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 #2967] [BUG]: Could not respond to message. 404 status code (no body) #1893

New Issue
Closed
opened 2026-02-22 18:27:06 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:27:06 -05:00
Owner
Copy Link
Copy Source

Originally created by @luoLojic on GitHub (Jan 12, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2967

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

I am attempting to import the Semikong model into AnythingLLM using the API provided by the text-generation-webui.

I’ve successfully tested the API (http://127.0.0.1:5000/v1/chat/completions) on my text-generation-webui setup, and I am trying to use the same API in AnythingLLM

Here’s the configuration I have set in AnythingLLM:
Generic OpenAl
Base URL: http://127.0.0.1:5000/v1/chat/completions
Chat Model Name: SEMIKONG_GPTQ
Token context window: 4096
Max Tokens: 1024
However, after sending a prompt, I receive the following error:
Error: "Could not respond to message. 404 status code (no body)"

This is a python program for testing API
curl -X POST "http://localhost:5000/v1/completions" ^
-H "Content-Type: application/json" ^
-d "{ ^
"model": "gpt-3.5-turbo", ^
"prompt": "Hello, how are you?", ^
"max_tokens": 100, ^
"temperature": 0.7 ^
}"

this is reply
{
"id": "conv-1736678707471457280",
"object": "text_completion",
"created": 1736678707,
"model": "SEMIKONG_GPTQ",
"choices": [
{
"index": 0,
"finish_reason": "length",
"text": " I hope you're doing well. Today, I wanted to talk about a topic that I think is really important for all of us: self-care. Self-care is not just about taking a bubble bath or getting a massage, it's about taking care of your physical, emotional, and mental health.\nOne of the most important things you can do for your self-care is to prioritize your sleep. Sleep is essential for your body to repair and rejuvenate itself, and when you don't get enough sleep",
"logprobs": {
"top_logprobs": [{}]
}
}
],
"usage": {
"prompt_tokens": 7,
"completion_tokens": 101,
"total_tokens": 108
}
}

Are there known steps to reproduce?

No response

Originally created by @luoLojic on GitHub (Jan 12, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2967 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? I am attempting to import the [Semikong model](https://huggingface.co/pentagoniac/SEMIKONG-8b-GPTQ/tree/main) into AnythingLLM using the API provided by the [text-generation-webui.](https://github.com/oobabooga/text-generation-webui) I’ve successfully tested the API (http://127.0.0.1:5000/v1/chat/completions) on my text-generation-webui setup, and I am trying to use the same API in AnythingLLM Here’s the configuration I have set in AnythingLLM: Generic OpenAl Base URL: http://127.0.0.1:5000/v1/chat/completions Chat Model Name: SEMIKONG_GPTQ Token context window: 4096 Max Tokens: 1024 However, after sending a prompt, I receive the following error: Error: "Could not respond to message. 404 status code (no body)" This is a python program for testing API curl -X POST "http://localhost:5000/v1/completions" ^ -H "Content-Type: application/json" ^ -d "{ ^ \"model\": \"gpt-3.5-turbo\", ^ \"prompt\": \"Hello, how are you?\", ^ \"max_tokens\": 100, ^ \"temperature\": 0.7 ^ }" this is reply { "id": "conv-1736678707471457280", "object": "text_completion", "created": 1736678707, "model": "SEMIKONG_GPTQ", "choices": [ { "index": 0, "finish_reason": "length", "text": " I hope you're doing well. Today, I wanted to talk about a topic that I think is really important for all of us: self-care. Self-care is not just about taking a bubble bath or getting a massage, it's about taking care of your physical, emotional, and mental health.\nOne of the most important things you can do for your self-care is to prioritize your sleep. Sleep is essential for your body to repair and rejuvenate itself, and when you don't get enough sleep", "logprobs": { "top_logprobs": [{}] } } ], "usage": { "prompt_tokens": 7, "completion_tokens": 101, "total_tokens": 108 } } ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:27:06 -05:00
yindo closed this issue 2026-02-22 18:27:06 -05:00
yindo commented 2026-02-22 18:27:06 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jan 13, 2025):

TextWebGenUI should return OpenAi Comptible responses - that is not one? The choices array is missing message and content

{
"choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "\n\nHello there, how may I assist you today?",
    },
    "logprobs": null,
    "finish_reason": "stop"
  }],
}

How is it this model responds with a different response format? The normal behavior is OpenAI formatted - is this a fork?
https://github.com/oobabooga/text-generation-webui/blob/main/docs/12%20-%20OpenAI%20API.md#chat-completions

@timothycarambat commented on GitHub (Jan 13, 2025): TextWebGenUI should return _OpenAi Comptible_ responses - that is not one? The `choices` array is missing `message` and `content` ```json { "choices": [{ "index": 0, "message": { "role": "assistant", "content": "\n\nHello there, how may I assist you today?", }, "logprobs": null, "finish_reason": "stop" }], } ``` How is it this model responds with a different response format? The normal behavior is OpenAI formatted - is this a fork? https://github.com/oobabooga/text-generation-webui/blob/main/docs/12%20-%20OpenAI%20API.md#chat-completions
yindo changed title from [BUG]: Could not respond to message. 404 status code (no body) to [GH-ISSUE #2967] [BUG]: Could not respond to message. 404 status code (no body) 2026-06-05 14:43:18 -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#1893
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?