[PR #14017] [MERGED] feat: read max_tokens from model config with fallback to 1000 for title and tag generation #62216

New Issue

GiteaMirror · 2026-05-06T06:13:15-05:00

GiteaMirror commented

2026-05-06 06:13:15 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/14017
Author: @athoik
Created: 5/18/2025
Status: ✅ Merged
Merged: 5/18/2025
Merged by: @tjbck

Base: dev ← Head: title_tags

📝 Commits (1)

eabdd4a feat: read max_tokens from model config with fallback to 1000 for title and tag generation

📊 Changes

1 file changed (+6 additions, -2 deletions)

View changed files

📝 backend/open_webui/routers/tasks.py (+6 -2)

📄 Description

Pull Request Checklist

Note to first-time contributors: Please open a discussion post in Discussions and describe your changes before submitting a pull request.

Before submitting, make sure you've checked the following:

Target branch: Please verify that the pull request targets the dev branch.
Description: Provide a concise description of the changes made in this pull request.
Changelog: Ensure a changelog entry following the format of Keep a Changelog is added at the bottom of the PR description.
Documentation: Have you updated relevant documentation Open WebUI Docs, or other documentation sources?
Dependencies: Are there any new dependencies? Have you updated the dependency versions in the documentation?
Testing: Have you written and run sufficient tests to validate the changes?
Code review: Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?
Prefix: To clearly categorize this pull request, prefix the pull request title using one of the following:
- BREAKING CHANGE: Significant changes that may affect compatibility
- build: Changes that affect the build system or external dependencies
- ci: Changes to our continuous integration processes or workflows
- chore: Refactor, cleanup, or other non-functional code changes
- docs: Documentation update or addition
- feat: Introduces a new feature or enhancement to the codebase
- fix: Bug fix or error correction
- i18n: Internationalization or localization changes
- perf: Performance improvement
- refactor: Code restructuring for better maintainability, readability, or scalability
- style: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.)
- test: Adding missing tests or correcting existing tests
- WIP: Work in progress, a temporary label for incomplete or ongoing work

Changelog Entry

Improves title and tag generation by using the max_tokens value from the model configuration when available, with a fallback to the previous default of 1000.

Description

This change is necessary for models like Gemini Pro that generate longer responses and require a higher token limit to successfully generate titles or tags.

Breaking Changes

BREAKING CHANGE: NONE

Additional Information

The request looks more or less like that:

{
  "model": "gemini-2.5-pro-preview-05-06",
  "top_p": 1,
  "stream": false,
  "messages": [
    {
      "role": "system",
      "content": "...."
    },
    {
      "role": "user",
      "content": "### Task:\nGenerate a concise, 3-5 word title with an emoji summarizing the chat history.\n### Guidelines:\n- The title should clearly represent the main theme or subject of the conversation.\n- Use emojis that enhance understanding of the topic, but avoid quotation marks or special formatting.\n- Write the title in the chat's primary language; default to English if multilingual.\n- Prioritize accuracy over excessive creativity; keep it clear and simple.\n- Your entire response must consist solely of the JSON object, without any introductory or concluding text.\n- The output must be a single, raw JSON object, without any markdown code fences or other encapsulating text.\n- Ensure no conversational text, affirmations, or explanations precede or follow the raw JSON output, as this will cause direct parsing failure.\n### Output:\nJSON format: { \"title\": \"your concise title here\" }\n### Examples:\n- { \"title\": \"📉 Stock Market Trends\" },\n- { \"title\": \"🍪 Perfect Chocolate Chip Recipe\" },\n- { \"title\": \"Ev... (truncated 6758 chars)"
    }
  ],
  "max_tokens": 1000,
  "temperature": 0
}

The response:

