LangChain agent not working

Short Course Q&A LangChain for LLM Application Development
1

When I ran agent(“what is 10% of 200?”), I got the following

Entering new AgentExecutor chain…

Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:

Finished chain.
{‘input’: ‘what is 10% of 200?’,
‘output’: ‘Agent stopped due to iteration limit or time limit.’}

Can anyone please tell me what went wrong?

2

Hi @Ezhilarasan

Thank you for your post.

According to the langchain documentation, it could be a issue with your output.

They recommend that approach for that situation.

To be honest, I’m kind a newbie on langchain, but i hope this help you.

It would be nice have a little bit more context regards your code or application to get more insights in order to help you out.

Never the less, i will chase for other solutions to get a more precise response.

As soon a find out, i will reply you properly.

Regards,
elirod

1 Like
3

I’m experiencing this straight inside the course. Is the course outdated?

4

I think their prompt doesn’t work. If I use this prompt it works:

agent("Compute the answer to: 25% of 300")