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
v0.6.33
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
Implementing a functional RAG feature with Qdrant and hybrid search.
Actual Behavior
In version 0.6.32, everything works fine.
In version 0.6.33, it loads the entire vector database, and then I get an error such as:
“This model’s maximum context length is 32,768 tokens. However, your request contains 353,282 input tokens. Please reduce the length of the input messages.”
In the logs, the entry open_webui.retrieval.utils:get_doc:142 - query_doc:result is huge.
Reindexing the vector database didn't change anything.
In the log, i didn't see open_webui.retrieval.utils:query_doc_with_hybrid_search:199 but open_webui.retrieval.utils:get_doc:142
Steps to Reproduce
Use v0.6.32
Create a model with a knowledge base
Configure Qdrant as a vector database and enable hybrid search
Use embeddings via the OpenAI endpoint and an external reranker
Originally created by @dotmobo on GitHub (Oct 8, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/18155
### 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
v0.6.33
### 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
Implementing a functional RAG feature with Qdrant and hybrid search.
### Actual Behavior
In version 0.6.32, everything works fine.
In version 0.6.33, it loads the entire vector database, and then I get an error such as:
“This model’s maximum context length is 32,768 tokens. However, your request contains 353,282 input tokens. Please reduce the length of the input messages.”
In the logs, the entry `open_webui.retrieval.utils:get_doc:142 - query_doc:result` is huge.
Reindexing the vector database didn't change anything.
In the log, i didn't see ```open_webui.retrieval.utils:query_doc_with_hybrid_search:199``` but ```open_webui.retrieval.utils:get_doc:142```
### Steps to Reproduce
- Use v0.6.32
- Create a model with a knowledge base
- Configure Qdrant as a vector database and enable hybrid search
- Use embeddings via the OpenAI endpoint and an external reranker
- Run a query
- Migrate to v0.6.33
- Run a query : failed
- Reindex the database
- Run a query : failed
### Logs & Screenshots
2025-10-08 15:01:44.190 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 130.79.202.31:0 - "GET /static/favicon.png HTTP/1.1" 304
2025-10-08 15:01:44.215 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 130.79.202.31:0 - "POST /api/v1/chats/b35fd6ea-1d7f-4a32-87cb-99c963df6394 HTTP/1.1" 200
2025-10-08 15:01:44.227 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 130.79.202.31:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2025-10-08 15:01:44.241 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 130.79.202.31:0 - "POST /api/chat/completions HTTP/1.1" 200
2025-10-08 15:01:44.248 | INFO | open_webui.utils.plugin:install_frontmatter_requirements:283 - No requirements found in frontmatter.
2025-10-08 15:01:44.250 | INFO | open_webui.utils.plugin:load_function_module_by_id:147 - Loaded module: function_limit_per_hour
2025-10-08 15:01:44.253 | INFO | httpx._client:_send_single_request:1025 - HTTP Request: GET http://192.168.0.10:6333/collections/open-webui_knowledge/exists "HTTP/1.1 200 OK"
2025-10-08 15:01:44.258 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 130.79.202.31:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2025-10-08 15:01:44.275 | INFO | httpx._client:_send_single_request:1025 - HTTP Request: POST http://192.168.0.10:6333/collections/open-webui_knowledge/points/scroll "HTTP/1.1 200 OK"
