Vector Databases
PgVector
Vector Databases
PgVector
| Parameter | Type | Default | Description |
|---|---|---|---|
table_name | str | Required | Name of the table to store vectors and metadata |
schema | str | "ai" | Database schema name |
db_url | Optional[str] | None | Database connection URL |
db_engine | Optional[Engine] | None | SQLAlchemy database engine |
embedder | Optional[Embedder] | OpenAIEmbedder() | Embedder instance to generate embeddings |
search_type | SearchType | SearchType.vector | Type of search to perform (vector, keyword, or hybrid) |
vector_index | Union[Ivfflat, HNSW] | HNSW() | Vector index configuration |
distance | Distance | Distance.cosine | Distance metric for vector comparisons |
prefix_match | bool | False | Enable prefix matching for full-text search |
vector_score_weight | float | 0.5 | Weight for vector similarity in hybrid search |
content_language | str | "english" | Language for full-text search |
schema_version | int | 1 | Version of the database schema |
auto_upgrade_schema | bool | False | Automatically upgrade schema if True |
reranker | Optional[Reranker] | None | Reranker instance for post-processing search results |