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 #2888] [BUG]: Could not respond to message. An error occurred while streaming response. network error #1839

New Issue
Closed
opened 2026-02-22 18:26:46 -05:00 by yindo · 12 comments
yindo commented 2026-02-22 18:26:46 -05:00
Owner
Copy Link
Copy Source

Originally created by @obieron on GitHub (Dec 22, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2888

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

AnythingLLM error
Hello. Using v1.7.1 but same error occurred in v1.7.0, Using windows 10 pro and anythingLLm desktop, everything functions very well until I attempt to embed a file. I receive the above error message and the instance freezes. In order to recover I must close the instance and restart, go in and delete the file I embedded ( tried several files and file types ) then I can resume the chat with whichever model.

Are there known steps to reproduce?

I can reproduce this error repeatedly without fail with different models and file types.

Originally created by @obieron on GitHub (Dec 22, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2888 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? ![AnythingLLM error](https://github.com/user-attachments/assets/5ec84711-4d49-4ffa-a274-28099c8b38be) Hello. Using v1.7.1 but same error occurred in v1.7.0, Using windows 10 pro and anythingLLm desktop, everything functions very well until I attempt to embed a file. I receive the above error message and the instance freezes. In order to recover I must close the instance and restart, go in and delete the file I embedded ( tried several files and file types ) then I can resume the chat with whichever model. ### Are there known steps to reproduce? I can reproduce this error repeatedly without fail with different models and file types.
yindo added the possible bug label 2026-02-22 18:26:46 -05:00
yindo closed this issue 2026-02-22 18:26:46 -05:00
yindo commented 2026-02-22 18:26:46 -05:00
Author
Owner
Copy Link
Copy Source

@obieron commented on GitHub (Dec 22, 2024):

I think it has to do with LanceDB IMO.

@obieron commented on GitHub (Dec 22, 2024): I think it has to do with LanceDB IMO.
yindo commented 2026-02-22 18:26:46 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Dec 28, 2024):

Install the latest VC++Redist and then restart the app and your issue will go away. Next version windows will check and install VC++ redist.

https://learn.microsoft.com/en-us/cpp/windows/latest-supported-vc-redist?view=msvc-170#latest-microsoft-visual-c-redistributable-version

Download x64 version 👍

@timothycarambat commented on GitHub (Dec 28, 2024): Install the latest VC++Redist and then restart the app and your issue will go away. Next version windows will check and install VC++ redist. https://learn.microsoft.com/en-us/cpp/windows/latest-supported-vc-redist?view=msvc-170#latest-microsoft-visual-c-redistributable-version Download x64 version 👍
yindo commented 2026-02-22 18:26:46 -05:00
Author
Owner
Copy Link
Copy Source

@obieron commented on GitHub (Dec 29, 2024):

Thank you. I followed these instructions to no avail. Same trouble with Windows 10 pro and Linux Mint 23 I noticed. I noticed on my wife's Windows 10 system she is running v 1.6.8 and her embedding function works just fine. Hope that helps.

@obieron commented on GitHub (Dec 29, 2024): Thank you. I followed these instructions to no avail. Same trouble with Windows 10 pro and Linux Mint 23 I noticed. I noticed on my wife's Windows 10 system she is running v 1.6.8 and her embedding function works just fine. Hope that helps.
yindo commented 2026-02-22 18:26:46 -05:00
Author
Owner
Copy Link
Copy Source

@sigalarm commented on GitHub (Dec 30, 2024):

Having the identical problem on MacOS 12.7.6 Monterey and MacOS 15.1 Sequoia. First noticed it when trying to run with a local Ollama instance, but happens with Claude as well. I am attaching a crash log.
AnythingLLM Helper-2024-12-30-105633.log

@sigalarm commented on GitHub (Dec 30, 2024): Having the identical problem on MacOS 12.7.6 Monterey and MacOS 15.1 Sequoia. First noticed it when trying to run with a local Ollama instance, but happens with Claude as well. I am attaching a crash log. [AnythingLLM Helper-2024-12-30-105633.log](https://github.com/user-attachments/files/18276557/AnythingLLM.Helper-2024-12-30-105633.log)
yindo commented 2026-02-22 18:26:46 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Dec 30, 2024):

@sigalarm this is not the same, these are not crashes - if you had a crash that is something else. Is that what is occuring?

