialized: dict[str, Any],
                       query: str,
                       *,
                       run_id: UUID,
                       parent_run_id: Optional[UUID] = None,
                       tags: Optional[list[str]] = None,
                       metadata: Optional[dict[str, Any]] = None,
                       **kwargs: Any) -> Any
```

Run when Retriever starts running.