I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
I am using the latest version of Open WebUI.
Installation Method
Git Clone
Open WebUI Version
7.0.2
Ollama Version (if applicable)
No response
Operating System
debian
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
Settings-Documents-Relevance **Threshold settings = 0,6. ** for the RAG knowledge retrieval threshold.
But i use simple chat, without knowledge collections, and upload document (attach to chat), "no resources found" and does not respond to the data in the documents. If threshold settings set 0,2, chat response the attached documents content. but this way the RAG returns too many inappropriate answers.
Actual Behavior
Settings-Documents-Relevance Threshold settings = 0,6. For the RAG knowledge retrieval threshold.
But i use simple chat, without knowledge collections, and upload document (attach to chat), "no resources found" and does not respond to the data in the documents. If threshold settings set 0,2, chat response the attached documents content. but this way the RAG returns too many inappropriate answers.
Steps to Reproduce
Documents Relevance Threshold settings change to 0,6+
Simple chat upload any documents and please, summarize.
Chat "no resources found" returns
Logs & Screenshots
2026-01-14 09:45:20.776 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/users/2974c035-3da0-40ff-98ff-752379a9616f/profile/image HTTP/1.1" 200
2026-01-14 09:45:20.777 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/models/model/profile/image?id=undefined&lang=en-GB HTTP/1.1" 200
2026-01-14 09:45:20.794 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/tools/ HTTP/1.1" 200
2026-01-14 09:45:20.795 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/models/model/profile/image?id=ltalnos-csevegs&lang=en-GB HTTP/1.1" 200
2026-01-14 09:45:20.842 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /static/favicon.png HTTP/1.1" 200
2026-01-14 09:45:27.374 | INFO | open_webui.routers.files:upload_file_handler:225 - file.content_type: application/vnd.openxmlformats-officedocument.wordprocessingml.document True
2026-01-14 09:45:27.388 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/v1/files/?process=true HTTP/1.1" 200
2026-01-14 09:45:27.403 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/files/1dae47bc-2203-4e95-8944-5d0a72c7c0ff/process/status?stream=true HTTP/1.1" 200
2026-01-14 09:45:29.412 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1425 - Using markdown header text splitter
2026-01-14 09:45:29.422 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1509 - generating embeddings for file-1dae47bc-2203-4e95-8944-5d0a72c7c0ff
2026-01-14 09:45:30.358 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1549 - embeddings generated 1 for 1 items
2026-01-14 09:45:30.358 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1561 - adding to collection file-1dae47bc-2203-4e95-8944-5d0a72c7c0ff
2026-01-14 09:45:30.406 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1567 - added 1 items to collection file-1dae47bc-2203-4e95-8944-5d0a72c7c0ff
2026-01-14 09:45:30.406 | INFO | open_webui.routers.retrieval:process_file:1762 - added 1 items to collection file-1dae47bc-2203-4e95-8944-5d0a72c7c0ff
2026-01-14 09:45:31.728 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /_app/version.json HTTP/1.1" 200
2026-01-14 09:45:31.857 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.3.146:0 - "GET /api/version HTTP/1.1" 200
2026-01-14 09:45:34.340 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/version HTTP/1.1" 200
2026-01-14 09:45:34.724 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/v1/chats/new HTTP/1.1" 200
2026-01-14 09:45:34.759 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/models/model/profile/image?id=ltalnos-csevegs&lang=en-GB HTTP/1.1" 200
2026-01-14 09:45:34.867 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/tools/ HTTP/1.1" 200
2026-01-14 09:45:34.890 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/models/model/profile/image?id=ltalnos-csevegs&lang=en-GB HTTP/1.1" 200
2026-01-14 09:45:35.159 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /static/favicon.png HTTP/1.1" 200
2026-01-14 09:45:35.161 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-14 09:45:35.185 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/v1/chats/b1dfbac5-5e73-47c3-a844-b6503f5cda74 HTTP/1.1" 200
2026-01-14 09:45:35.195 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-14 09:45:35.215 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/chat/completions HTTP/1.1" 200
2026-01-14 09:45:35.240 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-14 09:45:37.254 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/chats/37eee025-f864-4e16-9b99-af857b91dc7e HTTP/1.1" 200
2026-01-14 09:45:38.110 | INFO | open_webui.retrieval.utils:query_collection_with_hybrid_search:487 - Starting hybrid search for 3 queries in 1 collections...
