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 #3365] [BUG]: MP3 upload failure caused[Document processing API is not online] #2168

New Issue
Closed
opened 2026-02-22 18:28:26 -05:00 by yindo · 4 comments
yindo commented 2026-02-22 18:28:26 -05:00
Owner
Copy Link
Copy Source

Originally created by @atomxing on GitHub (Feb 27, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3365

How are you running AnythingLLM?

AnythingLLM desktop app windows

What happened?

MP3 upload failure caused[Document processing API is not online]

Attempted to upload an MP3 file, but encountered an error (see error log below), which will result in the inability to upload any more files and the error message 'Document processing API is not online' Documena.pdf will not be processed automatically.

[error log see 2 floor]

Are there known steps to reproduce?

MP3 upload failure （The speech processing model may not have been downloaded locally）

Originally created by @atomxing on GitHub (Feb 27, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3365 ### How are you running AnythingLLM? AnythingLLM desktop app windows ### What happened? MP3 upload failure caused[Document processing API is not online] Attempted to upload an MP3 file, but encountered an error (see error log below), which will result in the inability to upload any more files and the error message 'Document processing API is not online' Documena.pdf will not be processed automatically. [error log see 2 floor] ### Are there known steps to reproduce? MP3 upload failure （The speech processing model may not have been downloaded locally）
yindo added the possible bug label 2026-02-22 18:28:26 -05:00
yindo closed this issue 2026-02-22 18:28:27 -05:00
yindo commented 2026-02-22 18:28:27 -05:00
Author
Owner
Copy Link
Copy Source

@atomxing commented on GitHub (Feb 27, 2025):

first upload：
Image

second ：MP3 upload failure caused [any file] error log: [Document processing API is not online]
Image

[OllamaProcessManager] Ollama will bind on port 3368 when booted.
[Preferences] Will load window with last know bounds.
[collector] info: [TikTokenTokenizer] Initialized new TikTokenTokenizer instance.
[backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data.
[backend] info: [TokenManager] Initialized new TokenManager instance for model: gpt-3.5-turbo
[collector] info: Collector hot directory and tmp storage wiped!
[collector] info: [production] AnythingLLM Standalone Document processor listening on port 8888.
[backend] info: [TokenManager] Returning existing instance for model: gpt-3.5-turbo
[backend] info: [TELEMETRY DISABLED] Telemetry is marked as disabled - no events will send. Telemetry helps Mintplex Labs Inc improve AnythingLLM.
[backend] info: Skipping preloading of AnythingLLMOllama - LLM_PROVIDER is ollama.
[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: prisma:info Starting a sqlite pool with 17 connections.
[backend] info: [BackgroundWorkerService] Feature is not enabled and will not be started.
[backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data.
[collector] info: -- Working 123.mp3 --
[collector] info: [LocalWhisper] Initialized.
[collector] info: [LocalWhisper] The native whisper model has never been run and will be downloaded right now. Subsequent runs will be faster. (~250mb)
[collector] info: [LocalWhisper] Using temp folder at C:\Users\ylx\AppData\Roaming\anythingllm-desktop\storage\tmp
[collector] info: [LocalWhisper] File conversion required! .mp3 file detected - converting to .wav
[collector] info: [LocalWhisper] Conversion Error! Cannot find ffmpeg
[collector] error: convertToWavAudioData Error: [Conversion Failed]: Could not convert file to .wav format!
at #t (D:\Programs\AnythingLLM\resources\backend\collector.js:13:1799)
at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
[collector] info: [LocalWhisper] Failed to load the native whisper model: TypeError: fetch failed
at Object.fetch (node:internal/deps/undici/undici:11457:11)
at processTicksAndRejections (node:internal/process/task_queues:95:5)
at runNextTicks (node:internal/process/task_queues:64:3)
at process.processImmediate (node:internal/timers:447:9)
at async getModelFile (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/utils/hub.js:468:24)
at async getModelJSON (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/utils/hub.js:572:18)
at async Promise.all (index 0)
at async loadTokenizer (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/tokenizers.js:61:18)
at async AutoTokenizer.from_pretrained (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/tokenizers.js:4459:50)
at async Promise.all (index 0)
node:internal/process/promises:288
triggerUncaughtException(err, true /* fromPromise */);
^

