Fix AWS Bedrock timeout exception handling

- Use ReadTimeoutError and asyncio.TimeoutError which are the actual exceptions thrown by boto3

CHANGELOG.md

@@ -27,6 +27,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## Fixed
 
+- Fixed an issue in `AWSBedrockLLMService` where timeout exceptions weren't
+  being detected.
+
 - Fixed a `PipelineTask` issue that could prevent the application to exit if
   `task.cancel()` was called when the task was already finished.
 

src/pipecat/services/aws/llm.py

@@ -61,7 +61,6 @@ from pipecat.utils.tracing.service_decorators import traced_llm
 
 try:
     import aioboto3
-    import httpx
     from botocore.config import Config
     from botocore.exceptions import ReadTimeoutError
 except ModuleNotFoundError as e:
@@ -1117,7 +1116,7 @@ class AWSBedrockLLMService(LLMService):
             # also get cancelled.
             use_completion_tokens_estimate = True
             raise
-        except httpx.TimeoutException:
+        except (ReadTimeoutError, asyncio.TimeoutError):
             await self._call_event_handler("on_completion_timeout")
         except Exception as e:
             logger.exception(f"{self} exception: {e}")