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 #4024] [BUG]: qdrant failing to import document with fetch failed #2558

New Issue
Closed
opened 2026-02-22 18:30:14 -05:00 by yindo · 4 comments
yindo commented 2026-02-22 18:30:14 -05:00
Owner
Copy Link
Copy Source

Originally created by @andreab67 on GitHub (Jun 19, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4024

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

I have version 1.8.2 of aythingLLM
From the machine where AnythingLLM is installled I can connect to my QDRANT DB

https://qdrant.andrea-house.com/

object
{3}
commit
:
"671cf97bc27ac2d6f5c35bf5d4a20afad43291b3"
title
:
"qdrant - vector search engine"
version
:
"1.9.4"

I have variables QDRANT_API_KEY QDRANT_URL VECTOR_DB set at system level and I specified the extra CA

The Settings of the Vector DB seem to work

This is the error I get

{"level":"error","message":"fetch failed TypeError: fetch failed\n at Object.fetch (node:internal/deps/undici/undici:11457:11)\n at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n at async fetchJson (C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\openapi-typescript-fetch\dist\cjs\fetcher.js:135:22)\n at async C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\js-client-rest\dist\cjs\api-client.js:36:24\n at async handler (C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\openapi-typescript-fetch\dist\cjs\fetcher.js:156:16)\n at async C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\js-client-rest\dist\cjs\api-client.js:20:24\n at async handler (C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\openapi-typescript-fetch\dist\cjs\fetcher.js:156:16)\n at async fetchUrl (C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\openapi-typescript-fetch\dist\cjs\fetcher.js:162:22)\n at async Object.fun [as clusterStatus] (C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\openapi-typescript-fetch\dist\cjs\fetcher.js:168:20)\n at async Object.connect (C:\Program Files\AnythingLLM\resources\backend\server.js:73:52364)","service":"backend"}
{"level":"info","message":"Adding new vectorized document into namespace andrea","service":"backend"}
{"level":"info","message":"\u001b[35m[RecursiveSplitter]\u001b[0m Will split with {"chunkSize":8191,"chunkOverlap":20}","service":"backend"}
{"level":"info","message":"Chunks created from document: 79","service":"backend"}
{"level":"info","message":"\u001b[36m[OpenAiEmbedder]\u001b[0m Embedding 79 chunks...","service":"backend"}
{"level":"error","message":"addDocumentToNamespace fetch failed","service":"backend"}
{"level":"error","message":"Failed to vectorize book.epub","service":"backend"}

Are there known steps to reproduce?

No response

Originally created by @andreab67 on GitHub (Jun 19, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4024 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? I have version 1.8.2 of aythingLLM From the machine where AnythingLLM is installled I can connect to my QDRANT DB https://qdrant.andrea-house.com/ object {3} commit : "671cf97bc27ac2d6f5c35bf5d4a20afad43291b3" title : "qdrant - vector search engine" version : "1.9.4" I have variables QDRANT_API_KEY QDRANT_URL VECTOR_DB set at system level and I specified the extra CA The Settings of the Vector DB seem to work This is the error I get {"level":"error","message":"fetch failed TypeError: fetch failed\n at Object.fetch (node:internal/deps/undici/undici:11457:11)\n at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n at async fetchJson (C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\openapi-typescript-fetch\\dist\\cjs\\fetcher.js:135:22)\n at async C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\js-client-rest\\dist\\cjs\\api-client.js:36:24\n at async handler (C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\openapi-typescript-fetch\\dist\\cjs\\fetcher.js:156:16)\n at async C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\js-client-rest\\dist\\cjs\\api-client.js:20:24\n at async handler (C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\openapi-typescript-fetch\\dist\\cjs\\fetcher.js:156:16)\n at async fetchUrl (C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\openapi-typescript-fetch\\dist\\cjs\\fetcher.js:162:22)\n at async Object.fun [as clusterStatus] (C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\openapi-typescript-fetch\\dist\\cjs\\fetcher.js:168:20)\n at async Object.connect (C:\\Program Files\\AnythingLLM\\resources\\backend\\server.js:73:52364)","service":"backend"} {"level":"info","message":"Adding new vectorized document into namespace andrea","service":"backend"} {"level":"info","message":"\u001b[35m[RecursiveSplitter]\u001b[0m Will split with {\"chunkSize\":8191,\"chunkOverlap\":20}","service":"backend"} {"level":"info","message":"Chunks created from document: 79","service":"backend"} {"level":"info","message":"\u001b[36m[OpenAiEmbedder]\u001b[0m Embedding 79 chunks...","service":"backend"} {"level":"error","message":"addDocumentToNamespace fetch failed","service":"backend"} {"level":"error","message":"Failed to vectorize book.epub","service":"backend"} ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:30:14 -05:00
yindo closed this issue 2026-02-22 18:30:14 -05:00
yindo commented 2026-02-22 18:30:14 -05:00
Author
Owner
Copy Link
Copy Source

