mirror of
https://github.com/Mintplex-Labs/anything-llm.git
synced 2026-07-19 14:13:35 -04:00
Closed
opened 2026-02-22 18:30:03 -05:00 by yindo
·
11 comments
No Branch/Tag Specified
master
5846-bug-when-scrolling-up-scrolling-jumps
refactor-remove-workspace-pfp
5969-bug-stopgenerationbutton-disappears-on-the-first-prompt-that-initiates-an-agent-session
2235-bug-how-to-upload-a-folder-with-subfolders-with-files-to-anythingllm
5990-workspace-update-fails-with-unknown-argument-router_id-v1130v1150-intel-mac
opencomputer-examples
pg
feat/image-generation-translations
feat/image-generation
5924-bug-meeting-summary-fails-with-sincludes-is-not-a-function-when-default-llm-is-anthropic-claude
render
feat/uniform-modal-component
5883-bug-unescaped-content-in-json-strings-being-passed-to-document-generator-tools
5901-bug-api-update-embeddings-fails-prisma-argument-filename-is-missing-on-workspace_documentscreate-desktop-windows-v1141
hybrid-search
1981-translations
5752-bug-prompts-to-local-jan-endpoint-unresponsive
feat-disable-native-tool-calling-env-var
5676-bug-non-ollama-agent-providers-do-not-parse-and-present-reasoning-content
feat/markdown-web-scraping
5717-bug-apiv1documentupload-silently-drops-metadata-field-in-desktop-1130-arg-count-mismatch-nested-payload-key
fix/aibitat-context-overflow
5711-bug-erratic-deepseek-v4-flash-the-agent-model-failed-to-respond-400-the-reasoning_content
5631-feat-custom-api-request-timeouts-for-ai-providers
feat-reasoning-control
feat-agent-clarifying-questions-translations
5583-bug-lm-studio-provider-does-not-present-reasoning-output
5313-normalize-translations
feat/memory-translations
5305-lemonade-embedding-engine-swallows-errors-falsely-reports-documents-as-embedded
5060-bug-agent-interactions-agent-are-not-persisted-to-thread-history-via-api
pptx-subagent
feat-render-images-from-mcp-tool-results
stt-provider-expansion-openai-api-compatible
feat-file-search-agent-tool
feat-native-embedder-job-queue
5189-normalize-translations
feat-file-search-agent-tool-translations
i18n-eslint
5140-auto-migration
5112-bug-openrouter-failed-message-bug
3506-feat-parameters-for-openrouter-models
4992-feat-preserve-scroll-position
4973-bug-markdown-numbered-list-display-in-reasoning-pane
desktop
4938-bug-pending-chat-rerendering-ui-bug
quickstart-env
node-llama-cpp-in-container-cuda
node-llama-cpp-in-container
ollama-in-container
4817-feat-set-cooldown-per-mcp-server
4845-keyboard-shortcuts-to-navigate-in-chat
4844-feat-reorder-threads-by-latest-interaction
standardize-username-constraints-normalize-translations
4792-feat-refactor-workspacepfp-image
1382-embed-ip-improvements
1382-bug-embed-api-improvements
refactor-eslint-frontend
4687-feat-refactor-vector-db-providers
4615-feat-disable-apidocs-with-environment-variable
4559-feat-agent-web-search-enable-ordering-of-results
4599-bug-ollama-race-condition-bug
4572-bug-lmstudio-provided-llm-stopped-working-with-anything-llm-after-upgrading-to-190
4508-agent-youtube-transcript-analysis
4497-feat-workspace-names
frontend-eslint
ollama-lmstudio-auto-context-window
4431-validate-vector-database-connectioN
2019-slash-command-keyboard-selection
microsoft-foundry-provider
4431-validate-vector-database-connection
4325-sys-prompt-var-improvements
3209-feat-apiv1workspacestream-chat-sources-citations
4210-bug-voice-to-text-overwrite
4136-feat-jan-as-a-backend-server-option
4172-feat-openai-o3-support
1.8.3-rerelease
web-push-notifications-service
tasks
3955-feat-jinaai-embedder-provider-support
3921-feat-agent-skills-uiux-improvements
3901-bug-validfunccall-checks-optional-arguments
