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 #5624] [BUG]: An error occurred while streaming response. network error #2314

New Issue
Closed
opened 2026-02-22 18:29:08 -05:00 by yindo · 5 comments
yindo commented 2026-02-22 18:29:08 -05:00
Owner
Copy Link
Copy Source

Originally created by @Loopho66 on GitHub (May 13, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5624

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

Hi
I launch the app from a terminal under Debian Trixie (32GB RAM, i7-3770K CPU, no GPU).
This is the output i get on the terminal:

luca@Mithrandir:$ ./AnythingLLMDesktop.AppImage &
[1] 31916
luca@Mithrandir:$ [Preferences] preference config stored at /home/luca/.config/anythingllm-desktop/config.json
MESA-INTEL: warning: Ivy Bridge Vulkan support is incomplete
libva error: /usr/lib/x86_64-linux-gnu/dri/iHD_drv_video.so init failed
[PrismaHelper: linux] Setting Prisma Client output directory to userData. {
clientOutputPath: '/home/luca/.config/anythingllm-desktop/storage/.prisma/client'
}
[PrismaHelper] Query engine for debian-openssl-3.0.x already exists, skipping download.
[PrismaHelper] Schema engine for debian-openssl-3.0.x already exists, skipping download.
Prisma schema loaded from prisma/schema.prisma
Datasource "db": SQLite database "anythingllm.db" at "file:/home/luca/.config/anythingllm-desktop/storage/anythingllm.db"

Already in sync, no schema change or pending migration was found.

✔ Generated Prisma Client (v5.3.1) to ./../../../../home/luca/.config/anythingll
m-desktop/storage/.prisma/client in 365ms

Prisma schema loaded from prisma/schema.prisma

✔ Generated Prisma Client (v5.3.1) to ./../../../../home/luca/.config/anythingllm-desktop/storage/.prisma/client in 306ms

Start using Prisma Client in Node.js (See: https://pris.ly/d/client)

import { PrismaClient } from '../../../../home/luca/.config/anythingllm-desktop/storage/.prisma/client'
const prisma = new PrismaClient()

or start using Prisma Client at the edge (See: https://pris.ly/d/accelerate)

import { PrismaClient } from '../../../../home/luca/.config/anythingllm-desktop/storage/.prisma/client/edge'
const prisma = new PrismaClient()

See other ways of importing Prisma Client: http://pris.ly/d/importing-client

[OllamaProcessManager] Ollama will bind on port 11434 when booted.
[ManualBrowser] Listening for IPC messages from main renderer process!
[MeetingAssistantHelper.DownloadHelper] DownloadHelper initialized.
[MeetingAssistantHelper] Initialized & Registered
[meeting-assistant] info: Initialized & Registered
[MeetingAssistantHelper.MicrophoneMonitorManager] Microphone input change monitoring is not supported on Linux
[FFmpegHelper.Bootstrap] Bootstrap is not supported on this platform.
[FFmpegHelper] Bootstrap is not supported on this platform.
[ffmpeg] info: Bootstrap is not supported on this platform.
[Preferences] Startup window preference: main
[Preferences] Will load window with last known bounds.
[TrayManager] System tray initialized
[MeetingAssistantHelper] FFMPEG bootstrapped successfully!
[meeting-assistant] info: FFMPEG bootstrapped successfully!
[OllamaProcessManager] SINGLETON LOCK: Using existing OllamaProcessManager.
[OllamaProcessManager] [nix] Ollama subprocess running. Port 11434. PID 32155.

The GUI opens regularly, but if I ask a question ("what's the time?") I get "An error occurred while streaming response. network error". At this point, hitting "Open settings", opens an empty window and the spinner stays forever.
If I ask another question, I get again the network error.

What can I do?
Thanks so much for your help
Luca

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 @Loopho66 on GitHub (May 13, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5624 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? Hi I launch the app from a terminal under Debian Trixie (32GB RAM, i7-3770K CPU, no GPU). This is the output i get on the terminal: luca@Mithrandir:~$ ./AnythingLLMDesktop.AppImage & [1] 31916 luca@Mithrandir:~$ [Preferences] preference config stored at /home/luca/.config/anythingllm-desktop/config.json MESA-INTEL: warning: Ivy Bridge Vulkan support is incomplete libva error: /usr/lib/x86_64-linux-gnu/dri/iHD_drv_video.so init failed [PrismaHelper: linux] Setting Prisma Client output directory to userData. { clientOutputPath: '/home/luca/.config/anythingllm-desktop/storage/.prisma/client' } [PrismaHelper] Query engine for debian-openssl-3.0.x already exists, skipping download. [PrismaHelper] Schema engine for debian-openssl-3.0.x already exists, skipping download. Prisma schema loaded from prisma/schema.prisma Datasource "db": SQLite database "anythingllm.db" at "file:/home/luca/.config/anythingllm-desktop/storage/anythingllm.db" Already in sync, no schema change or pending migration was found. ✔ Generated Prisma Client (v5.3.1) to ./../../../../home/luca/.config/anythingll m-desktop/storage/.prisma/client in 365ms Prisma schema loaded from prisma/schema.prisma ✔ Generated Prisma Client (v5.3.1) to ./../../../../home/luca/.config/anythingllm-desktop/storage/.prisma/client in 306ms Start using Prisma Client in Node.js (See: https://pris.ly/d/client) ``` import { PrismaClient } from '../../../../home/luca/.config/anythingllm-desktop/storage/.prisma/client' const prisma = new PrismaClient() ``` or start using Prisma Client at the edge (See: https://pris.ly/d/accelerate) ``` import { PrismaClient } from '../../../../home/luca/.config/anythingllm-desktop/storage/.prisma/client/edge' const prisma = new PrismaClient() ``` See other ways of importing Prisma Client: http://pris.ly/d/importing-client [OllamaProcessManager] Ollama will bind on port 11434 when booted. [ManualBrowser] Listening for IPC messages from main renderer process! [MeetingAssistantHelper.DownloadHelper] DownloadHelper initialized. [MeetingAssistantHelper] Initialized & Registered [meeting-assistant] info: Initialized & Registered [MeetingAssistantHelper.MicrophoneMonitorManager] Microphone input change monitoring is not supported on Linux [FFmpegHelper.Bootstrap] Bootstrap is not supported on this platform. [FFmpegHelper] Bootstrap is not supported on this platform. [ffmpeg] info: Bootstrap is not supported on this platform. [Preferences] Startup window preference: main [Preferences] Will load window with last known bounds. [TrayManager] System tray initialized [MeetingAssistantHelper] FFMPEG bootstrapped successfully! [meeting-assistant] info: FFMPEG bootstrapped successfully! [OllamaProcessManager] SINGLETON LOCK: Using existing OllamaProcessManager. [OllamaProcessManager] [nix] Ollama subprocess running. Port 11434. PID 32155. The GUI opens regularly, but if I ask a question ("what's the time?") I get "An error occurred while streaming response. network error". At this point, hitting "Open settings", opens an empty window and the spinner stays forever. If I ask another question, I get again the network error. What can I do? Thanks so much for your help Luca ### 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 buginvestigating labels 2026-02-22 18:29:08 -05:00
yindo closed this issue 2026-02-22 18:29:08 -05:00
yindo commented 2026-02-22 18:29:08 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Apr 3, 2025):

