feat: Implement centralized storage for SPLADE and vector embeddings

- Added centralized SPLADE database and vector storage configuration in config.py.
- Updated embedding_manager.py to support centralized SPLADE database path.
- Enhanced generate_embeddings and generate_embeddings_recursive functions for centralized storage.
- Introduced centralized ANN index creation in ann_index.py.
- Modified hybrid_search.py to utilize centralized vector index for searches.
- Implemented methods to discover and manage centralized SPLADE and HNSW files.
This commit is contained in:
catlog22
2026-01-02 16:53:39 +08:00
parent 54fb7afdb2
commit 9157c5c78b
5 changed files with 1051 additions and 9 deletions

View File

@@ -19,6 +19,13 @@ WORKSPACE_DIR_NAME = ".codexlens"
# Settings file name
SETTINGS_FILE_NAME = "settings.json"
# SPLADE index database name (centralized storage)
SPLADE_DB_NAME = "_splade.db"
# Dense vector storage names (centralized storage)
VECTORS_HNSW_NAME = "_vectors.hnsw"
VECTORS_META_DB_NAME = "_vectors_meta.db"
log = logging.getLogger(__name__)