[GH-ISSUE #3986] RAG fails when documents increase #28983

Closed
opened 2026-04-25 03:27:59 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @snadeem1362 on GitHub (Jul 18, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/3986

Bug Report

RAG fails for large number of documents

Description

We have a huge number of pdf documents. Actually we want the whole library data to be ingested in RAG.
We are able to ingest data and generate embeddings, although it took a month to generate embeddings for 70GB PDF docs. The final vector DB size is 220GB. Now when we try to ask questions using these documents as context, it just never returns and keep on loading.
Is Open-webui RAG suitable for such huge amount of data? What are the alternatives?
Bug Summary:
Open-webui RAG just cant answer when embedding database is huge like 200GB

Steps to Reproduce:
Upload 20GB of documents in scan directory
Generate embeddings using default all-mini-llm-v2 embedding model
Set these documents as context
Ask question
It will never return and keep on loading

Expected Behavior:
It should come up with a precise answer from the embedded documents

Actual Behavior:
It is unable to answer and keep on searching

Environment

  • Open WebUI Version: [3.7]

  • Ollama (if applicable): [0.1.30]

  • Operating System: [Ubuntu 22.04]

  • Browser (if applicable): [Firefox 98.0]

Reproduction Details

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.

Logs and Screenshots

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

Docker Container Logs:
It just keep in searching relevant chunks from vector DB

Installation Method

Docker GPU Version

Additional Information

[Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.]

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 @snadeem1362 on GitHub (Jul 18, 2024). Original GitHub issue: https://github.com/open-webui/open-webui/issues/3986 # Bug Report RAG fails for large number of documents ## Description We have a huge number of pdf documents. Actually we want the whole library data to be ingested in RAG. We are able to ingest data and generate embeddings, although it took a month to generate embeddings for 70GB PDF docs. The final vector DB size is 220GB. Now when we try to ask questions using these documents as context, it just never returns and keep on loading. Is Open-webui RAG suitable for such huge amount of data? What are the alternatives? **Bug Summary:** Open-webui RAG just cant answer when embedding database is huge like 200GB **Steps to Reproduce:** Upload 20GB of documents in scan directory Generate embeddings using default all-mini-llm-v2 embedding model Set these documents as context Ask question It will never return and keep on loading **Expected Behavior:** It should come up with a precise answer from the embedded documents **Actual Behavior:** It is unable to answer and keep on searching ## Environment - **Open WebUI Version:** [3.7] - **Ollama (if applicable):** [0.1.30] - **Operating System:** [Ubuntu 22.04] - **Browser (if applicable):** [Firefox 98.0] ## Reproduction Details **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. - [ ] I have included the browser console logs. - [ ] I have included the Docker container logs. ## Logs and Screenshots **Browser Console Logs:** [Include relevant browser console logs, if applicable] **Docker Container Logs:** It just keep in searching relevant chunks from vector DB ## Installation Method Docker GPU Version ## Additional Information [Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.] ## 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.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#28983