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 #5616] [BUG]: Error message: "error: 400 status code (no body) Error: 400 status code (no body)" #5196

New Issue
Closed
opened 2026-06-05 14:52:34 -04:00 by yindo · 2 comments
yindo commented 2026-06-05 14:52:34 -04:00
Owner
Copy Link
Copy Source

Originally created by @attutude on GitHub (May 12, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5616

How are you running AnythingLLM?

Docker (remote machine)

What happened?

I discovered that in the workspace, when the vector database contains a large amount of vector data (e.g., 1700 or 3000 vectors in the workspace), sending messages with a low token count does not throw any errors and the message response works normally. However, when sending messages with a high token count (more than 10,000 tokens), the following error is thrown:

[backend] info: [TokenManager] Returning existing instance for model: DeepSeek-R1-LOCAL
[backend] error: 400 status code (no body) Error: 400 status code (no body)
at APIError.generate (/app/server/node_modules/openai/error.js:45:20)
at OpenAI.makeStatusError (/app/server/node_modules/openai/core.js:263:33)
at OpenAI.makeRequest (/app/server/node_modules/openai/core.js:306:30)
at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
at async LLMPerformanceMonitor.measureStream (/app/server/utils/helpers/chat/LLMPerformanceMonitor.js:67:20)
at async GenericOpenAiLLM.streamGetChatCompletion (/app/server/utils/AiProviders/genericOpenAi/index.js:195:35)
at async Object.streamChat (/app/server/utils/chats/apiChatHandler.js:665:20)
at async /app/server/endpoints/api/workspaceThread/index.js:594:9

Are there known steps to reproduce?

No response

LLM Provider & Model (if applicable)

No response

Embedder Provider & Model (if applicable)

No response

Originally created by @attutude on GitHub (May 12, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5616 ### How are you running AnythingLLM? Docker (remote machine) ### What happened? I discovered that in the workspace, when the vector database contains a large amount of vector data (e.g., 1700 or 3000 vectors in the workspace), sending messages with a low token count does not throw any errors and the message response works normally. However, when sending messages with a high token count (more than 10,000 tokens), the following error is thrown: [backend] info: [TokenManager] Returning existing instance for model: DeepSeek-R1-LOCAL [backend] error: 400 status code (no body) Error: 400 status code (no body) at APIError.generate (/app/server/node_modules/openai/error.js:45:20) at OpenAI.makeStatusError (/app/server/node_modules/openai/core.js:263:33) at OpenAI.makeRequest (/app/server/node_modules/openai/core.js:306:30) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async LLMPerformanceMonitor.measureStream (/app/server/utils/helpers/chat/LLMPerformanceMonitor.js:67:20) at async GenericOpenAiLLM.streamGetChatCompletion (/app/server/utils/AiProviders/genericOpenAi/index.js:195:35) at async Object.streamChat (/app/server/utils/chats/apiChatHandler.js:665:20) at async /app/server/endpoints/api/workspaceThread/index.js:594:9 <!-- Failed to upload "image.png" --> ### Are there known steps to reproduce? _No response_ ### LLM Provider & Model (if applicable) _No response_ ### Embedder Provider & Model (if applicable) _No response_
yindo added the possible bugneeds info / can't replicate labels 2026-06-05 14:52:34 -04:00
yindo closed this issue 2026-06-05 14:52:35 -04:00
yindo commented 2026-06-05 14:52:35 -04:00
Author
Owner
Copy Link
Copy Source

@attutude commented on GitHub (May 12, 2026):

When the vector database in the workspace contains only a small amount of vector data, sending messages with a high token count (more than 10,000 tokens) does not trigger any errors, and the message response is normal.

<!-- gh-comment-id:4429210169 --> @attutude commented on GitHub (May 12, 2026): When the vector database in the workspace contains only a small amount of vector data, sending messages with a high token count (more than 10,000 tokens) does not trigger any errors, and the message response is normal.
yindo commented 2026-06-05 14:52:35 -04:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (May 12, 2026):

Can you disclose what the generic connector you are using is? This seems like a simple context limit overflow issue and that the context window being used in AnythingLLM is higher than what the service can provide and so it 400's based on the request since there are too many tokens in the request to process.

<!-- gh-comment-id:4435087300 --> @timothycarambat commented on GitHub (May 12, 2026): Can you disclose what the generic connector you are using is? This seems like a simple context limit overflow issue and that the context window being used in AnythingLLM is higher than what the service can provide and so it 400's based on the request since there are too many tokens in the request to process.
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 needs info / can't replicate 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#5196
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?