github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-19 19:11:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix handling of missing action & input for async MRKL agent (#5985)

Browse Source 
Hi,

This is a fix for https://github.com/hwchase17/langchain/pull/5014. This
PR forgot to add the ability to self solve the ValueError(f"Could not
parse LLM output: {llm_output}") error for `_atake_next_step`.
This commit is contained in:
Daniel Grittner 2023-06-10 23:38:20 +02:00 committed by GitHub
parent ca1afa7213
commit 0ca37e613c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
langchain/agents/agent.py
View File

@ -864,7 +864,11 @@ class AgentExecutor(Chain):
raise e raise e
text = str(e) text = str(e)
if isinstance(self.handle_parsing_errors, bool): if isinstance(self.handle_parsing_errors, bool):
observation = "Invalid or incomplete response" if e.send_to_llm:
observation = str(e.observation)
text = str(e.llm_output)
else:
observation = "Invalid or incomplete response"
elif isinstance(self.handle_parsing_errors, str): elif isinstance(self.handle_parsing_errors, str):
observation = self.handle_parsing_errors observation = self.handle_parsing_errors
elif callable(self.handle_parsing_errors): elif callable(self.handle_parsing_errors):