Skip to content

Conversation

@khoroshevskyi
Copy link
Member

@khoroshevskyi khoroshevskyi commented Dec 18, 2025

Changes:

  • Updated qdrant and encoder model initialization. (One connection for qdrant and one initialized object per model)
  • Added hybrid semantic search.(dense + sparse search)

TODO:

  • Version of pepdbagent updated in __version__.py file
  • Changelog updated

Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR updates the project to version 0.14.0, introducing hybrid semantic search capabilities that combine dense and sparse embeddings for improved search accuracy. The key architectural change is the refactoring of Qdrant and encoder model initialization to use a single Qdrant connection and initialized encoder objects that are reused throughout the application.

Key Changes:

  • Refactored Qdrant client initialization to use a single shared QdrantClient instance
  • Added hybrid search functionality combining dense (semantic) and sparse (keyword-based) retrieval
  • Updated encoder initialization to create persistent instances (dense, sparse, r2v, umap) for reuse
  • Updated Python version support from 3.9-3.12 to 3.10-3.13 in CI workflows

Reviewed changes

Copilot reviewed 16 out of 16 changed files in this pull request and generated 16 comments.

Show a summary per file
File Description
bbconf/_version.py Version bumped to 0.14.0
bbconf/config_parser/const.py Added sparse model constant and renamed Qdrant collection constants for clarity
bbconf/config_parser/models.py Updated model paths and Qdrant collection names to match new constants
bbconf/config_parser/bedbaseconfig.py Major refactoring: single Qdrant client initialization, separate encoder instances, new hybrid collection setup
bbconf/modules/bedfiles.py Updated to use new encoder properties, added hybrid_search method, refactored semantic search
requirements/requirements-all.txt Updated geniml dependency from 0.7.1 to 0.8.2
tests/config_test.yaml Updated region2vec model name to use new naming convention
.github/workflows/*.yml Updated Python versions and GitHub Actions versions
Import organization files Reorganized imports alphabetically for consistency

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

@khoroshevskyi khoroshevskyi merged commit f03f1ba into master Dec 22, 2025
8 checks passed
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.

2 participants