What specific Gemini model are you using? Likely the culprit

@timothycarambat commented on GitHub (Apr 3, 2025): What specific Gemini model are you using? Likely the culprit
yindo commented 2026-02-22 18:29:08 -05:00
Author
Owner
Copy Link
Copy Source

@DangerousBerries commented on GitHub (Apr 4, 2025):

What specific Gemini model are you using? Likely the culprit

gemini-2.5-pro-exp-03-25. It doesn't happen all the time.

@DangerousBerries commented on GitHub (Apr 4, 2025): > What specific Gemini model are you using? Likely the culprit gemini-2.5-pro-exp-03-25. It doesn't happen all the time.
yindo commented 2026-02-22 18:29:08 -05:00
Author
Owner
Copy Link
Copy Source

@shatfield4 commented on GitHub (Apr 4, 2025):

I cannot replicate this after sending many chats to Gemini using that model.

gemini-2.5-pro-exp-03-25 is marked as an experimental model so this most likely caused by an issue on Gemini's end.

@shatfield4 commented on GitHub (Apr 4, 2025): I cannot replicate this after sending many chats to Gemini using that model. `gemini-2.5-pro-exp-03-25` is marked as an experimental model so this most likely caused by an issue on Gemini's end.
yindo changed title from [BUG]: An error occurred while streaming response. network error to [GH-ISSUE #3582] [BUG]: An error occurred while streaming response. network error 2026-06-05 14:45:50 -04:00
yindo changed title from [GH-ISSUE #3582] [BUG]: An error occurred while streaming response. network error to [GH-ISSUE #5624] [BUG]: An error occurred while streaming response. network error 2026-06-05 14:52:36 -04:00
yindo commented 2026-06-05 14:52:37 -04:00
Author
Owner
Copy Link
Copy Source

@shatfield4 commented on GitHub (May 13, 2026):

This sounds like you just have the LLM model not configured correctly. If you go into LLM settings, are you able to select/download other models to test? Closing for now but happy to reopen if you are able to provide more context on how to replicate this.

<!-- gh-comment-id:4445719390 --> @shatfield4 commented on GitHub (May 13, 2026): This sounds like you just have the LLM model not configured correctly. If you go into LLM settings, are you able to select/download other models to test? Closing for now but happy to reopen if you are able to provide more context on how to replicate this.
yindo commented 2026-06-05 14:52:37 -04:00
Author
Owner
Copy Link
Copy Source

@Loopho66 commented on GitHub (May 14, 2026):

Hi shatfield4.
Thanks for taking the time to reply.
Today, I managed to select and download a different model (Qwen3 Vision 2B Instruct).
The download was successful, but then the Unpacking never stopped. It remained in "unpacking" for 4 hours after which I tried to go back to the chat window.
It did go back to the chat window (and the chat is providing some replies - so a great improvement respect to yesterday situation!), but at this point, in the terminal from which I launched the program, I got the following error:

[3786:0514/205008.626072:ERROR:browser_main_loop.cc(278)] GLib-GObject: ../../../gobject/gsignal.c:2699: instance '0x230c02622d00' has no handler with id '4790'
[3786:0514/214024.096956:ERROR:nss_util.cc(345)] After loading Root Certs, loaded==false: NSS error code: -8018

Any clue?

Thanks!

<!-- gh-comment-id:4454215504 --> @Loopho66 commented on GitHub (May 14, 2026): Hi shatfield4. Thanks for taking the time to reply. Today, I managed to select and download a different model (Qwen3 Vision 2B Instruct). The download was successful, but then the Unpacking never stopped. It remained in "unpacking" for 4 hours after which I tried to go back to the chat window. It did go back to the chat window (and the chat is providing some replies - so a great improvement respect to yesterday situation!), but at this point, in the terminal from which I launched the program, I got the following error: [3786:0514/205008.626072:ERROR:browser_main_loop.cc(278)] GLib-GObject: ../../../gobject/gsignal.c:2699: instance '0x230c02622d00' has no handler with id '4790' [3786:0514/214024.096956:ERROR:nss_util.cc(345)] After loading Root Certs, loaded==false: NSS error code: -8018 Any clue? Thanks!
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#2314
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?