Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-22 01:55:24 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #406] issue: Error: 1 documents could not be embedded #233

New Issue
Closed
opened 2026-02-22 18:18:26 -05:00 by yindo · 8 comments
yindo commented 2026-02-22 18:18:26 -05:00
Owner
Copy Link
Copy Source

Originally created by @Justin-KM on GitHub (Dec 3, 2023).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/406

Originally assigned to: @Justin-KM on GitHub.

I deployed the docker image from the link:
docker pull mintplexlabs/anythingllm:master

and run it with the following cmd in my MacBook Pro intelCPU
docker run -d -p 3001:3001 mintplexlabs/anythingllm:master

and I got this error when trying to vectorize a document, I try to use embedding models from both openai and azure, it doesn't make any difference:

Error: 1 documents could not be embedded.

Originally created by @Justin-KM on GitHub (Dec 3, 2023). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/406 Originally assigned to: @Justin-KM on GitHub. I deployed the docker image from the link: docker pull mintplexlabs/anythingllm:master and run it with the following cmd in my MacBook Pro intelCPU docker run -d -p 3001:3001 mintplexlabs/anythingllm:master and I got this error when trying to vectorize a document, I try to use embedding models from both openai and azure, it doesn't make any difference: Error: 1 documents could not be embedded.
yindo added the Integration Requestpossible bug labels 2026-02-22 18:18:26 -05:00
yindo closed this issue 2026-02-22 18:18:26 -05:00
yindo commented 2026-02-22 18:18:26 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Dec 4, 2023):

Can you tail the docker logs to report why the embedding failed? It should be in the logs and from there can trace what was the root cause.

@timothycarambat commented on GitHub (Dec 4, 2023): Can you tail the docker logs to report why the embedding failed? It should be in the logs and from there can trace what was the root cause.
yindo commented 2026-02-22 18:18:26 -05:00
Author
Owner
Copy Link
Copy Source

@35develr commented on GitHub (Dec 7, 2023):

Same Problem: here the Log from Docker:

[TELEMETRY SENT] {

  event: 'document_uploaded',

  distinctId: '966042aa-53b7-4e18-a597-282a1515217f',

  properties: {}

}

Adding new vectorized document into namespace happy-18324266

Chunks created from document: 19

Error: Could not embed document chunks! This document will not be recorded.

    at Object.addDocumentToNamespace (/app/server/utils/vectorDbProviders/lance/index.js:211:15)

    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)

    at async Object.addDocuments (/app/server/models/documents.js:56:26)

    at async /app/server/endpoints/workspaces.js:161:33

addDocumentToNamespace Could not embed document chunks! This document will not be recorded.

Failed to vectorize custom-documents/a-113626-XXXXXXXXXXXXXX-20230912t1050-ap-75487-13f389ba-1b17-418c-91df-e9dec3e42b75.json

[TELEMETRY SENT] {

  event: 'documents_embedded_in_workspace',

  distinctId: '966042aa-53b7-4e18-a597-282a1515217f',

  properties: { LLMSelection: 'localai', VectorDbSelection: 'lancedb' }

}
@35develr commented on GitHub (Dec 7, 2023): Same Problem: here the Log from Docker: ``` [TELEMETRY SENT] { event: 'document_uploaded', distinctId: '966042aa-53b7-4e18-a597-282a1515217f', properties: {} } Adding new vectorized document into namespace happy-18324266 Chunks created from document: 19 Error: Could not embed document chunks! This document will not be recorded. at Object.addDocumentToNamespace (/app/server/utils/vectorDbProviders/lance/index.js:211:15) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async Object.addDocuments (/app/server/models/documents.js:56:26) at async /app/server/endpoints/workspaces.js:161:33 addDocumentToNamespace Could not embed document chunks! This document will not be recorded. Failed to vectorize custom-documents/a-113626-XXXXXXXXXXXXXX-20230912t1050-ap-75487-13f389ba-1b17-418c-91df-e9dec3e42b75.json [TELEMETRY SENT] { event: 'documents_embedded_in_workspace', distinctId: '966042aa-53b7-4e18-a597-282a1515217f', properties: { LLMSelection: 'localai', VectorDbSelection: 'lancedb' } } ```
yindo commented 2026-02-22 18:18:26 -05:00
Author
Owner
Copy Link
Copy Source

@Justin-KM commented on GitHub (Dec 7, 2023):

here you go:
Chunks created from document: 7

Error: Could not embed document chunks! This document will not be recorded.

at Object.addDocumentToNamespace (/app/server/utils/vectorDbProviders/lance/index.js:211:15)

at process.processTicksAndRejections (node:internal/process/task_queues:95:5)

at async Object.addDocuments (/app/server/models/documents.js:56:26)

at async /app/server/endpoints/workspaces.js:161:33

addDocumentToNamespace Could not embed document chunks! This document will not be recorded.

