Chatconv agent: output parser exception (#4923)

the output parser form chat conversational agent now raises
`OutputParserException` like the rest.

The `raise OutputParserExeption(...) from e` form also carries through
the original error details on what went wrong.

I added the `ValueError` as a base class to `OutputParserException` to
avoid breaking code that was relying on `ValueError` as a way to catch
exceptions from the agent. So catching ValuError still works. Not sure
if this is a good idea though ?

langchain/agents/conversational_chat/output_parser.py

@@ -5,7 +5,7 @@ from typing import Union
 
 from langchain.agents import AgentOutputParser
 from langchain.agents.conversational_chat.prompt import FORMAT_INSTRUCTIONS
-from langchain.schema import AgentAction, AgentFinish
+from langchain.schema import AgentAction, AgentFinish, OutputParserException
 
 
 class ConvoOutputParser(AgentOutputParser):
@@ -13,6 +13,7 @@ class ConvoOutputParser(AgentOutputParser):
         return FORMAT_INSTRUCTIONS
 
     def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
+        try:
             cleaned_output = text.strip()
             if "```json" in cleaned_output:
                 _, cleaned_output = cleaned_output.split("```json")
@@ -31,6 +32,8 @@ class ConvoOutputParser(AgentOutputParser):
                 return AgentFinish({"output": action_input}, text)
             else:
                 return AgentAction(action, action_input, text)
+        except Exception as e:
+            raise OutputParserException(f"Could not parse LLM output: {text}") from e
 
     @property
     def _type(self) -> str:

langchain/schema.py

@@ -360,7 +360,7 @@ class BaseOutputParser(BaseModel, ABC, Generic[T]):
         return output_parser_dict
 
 
-class OutputParserException(Exception):
+class OutputParserException(ValueError):
     """Exception that output parsers should raise to signify a parsing error.
 
     This exists to differentiate parsing errors from other code or execution errors