github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-06 19:08:59 -05:00
Code Issues 1.3k Packages Projects Releases 126 Wiki Activity

[GH-ISSUE #5721] Bug: RAG documents #14101

New Issue
Closed
opened 2026-04-19 20:34:39 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-19 20:34:39 -05:00
Owner
Copy Link

Originally created by @pablomart on GitHub (Sep 26, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/5721

Bug Report

Installation Method

  1. Clone repo from github.
  2. Install Node js
  3. Install javascript dependencies --> npm i
  4. build app -> npm run build
  5. Create virtual env python
  6. Install python dependecies --> pip install -r requeriment.txt
  7. start app -> backend/start_windows.bat

Environment

  • Open WebUI Version: v0.3.28

  • Ollama (if applicable): v0.3.0

  • Operating System: Windows 10

  • Browser (if applicable): Chrome Version 128.0.6613.85

Confirmation:

  • I have read and followed all the instructions provided in the README.md.
  • I am on the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below.

Expected Behavior:

I want to ask any question about a document, and I want the model answer according to the information of the document I have selected in the conversation.

Actual Behavior:

I select the document I want to ask for information about, but the model does not detect the document in the conversation and says other information not related to the document. The model lost the context of the document I am asking about and invents an answer about hotels that has nothing to do with the document and the requested question.

Description

Bug Summary:
You want to ask questions about a document selected in the conversation, but the model does not answer information about the document but about something else.

Reproduction Details

Steps to Reproduce:

  1. I upload a document to the platform
  2. use # to incorporate it into the conversation
  3. I ask a question about the selected document

Logs and Screenshots

Browser Console Logs:
[Include relevant browser console logs, if applicable]

Docker Container Logs:

I have noticed that in the application logs it is not recognising the file and the result id
image

Screenshots/Screen Recordings (if applicable):

This is an image of the chat made when asked about the selected document.

image

Additional Information

I would like to know more information about how to refer to the documents to ask questions, since in some cases it does answer me based on the information in the document and in others it does not recognize the document and the answer is invented.

@tjbck Would you know why this is happening, or could you teach me how to reference documents better?

Note

If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!

Originally created by @pablomart on GitHub (Sep 26, 2024). Original GitHub issue: https://github.com/open-webui/open-webui/issues/5721 # Bug Report ## Installation Method 1. Clone repo from github. 2. Install Node js 3. Install javascript dependencies --> npm i 4. build app -> npm run build 5. Create virtual env python 6. Install python dependecies --> pip install -r requeriment.txt 7. start app -> backend/start_windows.bat ## Environment - **Open WebUI Version:** v0.3.28 - **Ollama (if applicable):** v0.3.0 - **Operating System:** Windows 10 - **Browser (if applicable):** Chrome Version 128.0.6613.85 **Confirmation:** - [x] I have read and followed all the instructions provided in the README.md. - [x] I am on the latest version of both Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below. ## Expected Behavior: I want to ask any question about a document, and I want the model answer according to the information of the document I have selected in the conversation. ## Actual Behavior: I select the document I want to ask for information about, but the model does not detect the document in the conversation and says other information not related to the document. The model lost the context of the document I am asking about and invents an answer about hotels that has nothing to do with the document and the requested question. ## Description **Bug Summary:** You want to ask questions about a document selected in the conversation, but the model does not answer information about the document but about something else. ## Reproduction Details **Steps to Reproduce:** 1. I upload a document to the platform 2. use # to incorporate it into the conversation 3. I ask a question about the selected document ## Logs and Screenshots **Browser Console Logs:** [Include relevant browser console logs, if applicable] **Docker Container Logs:** I have noticed that in the application logs it is not recognising the file and the result id ![image](https://github.com/user-attachments/assets/156dbf55-944f-4cb1-aeea-ef2912b5bba0) **Screenshots/Screen Recordings (if applicable):** This is an image of the chat made when asked about the selected document. ![image](https://github.com/user-attachments/assets/a80954b9-79cf-4f76-a31f-f2ec06c2b3ff) ## Additional Information I would like to know more information about how to refer to the documents to ask questions, since in some cases it does answer me based on the information in the document and in others it does not recognize the document and the answer is invented. @tjbck Would you know why this is happening, or could you teach me how to reference documents better? ## Note If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#14101
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?