{
  "id": "chatcmpl-7990e450-9693-4c1c-9ce0-45f96154e3df",
  "model": "gemini-2.5-pro-preview-05-06",
  "usage": {
    "total_tokens": 3832,
    "prompt_tokens": 2832,
    "completion_tokens": 1000,
    "prompt_tokens_details": {
      "audio_tokens": null,
      "cached_tokens": null
    },
    "completion_tokens_details": {
      "audio_tokens": null,
      "reasoning_tokens": 1000,
      "accepted_prediction_tokens": null,
      "rejected_prediction_tokens": null
    }
  },
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "tool_calls": null,
        "function_call": null
      },
      "finish_reason": "length"
    }
  ],
  "created": 1747595646,
  "system_fingerprint": null,
  "vertex_ai_safety_results": [],
  "vertex_ai_citation_metadata": [],
  "vertex_ai_grounding_metadata": []
}

Causing the followng exception:

2025-05-18 23:09:00.333 | ERROR    | asyncio.runners:run:118 - Task exception was never retrieved
future: <Task finished name='Task-516' coro=<process_chat_response.<locals>.post_response_handler() done, defined at /home/user/open-webui/backend/open_webui/utils/middleware.py:1227> exception=AttributeError("'NoneType' object has no attribute 'find'")> - {}
Traceback (most recent call last):

> File "/home/user/open-webui/backend/open_webui/utils/middleware.py", line 2269, in post_response_handler
    await background_tasks_handler()
          └ <function process_chat_response.<locals>.background_tasks_handler at 0x7feba4033380>

  File "/home/user/open-webui/backend/open_webui/utils/middleware.py", line 1007, in background_tasks_handler
    title_string.find("{") : title_string.rfind("}") + 1
    │                        └ None
    └ None

AttributeError: 'NoneType' object has no attribute 'find'

Reading the max_tokens from model (eg 16384), title and tags generation works fine!