@timothycarambat commented on GitHub (Dec 30, 2024): @sigalarm this is not the same, these are not crashes - if you had a crash that is something else. Is that what is occuring?
yindo commented 2026-02-22 18:26:46 -05:00
Author
Owner
Copy Link
Copy Source

@sigalarm commented on GitHub (Dec 30, 2024):

@timothycarambat - thanks for the response, and sorry if I got it wrong. The message displayed was the same as @obieron showed, and I thought it might be the same.

Steps to reproduce

  1. Start AnythingLLM
  2. Use any thread (new, existing) against any LLM (local, remote)
  3. Attach a file
  4. Ask a question
  5. Boom - you get a file generated in the Crash Reports section of the system console, and you get the following display in AnythingLLM, with the crash report below
AnythingLLM Crash 
-------------------------------------
Translated Report (Full Report Below)
-------------------------------------

Process:               AnythingLLM Helper [2475]
Path:                  /Applications/AnythingLLM.app/Contents/Frameworks/AnythingLLM Helper.app/Contents/MacOS/AnythingLLM Helper
Identifier:            com.anythingllm.helper
Version:               1.7.1
Code Type:             X86-64 (Native)
Parent Process:        AnythingLLM [2460]
Responsible:           AnythingLLM [2460]
User ID:               501

Date/Time:             2024-12-30 12:42:50.1973 -0600
OS Version:            macOS 12.7.6 (21H1320)
Report Version:        12
Anonymous UUID:        33CD51C9-89A7-04BD-0D91-C3DDF29B8BDB


Time Awake Since Boot: 14000 seconds

System Integrity Protection: enabled

Crashed Thread:        107  tokio-runtime-worker

Exception Type:        EXC_BAD_INSTRUCTION (SIGILL)
Exception Codes:       0x0000000000000001, 0x0000000000000000
Exception Note:        EXC_CORPSE_NOTIFY

Termination Reason:    Namespace SIGNAL, Code 4 Illegal instruction: 4
Terminating Process:   exc handler [2475]
@sigalarm commented on GitHub (Dec 30, 2024): @timothycarambat - thanks for the response, and sorry if I got it wrong. The message displayed was the same as @obieron showed, and I thought it might be the same. Steps to reproduce 1. Start AnythingLLM 2. Use any thread (new, existing) against any LLM (local, remote) 3. Attach a file 4. Ask a question 5. Boom - you get a file generated in the Crash Reports section of the system console, and you get the following display in AnythingLLM, with the crash report below <img width="548" alt="AnythingLLM Crash" src="https://github.com/user-attachments/assets/4deef184-4922-4ba9-bf10-8532b2d15b50" /> ``` ------------------------------------- Translated Report (Full Report Below) ------------------------------------- Process: AnythingLLM Helper [2475] Path: /Applications/AnythingLLM.app/Contents/Frameworks/AnythingLLM Helper.app/Contents/MacOS/AnythingLLM Helper Identifier: com.anythingllm.helper Version: 1.7.1 Code Type: X86-64 (Native) Parent Process: AnythingLLM [2460] Responsible: AnythingLLM [2460] User ID: 501 Date/Time: 2024-12-30 12:42:50.1973 -0600 OS Version: macOS 12.7.6 (21H1320) Report Version: 12 Anonymous UUID: 33CD51C9-89A7-04BD-0D91-C3DDF29B8BDB Time Awake Since Boot: 14000 seconds System Integrity Protection: enabled Crashed Thread: 107 tokio-runtime-worker Exception Type: EXC_BAD_INSTRUCTION (SIGILL) Exception Codes: 0x0000000000000001, 0x0000000000000000 Exception Note: EXC_CORPSE_NOTIFY Termination Reason: Namespace SIGNAL, Code 4 Illegal instruction: 4 Terminating Process: exc handler [2475] ```
yindo commented 2026-02-22 18:26:47 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Dec 30, 2024):

Can you get the logs from the application here:
https://docs.anythingllm.com/installation-desktop/debug

Also the majority of your issues are most likely this:

macOS 12.7.6 (21H1320)

This is very old and our more current libraries (probably lancedb) for sure wont have full support for MacOS 12. Which would make the local vector db unusable

@timothycarambat commented on GitHub (Dec 30, 2024): Can you get the logs from the application here: https://docs.anythingllm.com/installation-desktop/debug Also the majority of your issues are most likely this: > macOS 12.7.6 (21H1320) This is _very old_ and our more current libraries (probably lancedb) for sure wont have full support for MacOS 12. Which would make the local vector db unusable
yindo commented 2026-02-22 18:26:47 -05:00
Author
Owner
Copy Link
Copy Source

@sigalarm commented on GitHub (Dec 30, 2024):

Thanks again for the response. If the OS is too old, so be it. I ran AnythingLLM from the command line, as requested, and the results were the same, but the log output is included below.