@andreab67 commented on GitHub (Jun 20, 2025):

I tried removing encryption since even creating a clr endpoint did not work.
I was surprised to see the same error with http://

level":"info","message":"\u001b[32m[Ollama]\u001b[0m OllamaAILLM initialized with\nmodel: devstral:24b-small-2505-q4_K_M\nperf: maximum\nn_ctx: 4096","service":"backend"}
{"level":"error","message":"TypeError: fetch failed\n at Object.fetch (node:internal/deps/undici/undici:11457:11)\n at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n at async fetchJson (C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\openapi-typescript-fetch\dist\cjs\fetcher.js:135:22)\n at async C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\js-client-rest\dist\cjs\api-client.js:36:24\n at async handler (C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\openapi-typescript-fetch\dist\cjs\fetcher.js:156:16)\n at async C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\js-client-rest\dist\cjs\api-client.js:20:24\n at async handler (C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\openapi-typescript-fetch\dist\cjs\fetcher.js:156:16)\n at async fetchUrl (C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\openapi-typescript-fetch\dist\cjs\fetcher.js:162:22)\n at async Object.fun [as clusterStatus] (C:\Program Files\AnythingLLM\resources\backend\node_modules\@qdrant\openapi-typescript-fetch\dist\cjs\fetcher.js:168:20)\n at async Object.connect (C:\Program Files\AnythingLLM\resources\backend\server.js:73:52364)","service":"backend"}

@andreab67 commented on GitHub (Jun 20, 2025): I tried removing encryption since even creating a clr endpoint did not work. I was surprised to see the same error with http:// level":"info","message":"\u001b[32m[Ollama]\u001b[0m OllamaAILLM initialized with\nmodel: devstral:24b-small-2505-q4_K_M\nperf: maximum\nn_ctx: 4096","service":"backend"} {"level":"error","message":"TypeError: fetch failed\n at Object.fetch (node:internal/deps/undici/undici:11457:11)\n at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n at async fetchJson (C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\openapi-typescript-fetch\\dist\\cjs\\fetcher.js:135:22)\n at async C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\js-client-rest\\dist\\cjs\\api-client.js:36:24\n at async handler (C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\openapi-typescript-fetch\\dist\\cjs\\fetcher.js:156:16)\n at async C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\js-client-rest\\dist\\cjs\\api-client.js:20:24\n at async handler (C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\openapi-typescript-fetch\\dist\\cjs\\fetcher.js:156:16)\n at async fetchUrl (C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\openapi-typescript-fetch\\dist\\cjs\\fetcher.js:162:22)\n at async Object.fun [as clusterStatus] (C:\\Program Files\\AnythingLLM\\resources\\backend\\node_modules\\@qdrant\\openapi-typescript-fetch\\dist\\cjs\\fetcher.js:168:20)\n at async Object.connect (C:\\Program Files\\AnythingLLM\\resources\\backend\\server.js:73:52364)","service":"backend"}
yindo commented 2026-02-22 18:30:14 -05:00
Author
Owner
Copy Link
Copy Source

@andreab67 commented on GitHub (Jun 20, 2025):

Then I thought maybe something is wrong with my installation - so I removed it, went to %username%/appdata and deleted the setting there too
Removed all environment variables

If I switch the vector to LanceDB Local embedding works

Is QDrant broken?
I tried Milvus and did not work as well

I need to run in my local network, which one I should use?