TypeError: fetch failed
at Object.fetch (node:internal/deps/undici/undici:11457:11)
at processTicksAndRejections (node:internal/process/task_queues:95:5)
at runNextTicks (node:internal/process/task_queues:64:3)
at process.processImmediate (node:internal/timers:447:9)
at async getModelFile (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/utils/hub.js:468:24)
at async getModelJSON (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/utils/hub.js:572:18)
at async Promise.all (index 0)
at async loadTokenizer (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/tokenizers.js:61:18)
at async AutoTokenizer.from_pretrained (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/tokenizers.js:4459:50)
at async Promise.all (index 0) {
cause: ConnectTimeoutError: Connect Timeout Error
at onConnectTimeout (node:internal/deps/undici/undici:8422:28)
at node:internal/deps/undici/undici:8380:50
at Immediate._onImmediate (node:internal/deps/undici/undici:8409:37)
at process.processImmediate (node:internal/timers:476:21) {
code: 'UND_ERR_CONNECT_TIMEOUT'
}
}

Node.js v18.16.1
[backend] info: [CollectorApi] fetch failed

@atomxing commented on GitHub (Feb 27, 2025): first upload： ![Image](https://github.com/user-attachments/assets/81ae9972-79ca-4b8a-b76e-c918af3c4c6f) second ：MP3 upload failure caused [any file] error log: [Document processing API is not online] ![Image](https://github.com/user-attachments/assets/2eb455d6-d18b-41d1-9288-f137cfffcb74) [OllamaProcessManager] Ollama will bind on port 3368 when booted. [Preferences] Will load window with last know bounds. [collector] info: [TikTokenTokenizer] Initialized new TikTokenTokenizer instance. [backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data. [backend] info: [TokenManager] Initialized new TokenManager instance for model: gpt-3.5-turbo [collector] info: Collector hot directory and tmp storage wiped! [collector] info: [production] AnythingLLM Standalone Document processor listening on port 8888. [backend] info: [TokenManager] Returning existing instance for model: gpt-3.5-turbo [backend] info: [TELEMETRY DISABLED] Telemetry is marked as disabled - no events will send. Telemetry helps Mintplex Labs Inc improve AnythingLLM. [backend] info: Skipping preloading of AnythingLLMOllama - LLM_PROVIDER is ollama. [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: prisma:info Starting a sqlite pool with 17 connections. [backend] info: [BackgroundWorkerService] Feature is not enabled and will not be started. [backend] info: [EncryptionManager] Loaded existing key & salt for encrypting arbitrary data. [collector] info: -- Working 123.mp3 -- [collector] info: [LocalWhisper] Initialized. [collector] info: [LocalWhisper] The native whisper model has never been run and will be downloaded right now. Subsequent runs will be faster. (~250mb) [collector] info: [LocalWhisper] Using temp folder at C:\Users\ylx\AppData\Roaming\anythingllm-desktop\storage\tmp [collector] info: [LocalWhisper] File conversion required! .mp3 file detected - converting to .wav [collector] info: [LocalWhisper] Conversion Error! Cannot find ffmpeg [collector] error: convertToWavAudioData Error: [Conversion Failed]: Could not convert file to .wav format! at #t (D:\Programs\AnythingLLM\resources\backend\collector.js:13:1799) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) [collector] info: [LocalWhisper] Failed to load the native whisper model: TypeError: fetch failed at Object.fetch (node:internal/deps/undici/undici:11457:11) at processTicksAndRejections (node:internal/process/task_queues:95:5) at runNextTicks (node:internal/process/task_queues:64:3) at process.processImmediate (node:internal/timers:447:9) at async getModelFile (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/utils/hub.js:468:24) at async getModelJSON (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/utils/hub.js:572:18) at async Promise.all (index 0) at async loadTokenizer (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/tokenizers.js:61:18) at async AutoTokenizer.from_pretrained (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/tokenizers.js:4459:50) at async Promise.all (index 0) node:internal/process/promises:288 triggerUncaughtException(err, true /* fromPromise */); ^ TypeError: fetch failed at Object.fetch (node:internal/deps/undici/undici:11457:11) at processTicksAndRejections (node:internal/process/task_queues:95:5) at runNextTicks (node:internal/process/task_queues:64:3) at process.processImmediate (node:internal/timers:447:9) at async getModelFile (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/utils/hub.js:468:24) at async getModelJSON (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/utils/hub.js:572:18) at async Promise.all (index 0) at async loadTokenizer (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/tokenizers.js:61:18) at async AutoTokenizer.from_pretrained (file:///D:/Programs/AnythingLLM/resources/backend/node_modules/@xenova/transformers/src/tokenizers.js:4459:50) at async Promise.all (index 0) { cause: ConnectTimeoutError: Connect Timeout Error at onConnectTimeout (node:internal/deps/undici/undici:8422:28) at node:internal/deps/undici/undici:8380:50 at Immediate._onImmediate (node:internal/deps/undici/undici:8409:37) at process.processImmediate (node:internal/timers:476:21) { code: 'UND_ERR_CONNECT_TIMEOUT' } } Node.js v18.16.1 [backend] info: [CollectorApi] fetch failed
yindo commented 2026-02-22 18:28:27 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Feb 27, 2025):