keyboard-dev
1787-custom-roles-and-permissions
add-jira-slack-data-connector
office-extension-wip
lightmode-dropdown-color-update
3586-bug-agent-flow-function-description-provided-by-user-is-not-seen-in-the-llm-query
3463-bug-agent-continues-to-run-if-request-failed-even-after-exit
3439-feat-call-variables-within-the-flow-api-block-url-field
3282-manager-view-models-workspace
3280-token-counting-server-side-truncation-improvements
3147-bug-embedded-chat-widget---not-considering-query-mode-option-always-working-in-chat-mode
2995-feat-disable-temperature-setting-for-deepseek-r1-deepseek-reasoner-model
2827-feat-perplexity-citations
2866-feat-finally-a-gemini-models-endpoint
2647-feat-hpp-header-for-a-c++-code-file-mime-addition
lancedb-revert
1656-feat-implement-tooltip-ui-designs
2011-feat-bump-perplexity-models
1873-feat-auto-add-and-watch-folder-for-document-uploads
1297-feat-gemini-agent-support
1759-bug-ui-bug-fixes
1686-feat-implement-winston-for-logging
1536-bug-toggling-on-users-can-delete-workspaces-does-not-take-effect
agent-ui-mobile-styles
1522-feat-chromadb-support
1595-bug-unable-to-get-live-web-search-and-browsing-agent-working-using-google-custom-search-engine-error-getaddrinfo-enotfound-http-errno-3008
1582-bug-lm-studio-does-not-allow-for-different-model-selection
1312-bug-usernames-should-not-be-case-sensitive-when-logging-in
1029-feat-hf-serverless-inference-api
1086-feat-implement-normalized-input-fields
knowledge-graph-support
644-bug-uploaded-file-name-does-not-match-the-displayed-file-name-after-the-upload
v1.15.0
v1.14.2
v1.14.1
v1.14.0
v1.13.0
v1.12.1
v1.12.0
v1.11.2
v1.11.1
v1.11.0
v1.10.0
v1.9.1
v1.9.0
v1.8.5
v1.8.4
v1.8.3
v1.8.2
v1.8.1
v1.8.0
v1.7.8
v1.7.6
v1.7.5
v1.7.4
v1.4.0
v1.3.0
v1.2.4
v1.2.3
v1.2.2
v1.2.1
v1.2.0
v1.1.1
v1.1.0
v1.0.0
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
question
stage: specifications
wontfix
Mirrored from GitHub Pull Request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: Mintplex-Labs/anything-llm#2523
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
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?
Originally created by @alainlizotte on GitHub (Jun 6, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3962
How are you running AnythingLLM?
Docker (local)
What happened?
When embedding files to my workspace, after about 3 minutes, I get an error message (Failed to execute "JSON" on"response"..) and the files window updates showing incomplete listing.
But I can hear that the CPU is still working. If I close et reopen the embedding window after a little while, I can see the complete file listing.
I don't know if everything gets embedded correctly.
Seems to be a kind of timeout when embedding large files (but largest is about 2 MB).
Using Milvus Vector Database and Ollama for embedding (BGE-M3).
Are there known steps to reproduce?
No response
@timothycarambat commented on GitHub (Jun 6, 2025):
In this case, can you view your logs to see a more definitive log or error? An unexpected JSON output is very weird, which would seem to indicate a connection aborted. BGE-M3 is not a crazy large model but depending on the size and amount of embeddings, it is possible that either Ollama is getting OOM errors or something outside of AnythingLLM is going down.
Since we dont get a JSON response as completed, it would indicate that the external service is failing/crashing and not something in AnythingLLM, which would be out of our scope to resolve.
Also what are the specs of the computer, since Ollama is using those resources to do the embeddings?