Failed to vectorize custom-documents/8807-20231115-77f486ad-c2dc-4697-8421-101055077607.json

@Justin-KM commented on GitHub (Dec 7, 2023): here you go: Chunks created from document: 7 Error: Could not embed document chunks! This document will not be recorded. at Object.addDocumentToNamespace (/app/server/utils/vectorDbProviders/lance/index.js:211:15) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async Object.addDocuments (/app/server/models/documents.js:56:26) at async /app/server/endpoints/workspaces.js:161:33 addDocumentToNamespace Could not embed document chunks! This document will not be recorded. Failed to vectorize custom-documents/8807-20231115-77f486ad-c2dc-4697-8421-101055077607.json
yindo commented 2026-02-22 18:18:27 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Dec 7, 2023):

@Justin-KM @roedlmax Both of your errors are coming from the embedding engine that is being used for vectorization. The logs do not include that information - could you provide it?

If you are using a non-hosted solution for embedding (localAI or LMStudio) this error likely lies in the connection information to those services or the model that is being used for embedding is not correct or responding. If so then we should further debug why to determine if the bug lies on our side or if it is the embedding endpoint.

The only other variable is that the document being embedded has issues like not parseable text, however, that is likely not the case here.

@timothycarambat commented on GitHub (Dec 7, 2023): @Justin-KM @roedlmax Both of your errors are coming from the embedding engine that is being used for vectorization. The logs do not include that information - could you provide it? If you are using a non-hosted solution for embedding (localAI or LMStudio) this error likely lies in the connection information to those services or the model that is being used for embedding is not correct or responding. If so then we should further debug why to determine if the bug lies on our side or if it is the embedding endpoint. The only other variable is that the document being embedded has issues like not parseable text, however, that is likely not the case here.
yindo commented 2026-02-22 18:18:27 -05:00
Author
Owner
Copy Link
Copy Source

@Justin-KM commented on GitHub (Dec 10, 2023):

thanks for your reply.
I spent some time today to trace down into source code and found the followingh http retturn of openai embedding api.
My guest is it is using async http calling openai embedding api, and the api doesn't like multiple calls.

Error: Request failed with status code 429
at createError (/Users/justin/anythingllm/anything-llm/server/node_modules/axios/lib/core/createError.js:16:15)
at settle (/Users/justin/anythingllm/anything-llm/server/node_modules/axios/lib/core/settle.js:17:12)
at IncomingMessage.handleStreamEnd (/Users/justin/anythingllm/anything-llm/server/node_modules/axios/lib/adapters/http.js:322:11)
at IncomingMessage.emit (node:events:531:35)
at endReadableNT (node:internal/streams/readable:1696:12)
at process.processTicksAndRejections (node:internal/process/task_queues:82:21) {
config: {
transitional: {
silentJSONParsing: true,
forcedJSONParsing: true,
clarifyTimeoutError: false
},
adapter: [Function: httpAdapter],
transformRequest: [ [Function: transformRequest] ],
transformResponse: [ [Function: transformResponse] ],
timeout: 0,
xsrfCookieName: 'XSRF-TOKEN',
xsrfHeaderName: 'X-XSRF-TOKEN',
maxContentLength: -1,
maxBodyLength: -1,
validateStatus: [Function: validateStatus],
headers: {