Prisma schema loaded from prisma/schema.prisma
Datasource "db": SQLite database "anythingllm.db" at "file:/Users/bruce/Library/Application Support/anythingllm-desktop/storage/anythingllm.db"

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

✔ Generated Prisma Client (v5.3.1) to ./node_modules/@prisma/client in 316ms


Prisma schema loaded from prisma/schema.prisma

✔ Generated Prisma Client (v5.3.1) to ./node_modules/@prisma/client in 316ms

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

import { PrismaClient } from '@prisma/client'
const prisma = new PrismaClient()

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

import { PrismaClient } from '@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.
[Preferences] Will load window with last know bounds.
[backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data.
[collector] info: Collector hot directory and tmp storage wiped!
[collector] info: [production] AnythingLLM Standalone Document processor listening on port 8888.
[backend] info: [TELEMETRY ENABLED] Anonymous Telemetry enabled. Telemetry helps Mintplex Labs Inc improve AnythingLLM.
[backend] info: prisma:info Starting a sqlite pool with 21 connections.
[backend] info: [TELEMETRY SENT] {"event":"server_boot","distinctId":"8ba16d2f-89eb-466c-9e37-d3bad1266cc2","properties":{"runtime":"desktop"}}
[backend] info: Skipping preloading of AnythingLLMOllama - LLM_PROVIDER is anthropic.
[backend] info: [CommunicationKey] RSA key pair generated for signed payloads within AnythingLLM services.
[backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data.
[backend] info: [production] AnythingLLM Standalone Backend listening on port 3001. Network discovery is disabled.
[backend] info: [BackgroundWorkerService] Feature is not enabled and will not be started.
[backend] info: [TELEMETRY SENT] {"event":"workspace_created","distinctId":"8ba16d2f-89eb-466c-9e37-d3bad1266cc2","properties":{"multiUserMode":false,"LLMSelection":"anthropic","Embedder":"native","VectorDbSelection":"lancedb","TTSSelection":"native","runtime":"desktop"}}
[backend] info: [Event Logged] - workspace_created
[backend] info: [NativeEmbedder] Initialized
[backend] info: [NativeEmbedder] Initialized
[backend] info: [NativeEmbedder] Initialized
[backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data.
[collector] info: -- Working COBCALC_001.txt --
[collector] info: [SUCCESS]: COBCALC_001.txt converted & ready for embedding.