@alainlizotte commented on GitHub (Jun 6, 2025):
@timothycarambat
Computer:
CPU: Intel 13600K
GPU: GeForce RTX 3060 Ti (8GB)
Ram: 32GB DDR4
@alainlizotte commented on GitHub (Jun 6, 2025):
@timothycarambat
Here is the log in Docker. The error in AnythingLLM is appening during the line ([backend] info: [OllamaEmbedder] Embedding 962 chunks of text with bge-m3:latest.)
This log was started juste before re-embedding my files.
2025-06-06 17:20:41.878 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:20:41.878 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:20:41.882 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:20:41.884 | [backend] info: Chunks created from document: 65
2025-06-06 17:20:41.886 | [backend] info: [OllamaEmbedder] Embedding 65 chunks of text with bge-m3:latest.
2025-06-06 17:20:48.294 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:20:48.346 | [backend] info: Caching vectorized results of SST/CCHST-Enquete-sur-les-incidents.pdf-d516fe87-36af-47a5-8c97-c737584f6a38.json to prevent duplicated embedding.
2025-06-06 17:20:51.352 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:20:51.352 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:20:51.355 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:20:51.356 | [backend] info: Chunks created from document: 28
2025-06-06 17:20:51.357 | [backend] info: [OllamaEmbedder] Embedding 28 chunks of text with bge-m3:latest.
2025-06-06 17:20:53.015 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:20:53.039 | [backend] info: Caching vectorized results of SST/CCHST-diligence-raisonnable.pdf-63d6d682-204e-49a3-8fc4-b11090b1d6fb.json to prevent duplicated embedding.
2025-06-06 17:20:53.302 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:20:53.302 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:20:53.305 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:20:53.310 | [backend] info: Chunks created from document: 417
2025-06-06 17:20:53.312 | [backend] info: [OllamaEmbedder] Embedding 417 chunks of text with bge-m3:latest.
2025-06-06 17:21:13.604 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:21:13.869 | [backend] info: Caching vectorized results of SST/LOI-SUR-LA-SANTE-ET-LA-SECURITE-DU-TRAVAIL.pdf-73ea42eb-8a6f-4643-ad49-6f6f73f8b852.json to prevent duplicated embedding.
2025-06-06 17:21:16.820 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:21:16.820 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:21:16.823 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:21:16.837 | [backend] info: Chunks created from document: 745
2025-06-06 17:21:16.840 | [backend] info: [OllamaEmbedder] Embedding 745 chunks of text with bge-m3:latest.
2025-06-06 17:21:54.163 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:21:54.604 | [backend] info: Caching vectorized results of SST/LOI-SUR-LES-ACCIDENTS-DU-TRAVAIL-ET-LES-MALADIES-PROFESSIONNELLES.pdf-cd060df8-c930-4aa2-b9fb-9556ab14b6d0.json to prevent duplicated embedding.
2025-06-06 17:21:57.363 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:21:57.363 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:21:57.368 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:21:57.369 | [backend] info: Chunks created from document: 88
2025-06-06 17:21:57.369 | [backend] info: [OllamaEmbedder] Embedding 88 chunks of text with bge-m3:latest.
2025-06-06 17:22:01.661 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:22:01.719 | [backend] info: Caching vectorized results of SST/Reglement-sur-l'information-concernant-les-produits-dangereux.pdf-b0992391-8865-4900-bf28-ee65aa4ea74a.json to prevent duplicated embedding.
2025-06-06 17:22:02.241 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:22:02.241 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:22:02.245 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:22:02.261 | [backend] info: Chunks created from document: 962
2025-06-06 17:22:02.262 | [backend] info: [OllamaEmbedder] Embedding 962 chunks of text with bge-m3:latest.
2025-06-06 17:22:49.264 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:22:49.765 | [backend] info: Caching vectorized results of SST/Reglement-sur-la-sante-et-la-securite-du-travail.pdf-8c7dac6e-eb8a-4929-a858-8394043e6c13.json to prevent duplicated embedding.
