Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #4979] [FEAT]: Add Reasoning/Non-Reasoning Mode Toggle for Hybrid Reasoning Models (DeepSeek, Qwen, etc.) #3124

New Issue
Closed
opened 2026-02-22 18:32:43 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:32:43 -05:00
Owner
Copy Link
Copy Source

Originally created by @momusticks on GitHub (Feb 10, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4979

What would you like to see?

Feature Request: Hybrid Reasoning Toggle & Native Alibaba Cloud Bailian Support

Summary

Add a "Deep Thinking" mode toggle for hybrid reasoning models (DeepSeek, Qwen, etc.) and native support for Alibaba Cloud Bailian Platform (DashScope).

1. Hybrid Reasoning Mode Toggle

Request: Add a "🧠 Thinking Mode" toggle in chat interface to switch between reasoning and non-reasoning modes for models like DeepSeek (R1/V3), Qwen , and Gemini.

Value: Eliminates the need to switch models or modify prompts manually, improving UX for complex workflows.

Implementation:

  • DeepSeek: Switch model name (deepseek-chat ↔ deepseek-reasoner) or use enable_reasoning parameter
  • Qwen: Prepend /think or /no_think tags to messages
  • UI: Button visible only for supported models; allow default setting per workspace

2. Native Alibaba Cloud Bailian Support

Request: Add "Alibaba Cloud Bailian" (Model Studio / DashScope) as a native LLM provider option instead of configuring via Generic OpenAI.

Value: The Qwen family (Qwen3 Max、Qwen3 next) represents one of the world's leading open-source model series, achieving top rankings on global benchmarks like Chatbot Arena and various reasoning evaluations. Bailian Platform serves as the official managed service for Qwen models, offering OpenAI-compatible APIs with global availability (Singapore, Virginia, Beijing regions). Native integration would provide developers worldwide with streamlined access to these state-of-the-art models alongside existing options like OpenAI, Anthropic, and DeepSeek.

Configuration:

  • Base URL: https://dashscope.aliyuncs.com/compatible-mode/v1 (or dashscope-intl.aliyuncs.com for international users)
  • Available Regions: Singapore (Global), Virginia (North America), Beijing (Asia-Pacific)
  • Key Models: qwen-max, qwen-plus, qwen-coder, deepseek-r1 (via Bailian)

Thank you for maintaining this excellent open-source project! These additions would strengthen AnythingLLM's support for the global open-source LLM ecosystem.

Originally created by @momusticks on GitHub (Feb 10, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4979 ### What would you like to see? ## Feature Request: Hybrid Reasoning Toggle & Native Alibaba Cloud Bailian Support ### Summary Add a "Deep Thinking" mode toggle for hybrid reasoning models (DeepSeek, Qwen, etc.) and native support for Alibaba Cloud Bailian Platform (DashScope). --- ### 1. Hybrid Reasoning Mode Toggle **Request**: Add a "🧠 Thinking Mode" toggle in chat interface to switch between reasoning and non-reasoning modes for models like DeepSeek (R1/V3), Qwen , and Gemini. **Value**: Eliminates the need to switch models or modify prompts manually, improving UX for complex workflows. **Implementation**: - DeepSeek: Switch model name (`deepseek-chat` ↔ `deepseek-reasoner`) or use `enable_reasoning` parameter - Qwen: Prepend `/think` or `/no_think` tags to messages - UI: Button visible only for supported models; allow default setting per workspace --- ### 2. Native Alibaba Cloud Bailian Support **Request**: Add "Alibaba Cloud Bailian" (Model Studio / DashScope) as a native LLM provider option instead of configuring via Generic OpenAI. **Value**: The Qwen family (Qwen3 Max、Qwen3 next) represents one of the world's leading open-source model series, achieving top rankings on global benchmarks like Chatbot Arena and various reasoning evaluations. Bailian Platform serves as the official managed service for Qwen models, offering OpenAI-compatible APIs with global availability (Singapore, Virginia, Beijing regions). Native integration would provide developers worldwide with streamlined access to these state-of-the-art models alongside existing options like OpenAI, Anthropic, and DeepSeek. **Configuration**: - Base URL: `https://dashscope.aliyuncs.com/compatible-mode/v1` (or `dashscope-intl.aliyuncs.com` for international users) - Available Regions: Singapore (Global), Virginia (North America), Beijing (Asia-Pacific) - Key Models: qwen-max, qwen-plus, qwen-coder, deepseek-r1 (via Bailian) --- Thank you for maintaining this excellent open-source project! These additions would strengthen AnythingLLM's support for the global open-source LLM ecosystem.
yindo added the enhancementfeature request labels 2026-02-22 18:32:43 -05:00
yindo commented 2026-02-22 18:32:44 -05:00
Author
Owner
Copy Link
Copy Source

@bittoby commented on GitHub (Feb 18, 2026):

@timothycarambat @shatfield4 I'm interested in this project! Can I pick this up? I can do it perfectly

@bittoby commented on GitHub (Feb 18, 2026): @timothycarambat @shatfield4 I'm interested in this project! Can I pick this up? I can do it perfectly
yindo changed title from [FEAT]: Add Reasoning/Non-Reasoning Mode Toggle for Hybrid Reasoning Models (DeepSeek, Qwen, etc.) to [GH-ISSUE #4979] [FEAT]: Add Reasoning/Non-Reasoning Mode Toggle for Hybrid Reasoning Models (DeepSeek, Qwen, etc.) 2026-06-05 14:50:26 -04:00
yindo closed this issue 2026-06-05 14:50:26 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label enhancement feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#3124
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?