Skip to content

feat(embedding): add pass_dimensions option to OpenAI embedding#1758

Open
jinliyl wants to merge 3 commits into
agentscope-ai:mainfrom
jinliyl:dev/0602
Open

feat(embedding): add pass_dimensions option to OpenAI embedding#1758
jinliyl wants to merge 3 commits into
agentscope-ai:mainfrom
jinliyl:dev/0602

Conversation

@jinliyl
Copy link
Copy Markdown
Member

@jinliyl jinliyl commented Jun 2, 2026

  • Added pass_dimensions parameter to control whether dimensions are passed to API
  • Updated constructor to accept pass_dimensions with default value True
  • Modified API call to conditionally include dimensions based on pass_dimensions
  • Implemented proper embedding result mapping by index to handle sparse responses
  • Updated embedding retrieval and storage to use indexed mapping instead of simple lists
  • Added fallback to dense_embedding when regular embedding is not available

PR Title Format

Please ensure your PR title follows the Conventional Commits format:

  • Format: <type>(<scope>): <description>
  • Example: feat(memory): add redis cache support
  • Allowed types: feat, fix, docs, ci, refactor, test, chore, perf, style, build, revert
  • Description should start with a lowercase letter

AgentScope Version

[The version of AgentScope you are working on, e.g. import agentscope; print(agentscope.__version__)]

Description

[Please describe the background, purpose, changes made, and how to test this PR]

Checklist

Please check the following items before code is ready to be reviewed.

  • Code has been formatted with pre-commit run --all-files command
  • All tests are passing
  • Docstrings are in Google style
  • Related documentation has been updated (e.g. links, examples, etc.)
  • Code is ready for review

jinliyl added 3 commits June 2, 2026 18:05
- Added pass_dimensions parameter to control whether dimensions are passed to API
- Updated constructor to accept pass_dimensions with default value True
- Modified API call to conditionally include dimensions based on pass_dimensions
- Implemented proper embedding result mapping by index to handle sparse responses
- Updated embedding retrieval and storage to use indexed mapping instead of simple lists
- Added fallback to dense_embedding when regular embedding is not available
…bedding handler

- Removed redundant None check and list conversion for embedding vectors
- Streamlined the embedding assignment to directly use emb.embedding or dense_embedding
- Maintained existing caching functionality for stored embeddings
- Improved code readability by reducing nested conditional logic
…ponse handling

- Changed getattr call to use proper attribute access with fallback
- Improved code readability by formatting multi-line attribute access
- Maintained existing functionality while enhancing code structure
- Applied consistent spacing and formatting for better maintainability
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.

1 participant