@Justin-KM commented on GitHub (Dec 10, 2023): thanks for your reply. I spent some time today to trace down into source code and found the followingh http retturn of openai embedding api. My guest is it is using async http calling openai embedding api, and the api doesn't like multiple calls. ------------------------ Error: Request failed with status code 429 at createError (/Users/justin/anythingllm/anything-llm/server/node_modules/axios/lib/core/createError.js:16:15) at settle (/Users/justin/anythingllm/anything-llm/server/node_modules/axios/lib/core/settle.js:17:12) at IncomingMessage.handleStreamEnd (/Users/justin/anythingllm/anything-llm/server/node_modules/axios/lib/adapters/http.js:322:11) at IncomingMessage.emit (node:events:531:35) at endReadableNT (node:internal/streams/readable:1696:12) at process.processTicksAndRejections (node:internal/process/task_queues:82:21) { config: { transitional: { silentJSONParsing: true, forcedJSONParsing: true, clarifyTimeoutError: false }, adapter: [Function: httpAdapter], transformRequest: [ [Function: transformRequest] ], transformResponse: [ [Function: transformResponse] ], timeout: 0, xsrfCookieName: 'XSRF-TOKEN', xsrfHeaderName: 'X-XSRF-TOKEN', maxContentLength: -1, maxBodyLength: -1, validateStatus: [Function: validateStatus], headers: {
yindo commented 2026-02-22 18:18:27 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Dec 11, 2023):

@Justin-KM Indeed, looks like a 429 error. Are you using the "free" version of the OpenAI API. A long time ago we had a question like this on Discord and that was the issue.

We have a couple known instances using OpenAi with ~20-30 concurrent users chatting during regular hours and never getting a 429. So wondering if this is an OpenAI account-level thing. Also if you are using the gpt-4-turbo model preview I believe the rate limits are lower on that model than others!

@timothycarambat commented on GitHub (Dec 11, 2023): @Justin-KM Indeed, looks like a 429 error. Are you using the "free" version of the OpenAI API. A long time ago we had a question like this on Discord and that was the issue. We have a couple known instances using OpenAi with ~20-30 concurrent users chatting during regular hours and never getting a 429. So wondering if this is an OpenAI account-level thing. Also if you are using the `gpt-4-turbo` model preview I believe the rate limits are lower on that model than others!
yindo commented 2026-02-22 18:18:27 -05:00
Author
Owner
Copy Link
Copy Source

@35develr commented on GitHub (Dec 19, 2023):

I am not shure if this is a rate limit issue. I run localai in docker with Mistral7B. I dont know where to set a rate-limit and there is no documentation where to set it. Localai gets the input, as follows:

The File i try to vectorize is named test.txt, the Content is: "Dies ist ein Text."

Output of localai Debug Log:

`[127.0.0.1]:44650 200 - GET /readyz

9:40AM DBG Request received:

9:40AM DBG Parameter Config: &{PredictionOptions:{Model:mistral-7b-openorca.Q6_K.gguf Language: N:0 TopP:0.95 TopK:40 Temperature:0.2 Maxtokens:0 Echo:false Batch:0 F16:false IgnoreEOS:false RepeatPenalty:0 Keep:0 MirostatETA:0 MirostatTAU:0 Mirostat:0 FrequencyPenalty:0 TFZ:0 TypicalP:0 Seed:0 NegativePrompt: RopeFreqBase:0 RopeFreqScale:0 NegativePromptScale:0 UseFastTokenizer:false ClipSkip:0 Tokenizer:} Name:mistral F16:true Threads:4 Debug:true Roles:map[] Embeddings:false Backend: TemplateConfig:{Chat:chatml-block ChatMessage:chatml Completion:completion Edit: Functions:} PromptStrings:[] InputStrings:[Dies ist ein Text.] InputToken:[] functionCallString: functionCallNameString: FunctionsConfig:{DisableNoAction:false NoActionFunctionName: NoActionDescriptionName:} FeatureFlag:map[] LLMConfig:{SystemPrompt: TensorSplit: MainGPU: RMSNormEps:0 NGQA:0 PromptCachePath: PromptCacheAll:false PromptCacheRO:false MirostatETA:0 MirostatTAU:0 Mirostat:0 NGPULayers:0 MMap:true MMlock:false LowVRAM:false Grammar: StopWords:[<|im_end|>] Cutstrings:[] TrimSpace:[] ContextSize:4096 NUMA:false LoraAdapter: LoraBase: LoraScale:0 NoMulMatQ:false DraftModel: NDraft:0 Quantization: MMProj: RopeScaling: YarnExtFactor:0 YarnAttnFactor:0 YarnBetaFast:0 YarnBetaSlow:0} AutoGPTQ:{ModelBaseName: Device: Triton:false UseFastTokenizer:false} Diffusers:{PipelineType: SchedulerType: CUDA:false EnableParameters: CFGScale:0 IMG2IMG:false ClipSkip:0 ClipModel: ClipSubFolder:} Step:0 GRPC:{Attempts:0 AttemptsSleepTime:0} VallE:{AudioPath:}}

