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 #2302] [BUG]: Error occurred while streaming response. Streaming error #1502

New Issue
Closed
opened 2026-02-22 18:25:09 -05:00 by yindo · 4 comments
yindo commented 2026-02-22 18:25:09 -05:00
Owner
Copy Link
Copy Source

Originally created by @saisandeepbalbari on GitHub (Sep 17, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2302

How are you running AnythingLLM?

Docker (remote machine)

What happened?

I'm using OLLAMA's nomic-embed-text as the embedding model and llama3.1:8b as the LLM.

After I upload the documents, when asked a question, it is generating the sentence partially and then giving the streaming error

Screenshot 2024-09-17 at 12 32 16 PM

On checking the logs of the docker are as below:

[Event Logged] - workspace_documents_added
[OllamaEmbedder] Embedding 1 chunks of text with nomic-embed-text:latest.
[STREAM ABORTED] Client requested to abort stream. Exiting LLM stream handler early.
[TELEMETRY SENT] {
event: 'sent_chat',
distinctId: 'xxxxxxxx-xxxx-xxxxx-xxxxxx-xxxxxxxxxxxxxxxx',
properties: {
multiUserMode: false,
LLMSelection: 'ollama',
Embedder: 'ollama',
VectorDbSelection: 'lancedb',
runtime: 'docker'
}
}
[Event Logged] - sent_chat

Are there known steps to reproduce?

No response

Originally created by @saisandeepbalbari on GitHub (Sep 17, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2302 ### How are you running AnythingLLM? Docker (remote machine) ### What happened? I'm using OLLAMA's nomic-embed-text as the embedding model and llama3.1:8b as the LLM. After I upload the documents, when asked a question, it is generating the sentence partially and then giving the streaming error <img width="795" alt="Screenshot 2024-09-17 at 12 32 16 PM" src="https://github.com/user-attachments/assets/9735b38d-3f48-4236-bdd3-513c411d19f8"> On checking the logs of the docker are as below: [Event Logged] - workspace_documents_added [OllamaEmbedder] Embedding 1 chunks of text with nomic-embed-text:latest. [STREAM ABORTED] Client requested to abort stream. Exiting LLM stream handler early. [TELEMETRY SENT] { event: 'sent_chat', distinctId: 'xxxxxxxx-xxxx-xxxxx-xxxxxx-xxxxxxxxxxxxxxxx', properties: { multiUserMode: false, LLMSelection: 'ollama', Embedder: 'ollama', VectorDbSelection: 'lancedb', runtime: 'docker' } } [Event Logged] - sent_chat ### Are there known steps to reproduce? _No response_
yindo added the needs info / can't replicate label 2026-02-22 18:25:09 -05:00
yindo closed this issue 2026-02-22 18:25:09 -05:00
yindo commented 2026-02-22 18:25:09 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Sep 17, 2024):

Client requested to abort stream. Exiting LLM stream handler early.

This is certainly something on the client side then which would occur from:

  • a websocket close
  • Browser connection to server interrupted (page reload)

What does frontend inspector > source show? Should be some relevant error there since this is the client dropping the connection and not the server aborting the connection

@timothycarambat commented on GitHub (Sep 17, 2024): > Client requested to abort stream. Exiting LLM stream handler early. This is certainly something on the client side then which would occur from: - a websocket close - Browser connection to server interrupted (page reload) What does frontend inspector > source show? Should be some relevant error there since this is the client dropping the connection and not the server aborting the connection
yindo commented 2026-02-22 18:25:09 -05:00
Author
Owner
Copy Link
Copy Source

@dimonier commented on GitHub (Sep 27, 2024):

I experience the same issue running AnythingLLM on local Windows 10 machine using Llama3.1 8B with default settings.

Everything works fine, but after I added a document to the workspace settings or uploaded a document via chat, the next chat message gives this result: "An error occurred while streaming response. network error".

P.S. Tried to open dev tools with Ctrl+Shift+I to take a look under the hood, but no result. Probably AnythingLLM is built not on Electron.

@dimonier commented on GitHub (Sep 27, 2024): I experience the same issue running AnythingLLM on local Windows 10 machine using Llama3.1 8B with default settings. Everything works fine, but after I added a document to the workspace settings or uploaded a document via chat, the next chat message gives this result: "An error occurred while streaming response. network error". P.S. Tried to open dev tools with Ctrl+Shift+I to take a look under the hood, but no result. Probably AnythingLLM is built not on Electron.
yindo commented 2026-02-22 18:25:09 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Sep 27, 2024):

@dimonier

Probably AnythingLLM is built not on Electron.

it is - logs are here. Frontend debug would not even help in this instance anyways.

Related documentation to solve this type of error
https://docs.anythingllm.com/fetch-failed-on-upload

@timothycarambat commented on GitHub (Sep 27, 2024): @dimonier > Probably AnythingLLM is built not on Electron. it is - [logs are here](https://docs.anythingllm.com/installation-desktop/debug). Frontend debug would not even help in this instance anyways. Related documentation to solve this type of error https://docs.anythingllm.com/fetch-failed-on-upload
yindo commented 2026-02-22 18:25:09 -05:00
Author
Owner
Copy Link
Copy Source

@dimonier commented on GitHub (Sep 27, 2024):

Related documentation to solve this type of error https://docs.anythingllm.com/fetch-failed-on-upload

Thank you so much for the quick response!

I use older Xeon that does not support AVX2 (and therefore embedded LanceDB).
Switching to chromadb solved the problem for me.

@dimonier commented on GitHub (Sep 27, 2024): > Related documentation to solve this type of error https://docs.anythingllm.com/fetch-failed-on-upload Thank you so much for the quick response! I use older Xeon that does not support AVX2 (and therefore embedded LanceDB). [Switching to chromadb](https://cookbook.chromadb.dev/running/running-chroma/#chroma-cli) solved the problem for me.
yindo changed title from [BUG]: Error occurred while streaming response. Streaming error to [GH-ISSUE #2302] [BUG]: Error occurred while streaming response. Streaming error 2026-06-05 14:41:07 -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 needs info / can't replicate
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#1502
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?