[backend] info: [CollectorApi] Document COBCALC_001.txt uploaded processed and successfully. It is now available in documents.
[backend] info: [TELEMETRY SENT] {"event":"document_uploaded","distinctId":"8ba16d2f-89eb-466c-9e37-d3bad1266cc2","properties":{"runtime":"desktop"}}
[backend] info: [Event Logged] - document_uploaded
[backend] info: Adding new vectorized document into namespace claude-remote
[backend] info: [NativeEmbedder] Initialized
[backend] info: [RecursiveSplitter] Will split with {"chunkSize":1000,"chunkOverlap":20}
[backend] info: Chunks created from document: 12
[backend] info: [NativeEmbedder] Embedded Chunk 1 of 1
[backend] info: Inserting vectorized chunks into LanceDB collection.
[backend] info: Caching vectorized results of custom-documents/COBCALC_001.txt-4da986e8-6981-4c96-b819-8241d4b44e65.json to prevent duplicated embedding.
[backend] info: [TELEMETRY SENT] {"event":"documents_embedded_in_workspace","distinctId":"8ba16d2f-89eb-466c-9e37-d3bad1266cc2","properties":{"LLMSelection":"anthropic","Embedder":"native","VectorDbSelection":"lancedb","TTSSelection":"native","runtime":"desktop"}}
[backend] info: [Event Logged] - workspace_documents_added
[backend] info: [NativeEmbedder] Initialized
[backend] info: [NativeEmbedder] Embedded Chunk 1 of 1
@sigalarm commented on GitHub (Dec 30, 2024): Thanks again for the response. If the OS is too old, so be it. I ran AnythingLLM from the command line, as requested, and the results were the same, but the log output is included below. ```[Preferences] preference config stored at /Users/bruce/Library/Application Support/anythingllm-desktop/config.json Prisma schema loaded from prisma/schema.prisma Datasource "db": SQLite database "anythingllm.db" at "file:/Users/bruce/Library/Application Support/anythingllm-desktop/storage/anythingllm.db" Already in sync, no schema change or pending migration was found. ✔ Generated Prisma Client (v5.3.1) to ./node_modules/@prisma/client in 316ms Prisma schema loaded from prisma/schema.prisma ✔ Generated Prisma Client (v5.3.1) to ./node_modules/@prisma/client in 316ms Start using Prisma Client in Node.js (See: https://pris.ly/d/client) ``` import { PrismaClient } from '@prisma/client' const prisma = new PrismaClient() ``` or start using Prisma Client at the edge (See: https://pris.ly/d/accelerate) ``` import { PrismaClient } from '@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. [Preferences] Will load window with last know bounds. [backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data. [collector] info: Collector hot directory and tmp storage wiped! [collector] info: [production] AnythingLLM Standalone Document processor listening on port 8888. [backend] info: [TELEMETRY ENABLED] Anonymous Telemetry enabled. Telemetry helps Mintplex Labs Inc improve AnythingLLM. [backend] info: prisma:info Starting a sqlite pool with 21 connections. [backend] info: [TELEMETRY SENT] {"event":"server_boot","distinctId":"8ba16d2f-89eb-466c-9e37-d3bad1266cc2","properties":{"runtime":"desktop"}} [backend] info: Skipping preloading of AnythingLLMOllama - LLM_PROVIDER is anthropic. [backend] info: [CommunicationKey] RSA key pair generated for signed payloads within AnythingLLM services. [backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data. [backend] info: [production] AnythingLLM Standalone Backend listening on port 3001. Network discovery is disabled. [backend] info: [BackgroundWorkerService] Feature is not enabled and will not be started. [backend] info: [TELEMETRY SENT] {"event":"workspace_created","distinctId":"8ba16d2f-89eb-466c-9e37-d3bad1266cc2","properties":{"multiUserMode":false,"LLMSelection":"anthropic","Embedder":"native","VectorDbSelection":"lancedb","TTSSelection":"native","runtime":"desktop"}} [backend] info: [Event Logged] - workspace_created [backend] info: [NativeEmbedder] Initialized [backend] info: [NativeEmbedder] Initialized [backend] info: [NativeEmbedder] Initialized [backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data. [collector] info: -- Working COBCALC_001.txt -- [collector] info: [SUCCESS]: COBCALC_001.txt converted & ready for embedding. [backend] info: [CollectorApi] Document COBCALC_001.txt uploaded processed and successfully. It is now available in documents. [backend] info: [TELEMETRY SENT] {"event":"document_uploaded","distinctId":"8ba16d2f-89eb-466c-9e37-d3bad1266cc2","properties":{"runtime":"desktop"}} [backend] info: [Event Logged] - document_uploaded [backend] info: Adding new vectorized document into namespace claude-remote [backend] info: [NativeEmbedder] Initialized [backend] info: [RecursiveSplitter] Will split with {"chunkSize":1000,"chunkOverlap":20} [backend] info: Chunks created from document: 12 [backend] info: [NativeEmbedder] Embedded Chunk 1 of 1 [backend] info: Inserting vectorized chunks into LanceDB collection. [backend] info: Caching vectorized results of custom-documents/COBCALC_001.txt-4da986e8-6981-4c96-b819-8241d4b44e65.json to prevent duplicated embedding. [backend] info: [TELEMETRY SENT] {"event":"documents_embedded_in_workspace","distinctId":"8ba16d2f-89eb-466c-9e37-d3bad1266cc2","properties":{"LLMSelection":"anthropic","Embedder":"native","VectorDbSelection":"lancedb","TTSSelection":"native","runtime":"desktop"}} [backend] info: [Event Logged] - workspace_documents_added [backend] info: [NativeEmbedder] Initialized [backend] info: [NativeEmbedder] Embedded Chunk 1 of 1 ```
yindo commented 2026-02-22 18:26:47 -05:00
Author
Owner
Copy Link
Copy Source

