Files
langchain/docs
Harel Gal a91181fe6d community[minor]: add support for Guardrails for Amazon Bedrock (#15099)
Added support for optionally supplying 'Guardrails for Amazon Bedrock'
on both types of model invocations (batch/regular and streaming) and for
all models supported by the Amazon Bedrock service.

@baskaryan  @hwchase17

```python 
llm = Bedrock(model_id="<model_id>", client=bedrock,
                  model_kwargs={},
                  guardrails={"id": " <guardrail_id>",
                              "version": "<guardrail_version>",
                               "trace": True}, callbacks=[BedrockAsyncCallbackHandler()])

class BedrockAsyncCallbackHandler(AsyncCallbackHandler):
    """Async callback handler that can be used to handle callbacks from langchain."""

    async def on_llm_error(
            self,
            error: BaseException,
            **kwargs: Any,
    ) -> Any:
        reason = kwargs.get("reason")
        if reason == "GUARDRAIL_INTERVENED":
           # kwargs contains additional trace information sent by 'Guardrails for Bedrock' service.
            print(f"""Guardrails: {kwargs}""")


# streaming 
llm = Bedrock(model_id="<model_id>", client=bedrock,
                  model_kwargs={},
                  streaming=True,
                  guardrails={"id": "<guardrail_id>",
                              "version": "<guardrail_version>"})
```

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-01-24 14:44:19 -08:00
..
2023-12-15 17:46:12 -08:00
2024-01-05 09:15:00 -08:00
2023-12-17 12:55:49 -08:00
2024-01-08 08:38:14 -08:00
2024-01-08 08:38:14 -08:00

LangChain Documentation

For more information on contributing to our documentation, see the Documentation Contributing Guide