θΏ™ζ˜―indexlocζδΎ›ηš„ζœεŠ‘οΌŒδΈθ¦θΎ“ε…₯任何密码
Skip to content

Conversation

@timothycarambat
Copy link
Member

@timothycarambat timothycarambat commented May 2, 2024

Pull Request Type

  • ✨ feat
  • πŸ› fix
  • ♻️ refactor
  • πŸ’„ style
  • πŸ”¨ chore
  • πŸ“ docs

Relevant Issues

resolves #1262

What is in this change?

  • User is on fresh installation of AnythingLLM with native embedder
  • Uploads a document which results in more than 1 chunk
  • Model will download from HuggingFace on chunk one
  • On subsequent chunks the model attempts to download again and then tries to embed
  • This pollutes the logs and results in unneeded cycles to attempt to download the pipeline even though it already exists.

Additional Information

Developer Validations

  • I ran yarn lint from the root of the repo & committed changes
  • Relevant documentation has been updated
  • I have tested my code functionality
  • Docker build succeeds locally

@timothycarambat timothycarambat merged commit 244ce2e into master May 2, 2024
@timothycarambat timothycarambat deleted the 1262-native-embedder-concurrent-downloads branch May 2, 2024 17:15
cabwds pushed a commit to cabwds/anything-llm that referenced this pull request Jul 3, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[BUG]: Multiple download of Xenova/all-MiniLM-L6-v2 on initial embed

2 participants