Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 22:23:50 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #3046] [BUG]: Can't change the output token limit with novita ai #1949

New Issue
Closed
opened 2026-02-22 18:27:23 -05:00 by yindo · 2 comments
yindo commented 2026-02-22 18:27:23 -05:00
Owner
Copy Link
Copy Source

Originally created by @nidupb on GitHub (Jan 28, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3046

Originally assigned to: @shatfield4 on GitHub.

How are you running AnythingLLM?

Docker (local)

What happened?

When experimenting with deepseek, Novita seems to limit the token output to 2048 when it should go up to 8196.

Novita provide an example of API implementation with the base limit :

from openai import OpenAI
  
client = OpenAI(
    base_url="https://api.novita.ai/v3/openai",
    api_key="<YOUR Novita AI API Key>",
)

model = "deepseek/deepseek-r1"
stream = True # or False
max_tokens = 2048
system_content = """Be a helpful assistant"""
temperature = 1
top_p = 1
min_p = 0
top_k = 50
presence_penalty = 0
frequency_penalty = 0
repetition_penalty = 1
response_format = { "type": "text" }

chat_completion_res = client.chat.completions.create(
    model=model,
    messages=[
        {
            "role": "system",
            "content": system_content,
        },
        {
            "role": "user",
            "content": "Hi there!",
        }
    ],
    stream=stream,
    max_tokens=max_tokens,
    temperature=temperature,
    top_p=top_p,
    presence_penalty=presence_penalty,
    frequency_penalty=frequency_penalty,
    response_format=response_format,
    extra_body={
      "top_k": top_k,
      "repetition_penalty": repetition_penalty,
      "min_p": min_p
    }
  )

if stream:
    for chunk in chat_completion_res:
        print(chunk.choices[0].delta.content or "", end="")
else:
    print(chat_completion_res.choices[0].message.content)

Are there known steps to reproduce?

Ask any complex issue that'll likely prompt an output above 2048 tokens

Originally created by @nidupb on GitHub (Jan 28, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3046 Originally assigned to: @shatfield4 on GitHub. ### How are you running AnythingLLM? Docker (local) ### What happened? When experimenting with deepseek, Novita seems to limit the token output to 2048 when it should go up to 8196. Novita provide an example of API implementation with the base limit : ``` from openai import OpenAI client = OpenAI( base_url="https://api.novita.ai/v3/openai", api_key="<YOUR Novita AI API Key>", ) model = "deepseek/deepseek-r1" stream = True # or False max_tokens = 2048 system_content = """Be a helpful assistant""" temperature = 1 top_p = 1 min_p = 0 top_k = 50 presence_penalty = 0 frequency_penalty = 0 repetition_penalty = 1 response_format = { "type": "text" } chat_completion_res = client.chat.completions.create( model=model, messages=[ { "role": "system", "content": system_content, }, { "role": "user", "content": "Hi there!", } ], stream=stream, max_tokens=max_tokens, temperature=temperature, top_p=top_p, presence_penalty=presence_penalty, frequency_penalty=frequency_penalty, response_format=response_format, extra_body={ "top_k": top_k, "repetition_penalty": repetition_penalty, "min_p": min_p } ) if stream: for chunk in chat_completion_res: print(chunk.choices[0].delta.content or "", end="") else: print(chat_completion_res.choices[0].message.content) ``` ### Are there known steps to reproduce? Ask any complex issue that'll likely prompt an output above 2048 tokens
yindo added the possible buginvestigating labels 2026-02-22 18:27:23 -05:00
yindo closed this issue 2026-02-22 18:27:23 -05:00
yindo commented 2026-02-22 18:27:23 -05:00
Author
Owner
Copy Link
Copy Source

@Karasowl commented on GitHub (Feb 4, 2025):

I wanted to report that I reproduced the issue using the standard AnythingLLM setup (not running in Docker) with the deepseek model via Novita AI. The response is still truncated.

Image

@Karasowl commented on GitHub (Feb 4, 2025): I wanted to report that I reproduced the issue using the standard AnythingLLM setup (not running in Docker) with the deepseek model via Novita AI. **The response is still truncated**. ![Image](https://github.com/user-attachments/assets/4e1b2ba3-185c-4cb9-a3a2-5a8ba919dda3)
yindo commented 2026-02-22 18:27:23 -05:00
Author
Owner
Copy Link
Copy Source

@shatfield4 commented on GitHub (Feb 13, 2025):

This seems that it could have been an issue with their API but as of today, I have just tested this using Deepseek models from Novita and I am able to get a response of close to 8000 tokens without being truncated. If you can provide more steps on how to replicate this we would be happy to reopen and create a fix for it.

@shatfield4 commented on GitHub (Feb 13, 2025): This seems that it could have been an issue with their API but as of today, I have just tested this using Deepseek models from Novita and I am able to get a response of close to 8000 tokens without being truncated. If you can provide more steps on how to replicate this we would be happy to reopen and create a fix for it.
yindo changed title from [BUG]: Can't change the output token limit with novita ai to [GH-ISSUE #3046] [BUG]: Can't change the output token limit with novita ai 2026-06-05 14:43:38 -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 investigating 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#1949
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?