**Agent stopped due to iteration limit or time limit**

🚀 Deployment
,
1

I have a langchain application with a streamlit frontend that runs seamlessly in the local environment. But when I deploy it the response returned by the langchain agent executor is
Agent stopped due to iteration limit or time limit. This is for for the first query/prompt. But I can view the SQL query output in the logs.

Then for the second query it responds with:
FileNotFoundError: [Errno 2] No such file or directory: 'output.csv'. But I see that the current directory actually exists.

I fear like missing something, but unable to figure out the actual cause. Would like to get quick help on the same to deliver it to the client.

Thanks in advance.

2

What do you mean by “current” here? The csv file is in streamlit-app/output.csv.

3

Thanks @Goyo , I tried the one as suggested which sorted the earlier issue.
I actually referred to current as the same directory equivalent to './'
And now facing a issue is ChromaDB.

Please visit                     https://docs.trychroma.com/troubleshooting#sqlite to learn how                     to upgrade.

Any help to upgrade is package is appreciated.

4

Please visit 🔍 Troubleshooting | Chroma to learn how to upgrade.

5

I checked this and was looking for a solution specific to streamlit because I couldn’t directly hardcode the version of pysqlite3-binary.

Also, not quite sure how compatible is ChromaDB in Streamlit cloud. Any specific help on these steps could be of great help.

6

The first suggestion is “Install the latest version of Python 3.10”. Why don’t you just try it and tell us how it goes?

7

I have updated to Python version 3.10.x as suggested and executed the application. Works well in localhost but fails in Streamlit cloud.
I have attached a video recording showing the same. Hope it helps to understand the issue better.

Thanks in advance.