[GH-ISSUE #6414] Ollama embedding is slow #66068

Closed
opened 2026-05-03 23:50:48 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @yuanjie-ai on GitHub (Aug 19, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6414

Ollama embedding is slow

Originally created by @yuanjie-ai on GitHub (Aug 19, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6414 Ollama embedding is slow
GiteaMirror added the feature request label 2026-05-03 23:50:48 -05:00
Author
Owner

@rick-github commented on GitHub (Aug 19, 2024):

Example?

<!-- gh-comment-id:2295975832 --> @rick-github commented on GitHub (Aug 19, 2024): Example?
Author
Owner

@pdevine commented on GitHub (Aug 23, 2024):

@yuanjie-ai make certain you're using the new batch embeddings endpoint instead of the older endpoint which could only generate a single embedding at a time.

Given a lack of detail in the issue though, I'm going to go ahead and close it. Feel free to comment with more details if you think it should be re-opened.

<!-- gh-comment-id:2307927917 --> @pdevine commented on GitHub (Aug 23, 2024): @yuanjie-ai make certain you're using the new [batch embeddings endpoint](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-embeddings) instead of the older endpoint which could only generate a single embedding at a time. Given a lack of detail in the issue though, I'm going to go ahead and close it. Feel free to comment with more details if you think it should be re-opened.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#66068