Failed to download the built in Whisper model from HuggingFace (probably blocked because in restricted Geo or VPN) - we cannot fix this since we do not mirror all of HF's assets like we do for the embedding model.

@timothycarambat commented on GitHub (Feb 27, 2025): Failed to download the [built in](https://github.com/Mintplex-Labs/anything-llm/blob/0cce89a4eb49fb7f42fae4c7f73f5476a8cc3c3a/collector/utils/WhisperProviders/localWhisper.js#L4-L5) Whisper model from HuggingFace (probably blocked because in restricted Geo or VPN) - we cannot fix this since we do not mirror all of HF's assets like we do for the embedding model.
yindo commented 2026-02-22 18:28:27 -05:00
Author
Owner
Copy Link
Copy Source

@atomxing commented on GitHub (Feb 28, 2025):

Failed to download the built in Whisper model from HuggingFace (probably blocked because in restricted Geo or VPN) - we cannot fix this since we do not mirror all of HF's assets like we do for the embedding model.

I believe that the failure to download the voice model cannot cause the Document processing API to not be online after uploading the voice file. I must restart anything llm before importing other files again. This is a bug that needs to be fixed. Thank you for your answer and contribution!

@atomxing commented on GitHub (Feb 28, 2025): > Failed to download the [built in](https://github.com/Mintplex-Labs/anything-llm/blob/0cce89a4eb49fb7f42fae4c7f73f5476a8cc3c3a/collector/utils/WhisperProviders/localWhisper.js#L4-L5) Whisper model from HuggingFace (probably blocked because in restricted Geo or VPN) - we cannot fix this since we do not mirror all of HF's assets like we do for the embedding model. I believe that the failure to download the voice model cannot cause the Document processing API to not be online after uploading the voice file. I must restart anything llm before importing other files again. This is a bug that needs to be fixed. Thank you for your answer and contribution!
yindo commented 2026-02-22 18:28:27 -05:00
Author
Owner
Copy Link
Copy Source

@jasonsi1993 commented on GitHub (May 21, 2025):

Failed to download the built in Whisper model from HuggingFace (probably blocked because in restricted Geo or VPN) - we cannot fix this since we do not mirror all of HF's assets like we do for the embedding model.

Does manually download all the files fix the issue?

@jasonsi1993 commented on GitHub (May 21, 2025): > Failed to download the [built in](https://github.com/Mintplex-Labs/anything-llm/blob/0cce89a4eb49fb7f42fae4c7f73f5476a8cc3c3a/collector/utils/WhisperProviders/localWhisper.js#L4-L5) Whisper model from HuggingFace (probably blocked because in restricted Geo or VPN) - we cannot fix this since we do not mirror all of HF's assets like we do for the embedding model. Does manually download all the files fix the issue?
yindo changed title from [BUG]: MP3 upload failure caused[Document processing API is not online] to [GH-ISSUE #3365] [BUG]: MP3 upload failure caused[Document processing API is not online] 2026-06-05 14:44:58 -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#2168
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?