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 #3177] [BUG]: Using the deepseek-R1 API from other providers, without a thinking process. #2043

New Issue
Closed
opened 2026-02-22 18:27:53 -05:00 by yindo · 2 comments
yindo commented 2026-02-22 18:27:53 -05:00
Owner
Copy Link
Copy Source

Originally created by @Rolling-Hol on GitHub (Feb 11, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3177

How are you running AnythingLLM?

Docker (local)

What happened?

I configure the new API via Generic OpenAI. This API is the deepseek-R1 API from other providers(e.g. siliconflow); after configuring it, I conduct conversations. It only outputs the final result without a thinking process.

Image

Are there known steps to reproduce?

No response

Originally created by @Rolling-Hol on GitHub (Feb 11, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3177 ### How are you running AnythingLLM? Docker (local) ### What happened? I configure the new API via Generic OpenAI. This API is the deepseek-R1 API from other providers(e.g. siliconflow); after configuring it, I conduct conversations. It only outputs the final result without a thinking process. ![Image](https://github.com/user-attachments/assets/b9d2eb26-038e-4a68-a421-5679c4d15805) ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:27:53 -05:00
yindo closed this issue 2026-02-22 18:27:53 -05:00
yindo commented 2026-02-22 18:27:53 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Feb 11, 2025):

API via Generic OpenAI.

The generic OpenAI handler does not parse think or reasoning since it comes in as a different stream from content - which is what we directly access.

Since the Generic Connector is, well, generic it would be ambitious to assume the connector would indeed work using the same Openai reasoning key.

Most providers return thoughts outside of content and we dont handle it since we dont know what response key is used. What provider are you using through the Generic OpenAI connector?

@timothycarambat commented on GitHub (Feb 11, 2025): > API via Generic OpenAI. The generic OpenAI handler does not parse `think` or `reasoning` since it comes in as a different stream from `content` - which is what we directly access. Since the Generic Connector is, well, generic it would be ambitious to assume the connector would indeed work using the same Openai `reasoning` key. Most providers return thoughts outside of `content` and we dont handle it since we dont know what response key is used. What provider are you using through the Generic OpenAI connector?
yindo commented 2026-02-22 18:27:53 -05:00
Author
Owner
Copy Link
Copy Source

@Rolling-Hol commented on GitHub (Feb 12, 2025):

API via Generic OpenAI.

The generic OpenAI handler does not parse think or reasoning since it comes in as a different stream from content - which is what we directly access.

Since the Generic Connector is, well, generic it would be ambitious to assume the connector would indeed work using the same Openai reasoning key.

Most providers return thoughts outside of content and we dont handle it since we dont know what response key is used. What provider are you using through the Generic OpenAI connector?

I'm using is Siliconflow (https://www.siliconflow.cn/). So, can I achieve the goal of adding my own Siliconflow connector by modifying some of the code?

@Rolling-Hol commented on GitHub (Feb 12, 2025): > > API via Generic OpenAI. > > The generic OpenAI handler does not parse `think` or `reasoning` since it comes in as a different stream from `content` - which is what we directly access. > > Since the Generic Connector is, well, generic it would be ambitious to assume the connector would indeed work using the same Openai `reasoning` key. > > Most providers return thoughts outside of `content` and we dont handle it since we dont know what response key is used. What provider are you using through the Generic OpenAI connector? I'm using is Siliconflow [(https://www.siliconflow.cn/)](https://www.siliconflow.cn/). So, can I achieve the goal of adding my own Siliconflow connector by modifying some of the code?
yindo changed title from [BUG]: Using the deepseek-R1 API from other providers, without a thinking process. to [GH-ISSUE #3177] [BUG]: Using the deepseek-R1 API from other providers, without a thinking process. 2026-06-05 14:44:12 -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 possible bug
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#2043
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?