2026-01-14 09:45:38.311 | INFO | open_webui.retrieval.utils:query_doc_with_hybrid_search:310 - query_doc_with_hybrid_search:result
2026-01-14 09:45:38.314 | INFO | open_webui.retrieval.utils:query_doc_with_hybrid_search:310 - query_doc_with_hybrid_search:result
2026-01-14 09:45:38.318 | INFO | open_webui.retrieval.utils:query_doc_with_hybrid_search:310 - query_doc_with_hybrid_search:result
2026-01-14 09:45:39.220 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/chat/completed HTTP/1.1" 200
Additional Information
No response
Originally created by @n4gY1 on GitHub (Jan 14, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20661
### 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 have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
- [x] I am using the latest version of Open WebUI.
### Installation Method
Git Clone
### Open WebUI Version
7.0.2
### Ollama Version (if applicable)
_No response_
### Operating System
debian
### 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
Settings-Documents-Relevance **Threshold settings = 0,6. ** for the RAG knowledge retrieval threshold.
But i use simple chat, without knowledge collections, and upload document (attach to chat), "no resources found" and does not respond to the data in the documents. If threshold settings set 0,2, chat response the attached documents content. but this way the RAG returns too many inappropriate answers.
### Actual Behavior
Settings-Documents-Relevance Threshold settings = 0,6. For the RAG knowledge retrieval threshold.
But i use simple chat, without knowledge collections, and upload document (attach to chat), "no resources found" and does not respond to the data in the documents. If threshold settings set 0,2, chat response the attached documents content. but this way the RAG returns too many inappropriate answers.
### Steps to Reproduce
Documents Relevance Threshold settings change to 0,6+
Simple chat upload any documents and please, summarize.
Chat "no resources found" returns
### Logs & Screenshots
2026-01-14 09:45:20.776 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/users/2974c035-3da0-40ff-98ff-752379a9616f/profile/image HTTP/1.1" 200
2026-01-14 09:45:20.777 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/models/model/profile/image?id=undefined&lang=en-GB HTTP/1.1" 200
2026-01-14 09:45:20.794 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/tools/ HTTP/1.1" 200
2026-01-14 09:45:20.795 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/models/model/profile/image?id=ltalnos-csevegs&lang=en-GB HTTP/1.1" 200
2026-01-14 09:45:20.842 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /static/favicon.png HTTP/1.1" 200
2026-01-14 09:45:27.374 | INFO | open_webui.routers.files:upload_file_handler:225 - file.content_type: application/vnd.openxmlformats-officedocument.wordprocessingml.document True
2026-01-14 09:45:27.388 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/v1/files/?process=true HTTP/1.1" 200
2026-01-14 09:45:27.403 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/files/1dae47bc-2203-4e95-8944-5d0a72c7c0ff/process/status?stream=true HTTP/1.1" 200
2026-01-14 09:45:29.412 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1425 - Using markdown header text splitter
2026-01-14 09:45:29.422 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1509 - generating embeddings for file-1dae47bc-2203-4e95-8944-5d0a72c7c0ff
2026-01-14 09:45:30.358 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1549 - embeddings generated 1 for 1 items
2026-01-14 09:45:30.358 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1561 - adding to collection file-1dae47bc-2203-4e95-8944-5d0a72c7c0ff
2026-01-14 09:45:30.406 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1567 - added 1 items to collection file-1dae47bc-2203-4e95-8944-5d0a72c7c0ff
2026-01-14 09:45:30.406 | INFO | open_webui.routers.retrieval:process_file:1762 - added 1 items to collection file-1dae47bc-2203-4e95-8944-5d0a72c7c0ff
2026-01-14 09:45:31.728 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /_app/version.json HTTP/1.1" 200
2026-01-14 09:45:31.857 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.3.146:0 - "GET /api/version HTTP/1.1" 200
