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 #3107] [BUG]: Ollama stops while using an embedding model on a large repository #1992

New Issue
Closed
opened 2026-02-22 18:27:37 -05:00 by yindo · 2 comments
yindo commented 2026-02-22 18:27:37 -05:00
Owner
Copy Link
Copy Source

Originally created by @emad-qadri on GitHub (Feb 4, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3107

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

I am using an open source embedder via Ollama (unclemusclez/jina-embeddings-v2-base-code:latest) to embed a large repository. However, the embeddings are never completed. Looks like Ollama service stops in between (see portion of logs below). I know the chunks are embedded sequentially to avoid overwhelming the Ollama API; what else could be the reason?

https://github.com/Mintplex-Labs/anything-llm/blob/cded1404cc018d83a0dceb1eb609d3e0ad9bd2b7/server/utils/EmbeddingEngines/ollama/index.js#L46

{"level":"error","message":"Failed to vectorize WakelockPowerCalculator.java","service":"backend"}
{"level":"info","message":"Adding new vectorized document into namespace new-test","service":"backend"}
{"level":"info","message":"\u001b[32m[TELEMETRY SENT]\u001b[0m {"event":"documents_embedded_in_workspace","distinctId":"4dd208d1-fca3-4021-bc4d-3503352ebefb","properties":{"LLMSelection":"openrouter","Embedder":"ollama","VectorDbSelection":"lancedb","TTSSelection":"native","runtime":"desktop"}}","service":"backend"}
{"level":"info","message":"\u001b[35m[RecursiveSplitter]\u001b[0m Will split with {"chunkSize":8192,"chunkOverlap":20}","service":"backend"}
{"level":"info","message":"Chunks created from document: 2","service":"backend"}
{"level":"info","message":"\u001b[36m[wa]\u001b[0m fetch failed","service":"backend"}
{"level":"error","message":"addDocumentToNamespace Ollama service could not be reached. Is Ollama running?","service":"backend"}
{"level":"error","message":"Failed to vectorize WatchlistConfig.java","service":"backend"}
{"level":"info","message":"Adding new vectorized document into namespace new-test","service":"backend"}
{"level":"info","message":"\u001b[32m[Event Logged]\u001b[0m - workspace_documents_added","service":"backend"}
{"level":"info","message":"\u001b[35m[RecursiveSplitter]\u001b[0m Will split with {"chunkSize":8192,"chunkOverlap":20}","service":"backend"}
{"level":"info","message":"Chunks created from document: 3","service":"backend"}
{"level":"info","message":"\u001b[36m[wa]\u001b[0m fetch failed","service":"backend"}
{"level":"error","message":"addDocumentToNamespace Ollama service could not be reached. Is Ollama running?","service":"backend"}
{"level":"error","message":"Failed to vectorize WatchlistLoggingHandler.java","service":"backend"}

Are there known steps to reproduce?

No response

Originally created by @emad-qadri on GitHub (Feb 4, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3107 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? I am using an open source embedder via Ollama (unclemusclez/jina-embeddings-v2-base-code:latest) to embed a large repository. However, the embeddings are never completed. Looks like Ollama service stops in between (see portion of logs below). I know the chunks are embedded sequentially to avoid overwhelming the Ollama API; what else could be the reason? https://github.com/Mintplex-Labs/anything-llm/blob/cded1404cc018d83a0dceb1eb609d3e0ad9bd2b7/server/utils/EmbeddingEngines/ollama/index.js#L46 {"level":"error","message":"Failed to vectorize WakelockPowerCalculator.java","service":"backend"} {"level":"info","message":"Adding new vectorized document into namespace new-test","service":"backend"} {"level":"info","message":"\u001b[32m[TELEMETRY SENT]\u001b[0m {\"event\":\"documents_embedded_in_workspace\",\"distinctId\":\"4dd208d1-fca3-4021-bc4d-3503352ebefb\",\"properties\":{\"LLMSelection\":\"openrouter\",\"Embedder\":\"ollama\",\"VectorDbSelection\":\"lancedb\",\"TTSSelection\":\"native\",\"runtime\":\"desktop\"}}","service":"backend"} {"level":"info","message":"\u001b[35m[RecursiveSplitter]\u001b[0m Will split with {\"chunkSize\":8192,\"chunkOverlap\":20}","service":"backend"} {"level":"info","message":"Chunks created from document: 2","service":"backend"} {"level":"info","message":"\u001b[36m[wa]\u001b[0m fetch failed","service":"backend"} {"level":"error","message":"addDocumentToNamespace Ollama service could not be reached. Is Ollama running?","service":"backend"} {"level":"error","message":"Failed to vectorize WatchlistConfig.java","service":"backend"} {"level":"info","message":"Adding new vectorized document into namespace new-test","service":"backend"} {"level":"info","message":"\u001b[32m[Event Logged]\u001b[0m - workspace_documents_added","service":"backend"} {"level":"info","message":"\u001b[35m[RecursiveSplitter]\u001b[0m Will split with {\"chunkSize\":8192,\"chunkOverlap\":20}","service":"backend"} {"level":"info","message":"Chunks created from document: 3","service":"backend"} {"level":"info","message":"\u001b[36m[wa]\u001b[0m fetch failed","service":"backend"} {"level":"error","message":"addDocumentToNamespace Ollama service could not be reached. Is Ollama running?","service":"backend"} {"level":"error","message":"Failed to vectorize WatchlistLoggingHandler.java","service":"backend"} ### Are there known steps to reproduce? _No response_
yindo added the possible bugneeds info / can't replicateinvestigating labels 2026-02-22 18:27:37 -05:00
yindo closed this issue 2026-02-22 18:27:37 -05:00
yindo commented 2026-02-22 18:27:37 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Feb 4, 2025):

In Ollama do you see logs that indicate that any requests complete. It seems that the text is split, but it is not able to reach the ollama endpoint. On desktop this simply is just http://localhost:11434 and requires the ollama server to be running so we can use the REST API.

Do you see any of that traffic to the Ollama server?

@timothycarambat commented on GitHub (Feb 4, 2025): In Ollama do you see logs that indicate that _any_ requests complete. It seems that the text is split, but it is not able to reach the ollama endpoint. On desktop this simply is just `http://localhost:11434` and _requires_ the ollama server to be running so we can use the REST API. Do you see any of that traffic to the Ollama server?
yindo commented 2026-02-22 18:27:38 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Feb 5, 2025):

closing until bug or more information is available for repro

@timothycarambat commented on GitHub (Feb 5, 2025): closing until bug or more information is available for repro
yindo changed title from [BUG]: Ollama stops while using an embedding model on a large repository to [GH-ISSUE #3107] [BUG]: Ollama stops while using an embedding model on a large repository 2026-06-05 14:43:52 -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 investigating needs info / can't replicate 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#1992
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?