2025-06-06 17:22:52.798 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:22:52.798 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:22:52.801 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:22:52.802 | [backend] info: Chunks created from document: 94
2025-06-06 17:22:52.804 | [backend] info: [OllamaEmbedder] Embedding 94 chunks of text with bge-m3:latest.
2025-06-06 17:22:57.581 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:22:57.663 | [backend] info: Caching vectorized results of SST/Reglement-sur-le-representant-a-la-prevention-dans-un-etablissement.pdf-4f9bf33a-80cb-435c-82d1-c7f3d94d407c.json to prevent duplicated embedding.
2025-06-06 17:22:58.167 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:22:58.167 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:22:58.170 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:22:58.171 | [backend] info: Chunks created from document: 111
2025-06-06 17:22:58.172 | [backend] info: [OllamaEmbedder] Embedding 111 chunks of text with bge-m3:latest.
2025-06-06 17:23:03.544 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:23:03.629 | [backend] info: Caching vectorized results of SST/Reglement-sur-les-comites-de-sante-et-de-securite-du-travail.pdf-d7399501-3998-40b1-b186-0e8e3e05c4e1.json to prevent duplicated embedding.
2025-06-06 17:23:06.711 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:23:06.712 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:23:06.715 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:23:06.715 | [backend] info: Chunks created from document: 24
2025-06-06 17:23:06.716 | [backend] info: [OllamaEmbedder] Embedding 24 chunks of text with bge-m3:latest.
2025-06-06 17:23:07.931 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:23:07.955 | [backend] info: Caching vectorized results of SST/Roles-et-fonctions-du-representant-a-la-prevention.docx-15989f9e-c54e-42c0-88eb-5a2a37d1d7d6.json to prevent duplicated embedding.
2025-06-06 17:23:08.196 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:23:08.196 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:23:08.199 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:23:08.199 | [backend] info: Chunks created from document: 11
2025-06-06 17:23:08.200 | [backend] info: [OllamaEmbedder] Embedding 11 chunks of text with bge-m3:latest.
2025-06-06 17:23:08.697 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:23:08.707 | [backend] info: Caching vectorized results of SST/accident-travail.docx-6d294a85-916d-4045-aa82-58fb04b5eaab.json to prevent duplicated embedding.
2025-06-06 17:23:08.887 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:23:08.887 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:23:08.891 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:23:08.891 | [backend] info: Chunks created from document: 5
2025-06-06 17:23:08.892 | [backend] info: [OllamaEmbedder] Embedding 5 chunks of text with bge-m3:latest.
2025-06-06 17:23:09.156 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:23:09.174 | [backend] info: Caching vectorized results of SST/droit-de-refus.docx-7fe94752-f1a5-4e3d-9522-fc97340c1a7d.json to prevent duplicated embedding.
2025-06-06 17:23:09.329 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:23:09.329 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:23:09.332 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:23:09.332 | [backend] info: Chunks created from document: 5
2025-06-06 17:23:09.333 | [backend] info: [OllamaEmbedder] Embedding 5 chunks of text with bge-m3:latest.
2025-06-06 17:23:09.610 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:23:09.632 | [backend] info: Caching vectorized results of SST/enquete.docx-c1e6e0e3-1658-48a2-9589-dcbb22efb1f2.json to prevent duplicated embedding.
2025-06-06 17:23:09.802 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:23:09.802 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:23:09.806 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:23:09.806 | [backend] info: Chunks created from document: 11
2025-06-06 17:23:09.807 | [backend] info: [OllamaEmbedder] Embedding 11 chunks of text with bge-m3:latest.
2025-06-06 17:23:10.345 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:23:10.355 | [backend] info: Caching vectorized results of SST/formation.docx-734dc5da-1210-4ce0-868d-125d4753d93f.json to prevent duplicated embedding.