2026-01-14 09:45:34.340 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/version HTTP/1.1" 200
2026-01-14 09:45:34.724 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/v1/chats/new HTTP/1.1" 200
2026-01-14 09:45:34.759 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/models/model/profile/image?id=ltalnos-csevegs&lang=en-GB HTTP/1.1" 200
2026-01-14 09:45:34.867 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/tools/ HTTP/1.1" 200
2026-01-14 09:45:34.890 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/models/model/profile/image?id=ltalnos-csevegs&lang=en-GB HTTP/1.1" 200
2026-01-14 09:45:35.159 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /static/favicon.png HTTP/1.1" 200
2026-01-14 09:45:35.161 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-14 09:45:35.185 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/v1/chats/b1dfbac5-5e73-47c3-a844-b6503f5cda74 HTTP/1.1" 200
2026-01-14 09:45:35.195 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-14 09:45:35.215 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/chat/completions HTTP/1.1" 200
2026-01-14 09:45:35.240 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-14 09:45:37.254 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/chats/37eee025-f864-4e16-9b99-af857b91dc7e HTTP/1.1" 200
2026-01-14 09:45:38.110 | INFO | open_webui.retrieval.utils:query_collection_with_hybrid_search:487 - Starting hybrid search for 3 queries in 1 collections...
2026-01-14 09:45:38.311 | INFO | open_webui.retrieval.utils:query_doc_with_hybrid_search:310 - query_doc_with_hybrid_search:result [[]] [[]]
2026-01-14 09:45:38.314 | INFO | open_webui.retrieval.utils:query_doc_with_hybrid_search:310 - query_doc_with_hybrid_search:result [[]] [[]]
2026-01-14 09:45:38.318 | INFO | open_webui.retrieval.utils:query_doc_with_hybrid_search:310 - query_doc_with_hybrid_search:result [[]] [[]]
2026-01-14 09:45:39.220 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/chat/completed HTTP/1.1" 200
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-05-18 04:30:25 -05:00
@owui-terminator[bot] commented on GitHub (Jan 14, 2026):
🔍Similar Issues Found
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
#20033issue: RAG not working when file uploaded through chat by abhishek-paradkar-sndk • Dec 18, 2025 • bug
#20558issue: RAG Knowledge file when modify/update, older data is available by n4gY1 • Jan 10, 2026 • bug
#20414issue: Chats can't be archived by Ithanil • Jan 06, 2026 • bug
#19281issue: RAG Template applied with "Bypass Embedding and Retrieval" enabled by lucyknada • Nov 19, 2025 • bug
#19098issue: Prompt & context duplication when RAG template is used by matiboux • Nov 11, 2025 • bug
Show 4 more related issues
#19101issue: RAG template query placeholder escaping logic error by matiboux • Nov 11, 2025 • bug
#19698issue: .41 web based search and webpages - RAG - are not fixed by frenzybiscuit • Dec 02, 2025 • bug
#19987issue: There is a lack of visual consistency between the home page and the chat interface. by i-iooi-i • Dec 16, 2025 • bug
#20059issue: Chat response is not working by navilg • Dec 20, 2025 • bug
💡Tips:
If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
If you found a solution in any of these issues, please share it here to help others
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
<!-- gh-comment-id:3748795160 -->
@owui-terminator[bot] commented on GitHub (Jan 14, 2026):
🔍 **Similar Issues Found**
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
1. [#20033](https://github.com/open-webui/open-webui/issues/20033) **issue: RAG not working when file uploaded through chat**
*by abhishek-paradkar-sndk • Dec 18, 2025 • `bug`*
2. [#20558](https://github.com/open-webui/open-webui/issues/20558) **issue: RAG Knowledge file when modify/update, older data is available**
*by n4gY1 • Jan 10, 2026 • `bug`*
3. [#20414](https://github.com/open-webui/open-webui/issues/20414) **issue: Chats can't be archived**
*by Ithanil • Jan 06, 2026 • `bug`*
4. [#19281](https://github.com/open-webui/open-webui/issues/19281) **issue: RAG Template applied with "Bypass Embedding and Retrieval" enabled**
*by lucyknada • Nov 19, 2025 • `bug`*
