[BUG] fail to chat after retrieving files

[sun-timer]

Description

I have uploaded the files and parsed it successfully. When I ask about the documents, it retrieved the specific information of the documents and the content was also relevant, but the reply was not known. (Both llms and embedded models are set and test has passed)

Reproduction steps

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

Screenshots

![DESCRIPTION](LINK.png)

Logs

No response

Browsers

Microsoft Edge

OS

Linux

Additional information

No response

[taprosoft]

@sun-timer could you provide the console log to see any issue happened? It could be:

• LLM model is not set up correctly, hence empty response
• Content filtering triggered from Azure / OpenAI
• OOM issue if you use large local LLM

[sun-timer]

should I only upload pdf instead of markdown , my embedding model is bce-embedding-base_v1