[172.23.0.1]:57178 500 - POST /v1/embeddings

HERE IS SEE A 500 ERROR AT POST DATA

[127.0.0.1]:44682 200 - GET /readyz`

How can i fix this?

@35develr commented on GitHub (Dec 19, 2023): I am not shure if this is a rate limit issue. I run localai in docker with Mistral7B. I dont know where to set a rate-limit and there is no documentation where to set it. Localai gets the input, as follows: The File i try to vectorize is named test.txt, the Content is: "Dies ist ein Text." Output of localai Debug Log: `[127.0.0.1]:44650 200 - GET /readyz 9:40AM DBG Request received: 9:40AM DBG Parameter Config: &{PredictionOptions:{Model:mistral-7b-openorca.Q6_K.gguf Language: N:0 TopP:0.95 TopK:40 Temperature:0.2 Maxtokens:0 Echo:false Batch:0 F16:false IgnoreEOS:false RepeatPenalty:0 Keep:0 MirostatETA:0 MirostatTAU:0 Mirostat:0 FrequencyPenalty:0 TFZ:0 TypicalP:0 Seed:0 NegativePrompt: RopeFreqBase:0 RopeFreqScale:0 NegativePromptScale:0 UseFastTokenizer:false ClipSkip:0 Tokenizer:} Name:mistral F16:true Threads:4 Debug:true Roles:map[] Embeddings:false Backend: TemplateConfig:{Chat:chatml-block ChatMessage:chatml Completion:completion Edit: Functions:} PromptStrings:[] InputStrings:[Dies ist ein Text.] InputToken:[] functionCallString: functionCallNameString: FunctionsConfig:{DisableNoAction:false NoActionFunctionName: NoActionDescriptionName:} FeatureFlag:map[] LLMConfig:{SystemPrompt: TensorSplit: MainGPU: RMSNormEps:0 NGQA:0 PromptCachePath: PromptCacheAll:false PromptCacheRO:false MirostatETA:0 MirostatTAU:0 Mirostat:0 NGPULayers:0 MMap:true MMlock:false LowVRAM:false Grammar: StopWords:[<|im_end|>] Cutstrings:[] TrimSpace:[] ContextSize:4096 NUMA:false LoraAdapter: LoraBase: LoraScale:0 NoMulMatQ:false DraftModel: NDraft:0 Quantization: MMProj: RopeScaling: YarnExtFactor:0 YarnAttnFactor:0 YarnBetaFast:0 YarnBetaSlow:0} AutoGPTQ:{ModelBaseName: Device: Triton:false UseFastTokenizer:false} Diffusers:{PipelineType: SchedulerType: CUDA:false EnableParameters: CFGScale:0 IMG2IMG:false ClipSkip:0 ClipModel: ClipSubFolder:} Step:0 GRPC:{Attempts:0 AttemptsSleepTime:0} VallE:{AudioPath:}} [172.23.0.1]:57178 500 - POST /v1/embeddings **HERE IS SEE A 500 ERROR AT POST DATA** [127.0.0.1]:44682 200 - GET /readyz` How can i fix this?
yindo commented 2026-02-22 18:18:27 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Dec 19, 2023):

You should put this as a bug in LocalAI, this is not a bug from AnythingLLM and appears to be related to how the model is loaded or run on the LocalAI side. AnythingLLM is just reporting back there was an error.

@timothycarambat commented on GitHub (Dec 19, 2023): You should put this as a bug in LocalAI, this is not a bug from AnythingLLM and appears to be related to how the model is loaded or run on the LocalAI side. AnythingLLM is just reporting back there was an error.
yindo changed title from issue: Error: 1 documents could not be embedded to [GH-ISSUE #406] issue: Error: 1 documents could not be embedded 2026-06-05 14:34:11 -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 Integration Request 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#233
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?