5. [#19098](https://github.com/open-webui/open-webui/issues/19098) **issue: Prompt & context duplication when RAG template is used**
*by matiboux • Nov 11, 2025 • `bug`*
<details>
<summary>Show 4 more related issues</summary>
6. [#19101](https://github.com/open-webui/open-webui/issues/19101) **issue: RAG template query placeholder escaping logic error**
*by matiboux • Nov 11, 2025 • `bug`*
7. [#19698](https://github.com/open-webui/open-webui/issues/19698) **issue: .41 web based search and webpages - RAG - are not fixed**
*by frenzybiscuit • Dec 02, 2025 • `bug`*
8. [#19987](https://github.com/open-webui/open-webui/issues/19987) **issue: There is a lack of visual consistency between the home page and the chat interface.**
*by i-iooi-i • Dec 16, 2025 • `bug`*
9. [#20059](https://github.com/open-webui/open-webui/issues/20059) **issue: Chat response is not working**
*by navilg • Dec 20, 2025 • `bug`*
</details>
---
💡 **Tips:**
- If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
- If you found a solution in any of these issues, please share it here to help others
*This comment was generated automatically by a bot.* Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
Because of this, i cannot use RAG threshold. By the way it's not a new problem i think it's existed since the 0.5 releases
<!-- gh-comment-id:3748947106 -->
@ctcanbol commented on GitHub (Jan 14, 2026):
Because of this, i cannot use RAG threshold. By the way it's not a new problem i think it's existed since the 0.5 releases
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @n4gY1 on GitHub (Jan 14, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20661
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
7.0.2
Ollama Version (if applicable)
No response
Operating System
debian
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
Settings-Documents-Relevance **Threshold settings = 0,6. ** for the RAG knowledge retrieval threshold.
But i use simple chat, without knowledge collections, and upload document (attach to chat), "no resources found" and does not respond to the data in the documents. If threshold settings set 0,2, chat response the attached documents content. but this way the RAG returns too many inappropriate answers.
Actual Behavior
Settings-Documents-Relevance Threshold settings = 0,6. For the RAG knowledge retrieval threshold.
But i use simple chat, without knowledge collections, and upload document (attach to chat), "no resources found" and does not respond to the data in the documents. If threshold settings set 0,2, chat response the attached documents content. but this way the RAG returns too many inappropriate answers.
Steps to Reproduce
Documents Relevance Threshold settings change to 0,6+
Simple chat upload any documents and please, summarize.
Chat "no resources found" returns
Logs & Screenshots
2026-01-14 09:45:20.776 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/users/2974c035-3da0-40ff-98ff-752379a9616f/profile/image HTTP/1.1" 200
2026-01-14 09:45:20.777 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/models/model/profile/image?id=undefined&lang=en-GB HTTP/1.1" 200
2026-01-14 09:45:20.794 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/tools/ HTTP/1.1" 200
2026-01-14 09:45:20.795 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/models/model/profile/image?id=ltalnos-csevegs&lang=en-GB HTTP/1.1" 200
2026-01-14 09:45:20.842 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /static/favicon.png HTTP/1.1" 200
2026-01-14 09:45:27.374 | INFO | open_webui.routers.files:upload_file_handler:225 - file.content_type: application/vnd.openxmlformats-officedocument.wordprocessingml.document True
2026-01-14 09:45:27.388 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/v1/files/?process=true HTTP/1.1" 200
2026-01-14 09:45:27.403 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/files/1dae47bc-2203-4e95-8944-5d0a72c7c0ff/process/status?stream=true HTTP/1.1" 200
2026-01-14 09:45:29.412 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1425 - Using markdown header text splitter
2026-01-14 09:45:29.422 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1509 - generating embeddings for file-1dae47bc-2203-4e95-8944-5d0a72c7c0ff