Contributor License Agreement

By submitting this pull request, I confirm that I have read and fully agree to the Contributor License Agreement (CLA), and I am providing my contributions under its terms.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/open-webui/pull/14017 **Author:** [@athoik](https://github.com/athoik) **Created:** 5/18/2025 **Status:** ✅ Merged **Merged:** 5/18/2025 **Merged by:** [@tjbck](https://github.com/tjbck) **Base:** `dev` ← **Head:** `title_tags` --- ### 📝 Commits (1) - [`eabdd4a`](https://github.com/open-webui/open-webui/commit/eabdd4a14059881b4a569dbb72e145d2b5e89a25) feat: read max_tokens from model config with fallback to 1000 for title and tag generation ### 📊 Changes **1 file changed** (+6 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/routers/tasks.py` (+6 -2) </details> ### 📄 Description # Pull Request Checklist ### Note to first-time contributors: Please open a discussion post in [Discussions](https://github.com/open-webui/open-webui/discussions) and describe your changes before submitting a pull request. **Before submitting, make sure you've checked the following:** - [x] **Target branch:** Please verify that the pull request targets the `dev` branch. - [x] **Description:** Provide a concise description of the changes made in this pull request. - [x] **Changelog:** Ensure a changelog entry following the format of [Keep a Changelog](https://keepachangelog.com/) is added at the bottom of the PR description. - [x] **Documentation:** Have you updated relevant documentation [Open WebUI Docs](https://github.com/open-webui/docs), or other documentation sources? - [x] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation? - [x] **Testing:** Have you written and run sufficient tests to validate the changes? - [x] **Code review:** Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards? - [x] **Prefix:** To clearly categorize this pull request, prefix the pull request title using one of the following: - **BREAKING CHANGE**: Significant changes that may affect compatibility - **build**: Changes that affect the build system or external dependencies - **ci**: Changes to our continuous integration processes or workflows - **chore**: Refactor, cleanup, or other non-functional code changes - **docs**: Documentation update or addition - **feat**: Introduces a new feature or enhancement to the codebase - **fix**: Bug fix or error correction - **i18n**: Internationalization or localization changes - **perf**: Performance improvement - **refactor**: Code restructuring for better maintainability, readability, or scalability - **style**: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.) - **test**: Adding missing tests or correcting existing tests - **WIP**: Work in progress, a temporary label for incomplete or ongoing work # Changelog Entry Improves title and tag generation by using the max_tokens value from the model configuration when available, with a fallback to the previous default of 1000. ### Description This change is necessary for models like Gemini Pro that generate longer responses and require a higher token limit to successfully generate titles or tags. ### Breaking Changes - **BREAKING CHANGE**: NONE --- ### Additional Information The request looks more or less like that: ``` { "model": "gemini-2.5-pro-preview-05-06", "top_p": 1, "stream": false, "messages": [ { "role": "system", "content": "...." }, { "role": "user", "content": "### Task:\nGenerate a concise, 3-5 word title with an emoji summarizing the chat history.\n### Guidelines:\n- The title should clearly represent the main theme or subject of the conversation.\n- Use emojis that enhance understanding of the topic, but avoid quotation marks or special formatting.\n- Write the title in the chat's primary language; default to English if multilingual.\n- Prioritize accuracy over excessive creativity; keep it clear and simple.\n- Your entire response must consist solely of the JSON object, without any introductory or concluding text.\n- The output must be a single, raw JSON object, without any markdown code fences or other encapsulating text.\n- Ensure no conversational text, affirmations, or explanations precede or follow the raw JSON output, as this will cause direct parsing failure.\n### Output:\nJSON format: { \"title\": \"your concise title here\" }\n### Examples:\n- { \"title\": \"📉 Stock Market Trends\" },\n- { \"title\": \"🍪 Perfect Chocolate Chip Recipe\" },\n- { \"title\": \"Ev... (truncated 6758 chars)" } ], "max_tokens": 1000, "temperature": 0 } ``` The response: ``` { "id": "chatcmpl-7990e450-9693-4c1c-9ce0-45f96154e3df", "model": "gemini-2.5-pro-preview-05-06", "usage": { "total_tokens": 3832, "prompt_tokens": 2832, "completion_tokens": 1000, "prompt_tokens_details": { "audio_tokens": null, "cached_tokens": null }, "completion_tokens_details": { "audio_tokens": null, "reasoning_tokens": 1000, "accepted_prediction_tokens": null, "rejected_prediction_tokens": null } }, "object": "chat.completion", "choices": [ { "index": 0, "message": { "role": "assistant", "content": null, "tool_calls": null, "function_call": null }, "finish_reason": "length" } ], "created": 1747595646, "system_fingerprint": null, "vertex_ai_safety_results": [], "vertex_ai_citation_metadata": [], "vertex_ai_grounding_metadata": [] } ``` Causing the followng exception: ``` 2025-05-18 23:09:00.333 | ERROR | asyncio.runners:run:118 - Task exception was never retrieved future: <Task finished name='Task-516' coro=<process_chat_response.<locals>.post_response_handler() done, defined at /home/user/open-webui/backend/open_webui/utils/middleware.py:1227> exception=AttributeError("'NoneType' object has no attribute 'find'")> - {} Traceback (most recent call last): > File "/home/user/open-webui/backend/open_webui/utils/middleware.py", line 2269, in post_response_handler await background_tasks_handler() └ <function process_chat_response.<locals>.background_tasks_handler at 0x7feba4033380> File "/home/user/open-webui/backend/open_webui/utils/middleware.py", line 1007, in background_tasks_handler title_string.find("{") : title_string.rfind("}") + 1 │ └ None └ None AttributeError: 'NoneType' object has no attribute 'find' ``` Reading the max_tokens from model (eg 16384), title and tags generation works fine! ### Contributor License Agreement By submitting this pull request, I confirm that I have read and fully agree to the [Contributor License Agreement (CLA)](/CONTRIBUTOR_LICENSE_AGREEMENT), and I am providing my contributions under its terms. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

GiteaMirror added the pull-request label 2026-05-06 06:13:15 -05:00

GiteaMirror closed this issue

2026-05-06 06:13:18 -05:00

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#62216