@andreab67 commented on GitHub (Jun 20, 2025): Then I thought maybe something is wrong with my installation - so I removed it, went to %username%/appdata and deleted the setting there too Removed all environment variables If I switch the vector to LanceDB Local embedding works Is QDrant broken? I tried Milvus and did not work as well I need to run in my local network, which one I should use?
yindo commented 2026-02-22 18:30:14 -05:00
Author
Owner
Copy Link
Copy Source

@andreab67 commented on GitHub (Jun 20, 2025):

This is the same epub successfully loaded in LanceDB

{"level":"info","message":"Inserting vectorized chunks into LanceDB collection.","service":"backend"}
{"level":"info","message":"Caching vectorized results of custom-documents/ggggggggggggggg.json to prevent duplicated embedding.","service":"backend"}
{"level":"info","message":"\u001b[32m[TELEMETRY SENT]\u001b[0m {"event":"documents_embedded_in_workspace","distinctId":"353312ca-46e2-41b1-aefc-ae75951ffdeb","properties":{"LLMSelection":"ollama","Embedder":"inherit","VectorDbSelection":"lancedb","TTSSelection":"native","LLMModel":"devstral:24b-small-2505-q4_K_M"}}","service":"backend"}
{"level":"info","message":"\u001b[32m[Event Logged]\u001b[0m - workspace_documents_added","service":"backend"}

@andreab67 commented on GitHub (Jun 20, 2025): This is the same epub successfully loaded in LanceDB {"level":"info","message":"Inserting vectorized chunks into LanceDB collection.","service":"backend"} {"level":"info","message":"Caching vectorized results of custom-documents/ggggggggggggggg.json to prevent duplicated embedding.","service":"backend"} {"level":"info","message":"\u001b[32m[TELEMETRY SENT]\u001b[0m {\"event\":\"documents_embedded_in_workspace\",\"distinctId\":\"353312ca-46e2-41b1-aefc-ae75951ffdeb\",\"properties\":{\"LLMSelection\":\"ollama\",\"Embedder\":\"inherit\",\"VectorDbSelection\":\"lancedb\",\"TTSSelection\":\"native\",\"LLMModel\":\"devstral:24b-small-2505-q4_K_M\"}}","service":"backend"} {"level":"info","message":"\u001b[32m[Event Logged]\u001b[0m - workspace_documents_added","service":"backend"}
yindo commented 2026-02-22 18:30:14 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jun 24, 2025):

Then I thought maybe something is wrong with my installation - so I removed it, went to %username%/appdata and deleted the setting there too Removed all environment variables

If I switch the vector to LanceDB Local embedding works

Is QDrant broken? I tried Milvus and did not work as well

I need to run in my local network, which one I should use?

A couple of things!

I have variables QDRANT_API_KEY QDRANT_URL VECTOR_DB set at system level and I specified the extra CA

These are not the variables we use to connect to QDrant. You can set up the connection via the UI in the Settings > Embedder page. Choose QDrant as the provider and enter the right information.

If this is local, the host is just http://localhost:PORT

Sounds just like you are not using the UI to set up this information and it does not inherit system vars you set or have in your bash/powershell session

@timothycarambat commented on GitHub (Jun 24, 2025): > Then I thought maybe something is wrong with my installation - so I removed it, went to %username%/appdata and deleted the setting there too Removed all environment variables > > If I switch the vector to LanceDB Local embedding works > > Is QDrant broken? I tried Milvus and did not work as well > > I need to run in my local network, which one I should use? A couple of things! > I have variables QDRANT_API_KEY QDRANT_URL VECTOR_DB set at system level and I specified the extra CA These are not the [variables ](https://github.com/Mintplex-Labs/anything-llm/blob/c4f49ff6b445f8f1b15d3bd42f8a2d24317b745c/server/utils/vectorDbProviders/qdrant/index.js#L15-L20)we use to connect to QDrant. You can set up the connection via the UI in the Settings > Embedder page. Choose QDrant as the provider and enter the right information. If this is local, the host is just `http://localhost:PORT` Sounds just like you are not using the UI to set up this information and it _does not_ inherit system vars you set or have in your bash/powershell session
yindo changed title from [BUG]: qdrant failing to import document with fetch failed to [GH-ISSUE #4024] [BUG]: qdrant failing to import document with fetch failed 2026-06-05 14:47:15 -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#2558
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?