2025-10-08 15:01:44.327 | INFO | open_webui.retrieval.utils:get_doc:142 - query_doc:result [['00131a1d-0b6d-445c-9b60-7888a2884e18', '00420443-f122-44fe-a9df-4bbfa445bf6a', '0045188d-731a-4bcf-b16c-276e8b3a6667', '00920ee1-fb13-4a36-9a86-40fd99b856e6', '00e00673-ae10-4ef5-9ea1-3c478a014981', '011cf222-3249-4d75-9012-1d7428e65158', '0129cd78-943a-4271-9fc7-c1d4f627f00b', '013c1a93-9eec-4ff5-b6c3-cace914c1059', '01884c43-deee-455e-870b-2a05ef504da3', '02173d79-ae84-4780-8117-58c8fff342e0', '0221f51a-d331-487a-ad3c-28c7be3ff9a6', '022263ea-538e-4fc9-93b7-0cb999cc1929', '0230f60b-2810-44ac-ab10-5c2ca706ea59', '026f4644-b0cc-4e2e-95b5-cff3ed189d9a', '0286459c-8728-4b7d-b62f-a4a4be5a5e06', '028cebb7-0939-4def-9b01-5cd8622b33d6', '02c7cada-0082-4b3c-8df4-ef2db7f3f1cf', '02f87cdc-e2bb-49b4-aae4-9aa2ca754a82', '02f8c979-514d-4943-8256-934a7b625867', '03256cd4-dd22-47cf-8dbb-33c43c252de5', '0348dd1b-e38b-481d-bced-c40ac803dd70', '03654166-66c5-4ee2-864f-6b8291869aea', '0379fbb5-87d6-45bb-b440-6122f4894b85', '038d6cd6-4b4f-47ad-a283-4a603b590787', '039eed9b-18a6-4b4e-b56b-f1841d12913c', '03a64412-9dfe-474c-83a3-21ecacd0d570', '03ad3696-66e8-452f-9efb-e90bbc506f12', '03b4763e-7f9a-400d-8880-4e98b0795074', '0441cd23-543a-43ea-9d58-de6964311380', '04611d17-a0bc-4b9f-9d85-9c501c51d293', '0495519a-c60b-4dcf-99af-a387794d7ca0', '04ac7837-c528-45ce-a7b2-5f58f0738451', '04f2faf5-f87d-45f2-806e-e2a3508fd698', '050dccd8-f8e4-457f-b94c-da2728f38ea1', '05344183-40db-4d63-844d-a278861f427d', '054425dc-bb14-4721-8ce7-661a3834038d', '054604e6-4547-4862-9424-8791295ad209', '05767db4-89dc-495f-8a54-f85ff67bfd7c', '06248779-b969-4c61-9d2a-ed7080e6a0ff', '062b3ecc-aa79-4ea1-ae99-fb604fb495b6', '0646bc2a-c28a-4133-9545-e3da92626dba', '064b38af-babc-4fc1-9a62-ee49f900e537', '065be188-3bec-4938-888f-2085468860f2', '065e1553-9f7c-45e0-a787-b96da2df02c9', '066167a1-11bf-4e60-8c99-b0f01f5d0428', '06a463fe-4afe-47d4-93c1-4154594d7f58', '06a7c19d-360d-4e6e-ac7d-fd992b84f08b', '06ad7321-9bdf-42ad-b097-3f2b7f8879c5', '06d91a3b-4f67-45bf-95a0-ff1b6d7ad088', '06fd2e12-0f0d-4d2c-967e-1c55a88ff1d5', '0728a0ee-848f-473f-8f40-e6568d0d9795', '0728c4ea-ce9d-4f4a-83d5-f4f8a85391a4', '07342af8-d770-45a9-8e93-c85925259bb9', '074e5050-f6f8-4b2e-a6aa-c70f54f61f15', '07631e0c-f8d8-4303-8dd9-48e790892a8e', '076b7fe3-27e0-4b72-a709-193741abe399', '0781a0af-602e-4117-9bea-ff21085e3e6d', '0798541e-b4d3-447d-8658-ef25e0faf534', '07a2cf0d-6e4c-4c65-9d43-667d405f88c6', '07dc9aa0-10f6-4d59-926f-23babd8482a2', '080844af-74ed-477b-8372-e8c728765d32', '082ecae5-b27b-429f-9492-bf82d1f1cb42', '0856f34b-6ce2-4d10-9a0f-ab27a1ec61e1', '0899abc4-bba7-4699-8ec3-e0a1605be42e', '089b5abb-4df8-4cf2-9066-5f61533d8b8a', '08d2148d-2972-4b8f-b1ea-07f87d69bcc5', '0956a9ed-0550-4551-87ab-b95c9707bbc9', '095c8ad7-c63c-47b3-bb77-cbac9d3dab66'
.....
}
76292 lines
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-04-25 07:56:54 -05:00
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 @dotmobo on GitHub (Oct 8, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/18155
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.6.33
Ollama Version (if applicable)
No response
Operating System
Debian
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
Implementing a functional RAG feature with Qdrant and hybrid search.
Actual Behavior
In version 0.6.32, everything works fine.
In version 0.6.33, it loads the entire vector database, and then I get an error such as:
“This model’s maximum context length is 32,768 tokens. However, your request contains 353,282 input tokens. Please reduce the length of the input messages.”
In the logs, the entry
open_webui.retrieval.utils:get_doc:142 - query_doc:resultis huge.Reindexing the vector database didn't change anything.
In the log, i didn't see
open_webui.retrieval.utils:query_doc_with_hybrid_search:199butopen_webui.retrieval.utils:get_doc:142Steps to Reproduce
Logs & Screenshots
2025-10-08 15:01:44.190 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 130.79.202.31:0 - "GET /static/favicon.png HTTP/1.1" 304
2025-10-08 15:01:44.215 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 130.79.202.31:0 - "POST /api/v1/chats/b35fd6ea-1d7f-4a32-87cb-99c963df6394 HTTP/1.1" 200
2025-10-08 15:01:44.227 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 130.79.202.31:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2025-10-08 15:01:44.241 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 130.79.202.31:0 - "POST /api/chat/completions HTTP/1.1" 200
2025-10-08 15:01:44.248 | INFO | open_webui.utils.plugin:install_frontmatter_requirements:283 - No requirements found in frontmatter.
