[GH-ISSUE #17700] issue: Using single file from knowledge base is not working

GiteaMirror commented

2026-04-20 00:35:57 -05:00

Owner

Originally created by @DrZoidberg09 on GitHub (Sep 24, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17700

Check Existing Issues

I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.6.30

Ollama Version (if applicable)

No response

Operating System

Ubuntu 24.04

Browser (if applicable)

No response

Confirmation

I have read and followed all instructions in README.md.
I am using 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 every relevant configuration, setting, and environment variable used in my setup.
I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
Start with the initial platform/version/OS and dependencies used,
Specify exact install/launch/configure commands,
List URLs visited, user input (incl. example values/emails/passwords if needed),
Describe all options and toggles enabled or changed,
Include any files or environmental changes,
Identify the expected and actual result at each stage,
Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

We are using open-webui with qdrant as vector database. We have embedded ~1500 PDF files there. We want to chat with the whole set of files or specific files.

Actual Behavior

If selecting the whole knowledge base, everythign works fine. If a single or multiple files are selected, it returns always: No source found.

Steps to Reproduce

Create a new chat
Select one or more files from the knowledge base
Ask any kind of task such as "Please summarize the document"
"No source found" will be returned

Logs & Screenshots

Three is nothing suspicious in the logs:

2025-09-24 07:32:15.600 | INFO | httpx._client:_send_single_request:1025 - HTTP Request: GET http://qdrant:6333/collections/open-webui_files/exists "HTTP/1.1 200 OK"
2025-09-24 07:32:15.607 | INFO | httpx._client:_send_single_request:1025 - HTTP Request: POST http://qdrant:6333/collections/open-webui_files/points/query "HTTP/1.1 200 OK"
2025-09-24 07:32:15.607 | INFO | open_webui.retrieval.utils:query_doc:96 - query_doc:result

Additional Information

No response

Originally created by @DrZoidberg09 on GitHub (Sep 24, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/17700 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v0.6.30 ### Ollama Version (if applicable) _No response_ ### Operating System Ubuntu 24.04 ### Browser (if applicable) _No response_ ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using 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 every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior We are using open-webui with qdrant as vector database. We have embedded ~1500 PDF files there. We want to chat with the whole set of files or specific files. ### Actual Behavior If selecting the whole knowledge base, everythign works fine. If a single or multiple files are selected, it returns always: No source found. ### Steps to Reproduce 1. Create a new chat 2. Select one or more files from the knowledge base 3. Ask any kind of task such as "Please summarize the document" 4. "No source found" will be returned ### Logs & Screenshots Three is nothing suspicious in the logs: 2025-09-24 07:32:15.600 | INFO | httpx._client:_send_single_request:1025 - HTTP Request: GET http://qdrant:6333/collections/open-webui_files/exists "HTTP/1.1 200 OK" 2025-09-24 07:32:15.607 | INFO | httpx._client:_send_single_request:1025 - HTTP Request: POST http://qdrant:6333/collections/open-webui_files/points/query "HTTP/1.1 200 OK" 2025-09-24 07:32:15.607 | INFO | open_webui.retrieval.utils:query_doc:96 - query_doc:result [[]] [[]] ### Additional Information _No response_