2025-06-06 17:23:10.545 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:23:10.545 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:23:10.548 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:23:10.548 | [backend] info: Chunks created from document: 9
2025-06-06 17:23:10.549 | [backend] info: [OllamaEmbedder] Embedding 9 chunks of text with bge-m3:latest.
2025-06-06 17:23:10.988 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:23:10.999 | [backend] info: Caching vectorized results of SST/harcelement.docx-987de628-bced-4eba-83fa-a4944d31a9cd.json to prevent duplicated embedding.
2025-06-06 17:23:11.172 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:23:11.172 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:23:11.174 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:23:11.174 | [backend] info: Chunks created from document: 13
2025-06-06 17:23:11.175 | [backend] info: [OllamaEmbedder] Embedding 13 chunks of text with bge-m3:latest.
2025-06-06 17:23:11.775 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:23:11.794 | [backend] info: Caching vectorized results of SST/multiprevention-diligence-raisonnable.pdf-907950bb-1542-4157-b4ba-1a04b134c555.json to prevent duplicated embedding.
2025-06-06 17:23:11.981 | [backend] info: Adding new vectorized document into namespace cnesst
2025-06-06 17:23:11.981 | [backend] info: [OllamaEmbedder] initialized with model bge-m3:latest at http://172.17.0.1:11434. num_ctx: 600
2025-06-06 17:23:11.984 | [backend] info: [RecursiveSplitter] Will split with {"chunkSize":600,"chunkOverlap":100}
2025-06-06 17:23:11.984 | [backend] info: Chunks created from document: 10
2025-06-06 17:23:11.985 | [backend] info: [OllamaEmbedder] Embedding 10 chunks of text with bge-m3:latest.
2025-06-06 17:23:12.448 | [backend] info: Inserting vectorized chunks into Milvus.
2025-06-06 17:23:12.471 | [backend] info: Caching vectorized results of SST/quoi-faire-harcelement.docx-ba1526d1-6a1f-432c-b7a2-4f2d7992d7f9.json to prevent duplicated embedding.
2025-06-06 17:23:12.643 | [backend] info: [TELEMETRY SENT] {"event":"documents_embedded_in_workspace","distinctId":"1ce1fa87-f54c-4208-a020-750c6d6ec7b6","properties":{"LLMSelection":"ollama","Embedder":"ollama","VectorDbSelection":"milvus","TTSSelection":"native","LLMModel":"qwen3:8b-q4_K_M","runtime":"docker"}}
2025-06-06 17:23:12.659 | [backend] info: [Event Logged] - workspace_documents_added
@alainlizotte commented on GitHub (Jun 6, 2025):
Never during the process, the VRAM or GPU got maxed out.
@alainlizotte commented on GitHub (Jun 6, 2025):
I'm using the latest version of AnythingLLM, Ollama and Docker.
But this error was there with older releases too.
@timothycarambat commented on GitHub (Jun 9, 2025):
This would very much seem to be related to the Ollama embedder basically be overwhelmed
https://github.com/Mintplex-Labs/anything-llm/blob/020acde3b9831daf16ea174b2edbbda6272f61ea/server/utils/EmbeddingEngines/ollama/index.js#L78-L80
What do you have set as the max token size for this model? It should be 8192 max but I would go a bit under just for how tokenization occurs since it would be super accurate for each chunk
@alainlizotte commented on GitHub (Jun 9, 2025):
@timothycarambat
@alainlizotte commented on GitHub (Jun 9, 2025):
@timothycarambat
Here is my Ollama Log while embedding.
ollama_log.txt
@alainlizotte commented on GitHub (Jun 9, 2025):
The error message at the end may be because I just tried to enable KeepAlive = 5min.
@alainlizotte commented on GitHub (Jun 11, 2025):
Same result with new AnythingLLM release.
@alainlizotte commented on GitHub (Jun 24, 2025):
Tryied a lot of things as you can see here:
https://discord.com/channels/1114740394715004990/1383199890493935617
Nothing fixed the error. :(
[BUG]: Embedding timeoutto [GH-ISSUE #3962] [BUG]: Embedding timeout