Skip to content

Conversation

@sobychacko
Copy link
Contributor

  • Precompute Document token count before sub-batching them as List<List<Document>>.
  • Configurable threshold value for the upper bound of max input tokens.

Resolves #1260

…BatchingStrategy`

- Precompute Document token count before sub-batching them as `List<List<Document>>`.
- Configurable threshold value for the upper bound of max input tokens.

Resolves spring-projects#1260
@markpollack markpollack self-assigned this Sep 4, 2024
@markpollack
Copy link
Member

merged in 73d0b30

renamed 'thresholdFactor' to 'reservePercentage' for clarity and refactored the formula to use (1 - reservePercentage) for clarity

@markpollack markpollack closed this Sep 4, 2024
@markpollack markpollack added this to the 1.0.0-M3 milestone Sep 4, 2024
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.

Batching strategy improvements

2 participants