[GH-ISSUE #2735] [FEAT]: API for "/reset"? #1755

Closed
opened 2026-02-22 18:26:22 -05:00 by yindo · 1 comment
Owner

Originally created by @GPTLocalhost on GitHub (Nov 29, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2735

Originally assigned to: @shatfield4, @timothycarambat on GitHub.

What would you like to see?

http://localhost:3001/api/docs

Is there any API for sending "/reset" to clear the chat memory in workspace? I tried sending it through "/api/v1/openai/chat/completions" but it won't work. I'm currently integrating AnythingLLM with Microsoft Word like the following. It would be helpful if users can reset workspace memory in AnythingLLM from Word Add-in.

Originally created by @GPTLocalhost on GitHub (Nov 29, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2735 Originally assigned to: @shatfield4, @timothycarambat on GitHub. ### What would you like to see? > http://localhost:3001/api/docs Is there any API for sending "/reset" to clear the chat memory in workspace? I tried sending it through "/api/v1/openai/chat/completions" but it won't work. I'm currently integrating AnythingLLM with Microsoft Word like the following. It would be helpful if users can reset workspace memory in AnythingLLM from Word Add-in. * [Using Microsoft Word in multiple minds? An experiment with two workspaces in AnythingLLM.](https://medium.com/@gptlocalhost/using-microsoft-word-in-multiple-minds-an-experiment-with-two-workspaces-in-anythingllm-fb5044174b21)
yindo added the enhancementfeature request labels 2026-02-22 18:26:22 -05:00
yindo closed this issue 2026-02-22 18:26:22 -05:00
Author
Owner

@timothycarambat commented on GitHub (Dec 11, 2024):

The openai endpoints are openai compatible.
https://github.com/Mintplex-Labs/anything-llm/blob/69b672b625cc9fc8e4eba3793610b8c8c5cad46f/server/endpoints/api/openai/index.js#L143-L149

A request looks like

 messages: [
                {"role":"system", content: "You are a helpful assistant"},
                {"role":"user", content: "What is AnythingLLM?"},
                {"role":"assistant", content: "AnythingLLM is...."},
                {"role":"user", content: "Follow up question..."}
 ],
 model: "sample-workspace",
 stream: true,
temperature: 0.7

So to remove the "history" you send less messages, just like OpenAI normally.

@timothycarambat commented on GitHub (Dec 11, 2024): The openai endpoints are openai compatible. https://github.com/Mintplex-Labs/anything-llm/blob/69b672b625cc9fc8e4eba3793610b8c8c5cad46f/server/endpoints/api/openai/index.js#L143-L149 A request looks like ``` messages: [ {"role":"system", content: "You are a helpful assistant"}, {"role":"user", content: "What is AnythingLLM?"}, {"role":"assistant", content: "AnythingLLM is...."}, {"role":"user", content: "Follow up question..."} ], model: "sample-workspace", stream: true, temperature: 0.7 ``` So to remove the "history" you send less messages, just like OpenAI normally.
yindo changed title from [FEAT]: API for "/reset"? to [GH-ISSUE #2735] [FEAT]: API for "/reset"? 2026-06-05 14:42:30 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#1755