2025-10-08 15:01:44.250 | INFO | open_webui.utils.plugin:load_function_module_by_id:147 - Loaded module: function_limit_per_hour
2025-10-08 15:01:44.253 | INFO | httpx._client:_send_single_request:1025 - HTTP Request: GET http://192.168.0.10:6333/collections/open-webui_knowledge/exists "HTTP/1.1 200 OK"
2025-10-08 15:01:44.258 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 130.79.202.31:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200
2025-10-08 15:01:44.275 | INFO | httpx._client:_send_single_request:1025 - HTTP Request: POST http://192.168.0.10:6333/collections/open-webui_knowledge/points/scroll "HTTP/1.1 200 OK"
2025-10-08 15:01:44.327 | INFO | open_webui.retrieval.utils:get_doc:142 - query_doc:result [['00131a1d-0b6d-445c-9b60-7888a2884e18', '00420443-f122-44fe-a9df-4bbfa445bf6a', '0045188d-731a-4bcf-b16c-276e8b3a6667', '00920ee1-fb13-4a36-9a86-40fd99b856e6', '00e00673-ae10-4ef5-9ea1-3c478a014981', '011cf222-3249-4d75-9012-1d7428e65158', '0129cd78-943a-4271-9fc7-c1d4f627f00b', '013c1a93-9eec-4ff5-b6c3-cace914c1059', '01884c43-deee-455e-870b-2a05ef504da3', '02173d79-ae84-4780-8117-58c8fff342e0', '0221f51a-d331-487a-ad3c-28c7be3ff9a6', '022263ea-538e-4fc9-93b7-0cb999cc1929', '0230f60b-2810-44ac-ab10-5c2ca706ea59', '026f4644-b0cc-4e2e-95b5-cff3ed189d9a', '0286459c-8728-4b7d-b62f-a4a4be5a5e06', '028cebb7-0939-4def-9b01-5cd8622b33d6', '02c7cada-0082-4b3c-8df4-ef2db7f3f1cf', '02f87cdc-e2bb-49b4-aae4-9aa2ca754a82', '02f8c979-514d-4943-8256-934a7b625867', '03256cd4-dd22-47cf-8dbb-33c43c252de5', '0348dd1b-e38b-481d-bced-c40ac803dd70', '03654166-66c5-4ee2-864f-6b8291869aea', '0379fbb5-87d6-45bb-b440-6122f4894b85', '038d6cd6-4b4f-47ad-a283-4a603b590787', '039eed9b-18a6-4b4e-b56b-f1841d12913c', '03a64412-9dfe-474c-83a3-21ecacd0d570', '03ad3696-66e8-452f-9efb-e90bbc506f12', '03b4763e-7f9a-400d-8880-4e98b0795074', '0441cd23-543a-43ea-9d58-de6964311380', '04611d17-a0bc-4b9f-9d85-9c501c51d293', '0495519a-c60b-4dcf-99af-a387794d7ca0', '04ac7837-c528-45ce-a7b2-5f58f0738451', '04f2faf5-f87d-45f2-806e-e2a3508fd698', '050dccd8-f8e4-457f-b94c-da2728f38ea1', '05344183-40db-4d63-844d-a278861f427d', '054425dc-bb14-4721-8ce7-661a3834038d', '054604e6-4547-4862-9424-8791295ad209', '05767db4-89dc-495f-8a54-f85ff67bfd7c', '06248779-b969-4c61-9d2a-ed7080e6a0ff', '062b3ecc-aa79-4ea1-ae99-fb604fb495b6', '0646bc2a-c28a-4133-9545-e3da92626dba', '064b38af-babc-4fc1-9a62-ee49f900e537', '065be188-3bec-4938-888f-2085468860f2', '065e1553-9f7c-45e0-a787-b96da2df02c9', '066167a1-11bf-4e60-8c99-b0f01f5d0428', '06a463fe-4afe-47d4-93c1-4154594d7f58', '06a7c19d-360d-4e6e-ac7d-fd992b84f08b', '06ad7321-9bdf-42ad-b097-3f2b7f8879c5', '06d91a3b-4f67-45bf-95a0-ff1b6d7ad088', '06fd2e12-0f0d-4d2c-967e-1c55a88ff1d5', '0728a0ee-848f-473f-8f40-e6568d0d9795', '0728c4ea-ce9d-4f4a-83d5-f4f8a85391a4', '07342af8-d770-45a9-8e93-c85925259bb9', '074e5050-f6f8-4b2e-a6aa-c70f54f61f15', '07631e0c-f8d8-4303-8dd9-48e790892a8e', '076b7fe3-27e0-4b72-a709-193741abe399', '0781a0af-602e-4117-9bea-ff21085e3e6d', '0798541e-b4d3-447d-8658-ef25e0faf534', '07a2cf0d-6e4c-4c65-9d43-667d405f88c6', '07dc9aa0-10f6-4d59-926f-23babd8482a2', '080844af-74ed-477b-8372-e8c728765d32', '082ecae5-b27b-429f-9492-bf82d1f1cb42', '0856f34b-6ce2-4d10-9a0f-ab27a1ec61e1', '0899abc4-bba7-4699-8ec3-e0a1605be42e', '089b5abb-4df8-4cf2-9066-5f61533d8b8a', '08d2148d-2972-4b8f-b1ea-07f87d69bcc5', '0956a9ed-0550-4551-87ab-b95c9707bbc9', '095c8ad7-c63c-47b3-bb77-cbac9d3dab66'
.....
}
76292 lines
Additional Information
No response
@athoik commented on GitHub (Oct 8, 2025):
Duplicate of https://github.com/open-webui/open-webui/issues/18133