Vector Databases
LanceDb
Parameter | Type | Default | Description |
---|---|---|---|
uri | lancedb.URI | "/tmp/lancedb" | URI path or connection string for LanceDB |
table | Optional[lancedb.db.LanceTable] | None | Pre-configured LanceDB table instance |
table_name | Optional[str] | None | Name of the table to store vectors and metadata |
connection | Optional[lancedb.LanceDBConnection] | None | Pre-configured LanceDB connection |
api_key | Optional[str] | None | API key for cloud LanceDB authentication |
embedder | Optional[Embedder] | OpenAIEmbedder() | Embedder instance to generate embeddings |
search_type | SearchType | SearchType.vector | Type of search to perform (vector, keyword, or hybrid) |
distance | Distance | Distance.cosine | Distance metric to use for similarity search |
nprobes | Optional[int] | None | Number of probes for approximate nearest neighbor search |
reranker | Optional[Reranker] | None | Optional reranker instance to rerank search results |
use_tantivy | bool | True | Whether to use Tantivy for full-text search indexing |