@obieron commented on GitHub (Dec 30, 2024):

I'm not as knowledgeable as you guys BUT, I'm getting the same error with this version and attempt to embed a file with Windows 10 pro 22H2 and Linux mint 23. I tried updating vc++ redlist to no avail. I have AnythingLLM 6 8 1 that was still in a download folder and the older version works just fine but without the community tab and function. Hope it helps. Great product and thank you.

@obieron commented on GitHub (Dec 30, 2024): I'm not as knowledgeable as you guys BUT, I'm getting the same error with this version and attempt to embed a file with Windows 10 pro 22H2 and Linux mint 23. I tried updating vc++ redlist to no avail. I have AnythingLLM 6 8 1 that was still in a download folder and the older version works just fine but without the community tab and function. Hope it helps. Great product and thank you.
yindo commented 2026-02-22 18:26:47 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Dec 30, 2024):

@obieron what is the version?

AnythingLLM 6 8 1
does not exist yet, we are only on 1.7.1 right now.

@sigalarm Looking over the crash logs this is quite odd, but seems to be something releated to ONNXruntime or Lancedb, both of which are leveraged when embedding documents locally. If you are able to swap your embedder to something other than the built in, like Ollama or OpenAi and try to embed + query we can then deduce if the issue is lancedb or Onnxruntime causing the crash.

My hunch is lancedb, since that typically targeted to "newer" arch's

@timothycarambat commented on GitHub (Dec 30, 2024): @obieron what is the version? > AnythingLLM 6 8 1 does not exist yet, we are only on 1.7.1 right now. @sigalarm Looking over the crash logs this is quite odd, but seems to be something releated to ONNXruntime or Lancedb, both of which are leveraged when embedding documents locally. If you are able to swap your embedder to something other than the built in, like Ollama or OpenAi and try to embed + query we can then deduce if the issue is lancedb or Onnxruntime causing the crash. My hunch is lancedb, since that typically targeted to "newer" arch's
yindo commented 2026-02-22 18:26:47 -05:00
Author
Owner
Copy Link
Copy Source

@ctcanbol commented on GitHub (Feb 16, 2025):

I am using the latest version of anythingllm on linux docker. I have 1 very short and simple txt file attached to the workspace. I tried with both LanceDB and ChromaDB and I get the same “network error” error 4 out of 5 times. The dev console has the following error “POST /api/workspace/knowledge-base/thread/87298c23-56fa-41fa-9963-4a7cc978d3fa/stream-chat net::ERR_INCOMPLETE_CHUNKED_ENCODING 200 (OK)”. The interesting thing is that the response actually comes after a while. When I refresh the page, I see that the response has returned. I haven't found a solution to this yet, but it prevents us from using documents in the workspace.

@ctcanbol commented on GitHub (Feb 16, 2025): I am using the latest version of anythingllm on linux docker. I have 1 very short and simple txt file attached to the workspace. I tried with both LanceDB and ChromaDB and I get the same “network error” error 4 out of 5 times. The dev console has the following error “POST /api/workspace/knowledge-base/thread/87298c23-56fa-41fa-9963-4a7cc978d3fa/stream-chat net::ERR_INCOMPLETE_CHUNKED_ENCODING 200 (OK)”. The interesting thing is that the response actually comes after a while. When I refresh the page, I see that the response has returned. I haven't found a solution to this yet, but it prevents us from using documents in the workspace.
yindo commented 2026-02-22 18:26:47 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Feb 16, 2025):

https://github.com/Mintplex-Labs/anything-llm/issues/3235#issuecomment-2661671699

@timothycarambat commented on GitHub (Feb 16, 2025): https://github.com/Mintplex-Labs/anything-llm/issues/3235#issuecomment-2661671699
yindo changed title from [BUG]: Could not respond to message. An error occurred while streaming response. network error to [GH-ISSUE #2888] [BUG]: Could not respond to message. An error occurred while streaming response. network error 2026-06-05 14:42:59 -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#1839
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?