2026-01-14 09:45:30.358 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1549 - embeddings generated 1 for 1 items
2026-01-14 09:45:30.358 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1561 - adding to collection file-1dae47bc-2203-4e95-8944-5d0a72c7c0ff
2026-01-14 09:45:30.406 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:1567 - added 1 items to collection file-1dae47bc-2203-4e95-8944-5d0a72c7c0ff
2026-01-14 09:45:30.406 | INFO | open_webui.routers.retrieval:process_file:1762 - added 1 items to collection file-1dae47bc-2203-4e95-8944-5d0a72c7c0ff
2026-01-14 09:45:31.728 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /_app/version.json HTTP/1.1" 200
2026-01-14 09:45:31.857 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.3.146:0 - "GET /api/version HTTP/1.1" 200
2026-01-14 09:45:34.340 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/version HTTP/1.1" 200
2026-01-14 09:45:34.724 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/v1/chats/new HTTP/1.1" 200
2026-01-14 09:45:34.759 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/models/model/profile/image?id=ltalnos-csevegs&lang=en-GB HTTP/1.1" 200
2026-01-14 09:45:34.867 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/tools/ HTTP/1.1" 200
2026-01-14 09:45:34.890 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/models/model/profile/image?id=ltalnos-csevegs&lang=en-GB HTTP/1.1" 200
2026-01-14 09:45:35.159 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /static/favicon.png HTTP/1.1" 200
2026-01-14 09:45:35.161 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-14 09:45:35.185 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/v1/chats/b1dfbac5-5e73-47c3-a844-b6503f5cda74 HTTP/1.1" 200
2026-01-14 09:45:35.195 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-14 09:45:35.215 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/chat/completions HTTP/1.1" 200
2026-01-14 09:45:35.240 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2026-01-14 09:45:37.254 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "GET /api/v1/chats/37eee025-f864-4e16-9b99-af857b91dc7e HTTP/1.1" 200
2026-01-14 09:45:38.110 | INFO | open_webui.retrieval.utils:query_collection_with_hybrid_search:487 - Starting hybrid search for 3 queries in 1 collections...
2026-01-14 09:45:38.311 | INFO | open_webui.retrieval.utils:query_doc_with_hybrid_search:310 - query_doc_with_hybrid_search:result
2026-01-14 09:45:38.314 | INFO | open_webui.retrieval.utils:query_doc_with_hybrid_search:310 - query_doc_with_hybrid_search:result
2026-01-14 09:45:38.318 | INFO | open_webui.retrieval.utils:query_doc_with_hybrid_search:310 - query_doc_with_hybrid_search:result
2026-01-14 09:45:39.220 | INFO | uvicorn.protocols.http.httptools_impl:send:483 - 10.49.160.135:0 - "POST /api/chat/completed HTTP/1.1" 200
Additional Information
No response
@owui-terminator[bot] commented on GitHub (Jan 14, 2026):
🔍 Similar Issues Found
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
#20033 issue: RAG not working when file uploaded through chat
by abhishek-paradkar-sndk • Dec 18, 2025 •
bug#20558 issue: RAG Knowledge file when modify/update, older data is available
by n4gY1 • Jan 10, 2026 •
bug#20414 issue: Chats can't be archived
by Ithanil • Jan 06, 2026 •
bug#19281 issue: RAG Template applied with "Bypass Embedding and Retrieval" enabled
by lucyknada • Nov 19, 2025 •
bug#19098 issue: Prompt & context duplication when RAG template is used
by matiboux • Nov 11, 2025 •
bugShow 4 more related issues
#19101 issue: RAG template query placeholder escaping logic error
by matiboux • Nov 11, 2025 •
bug#19698 issue: .41 web based search and webpages - RAG - are not fixed
by frenzybiscuit • Dec 02, 2025 •
bug#19987 issue: There is a lack of visual consistency between the home page and the chat interface.
by i-iooi-i • Dec 16, 2025 •
bug#20059 issue: Chat response is not working
by navilg • Dec 20, 2025 •
bug💡 Tips:
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
@ctcanbol commented on GitHub (Jan 14, 2026):
Because of this, i cannot use RAG threshold. By the way it's not a new problem i think it's existed since the 0.5 releases