Retrieval
VectorDBSettings:
Retrieval base settings.
provider_id: VectorDBEnum
VectorDBEnumDescription: VectorDB provider id. Available options: "qdrant" | "pgvector".
config: Union[QdrantSettings, PGVectorSettings]
Union[QdrantSettings, PGVectorSettings]Description: VectorDB provider settings.\
prompt_utils: Optional[PromptUtilsSettings]
Optional[PromptUtilsSettings]Description: Prompt utils settings.
Default: None
extract_utils: Optional[ExtractUtilsSettings]
Optional[ExtractUtilsSettings]Description: Extract utils settings.
Default: None
ExtractUtilsSettings
ExtractUtils setting. Used to extract keys from the response of the vector database. For example, some jinja prompt my expect the context for the vector-db to have specific keys which my not be the same as the keys in the response of the vector database. Thus, this setting can be used to extract and remap keys.
keys: Optional[List[str]]
Optional[List[str]]Description: List of keys names to extract.
Default: None
keys_mapping: Optional[Dict[str, str]]
Optional[Dict[str, str]]Description: Mapping of extracted keys.
Default: None
Distances
Available distances are: "l1" | "l2" | "inner_product" | "cosine". Note that "inner_product" is in fact the negative inner product.
PGVectorSettings
model_type: Literal["vector-db"] = "ector-db"
Literal["vector-db"] = "ector-db"Description: The model type.
Default: "vector-db"
host: str
strDescription: Hostname of the PostgreSQL server.
Default: "localhost"
port: int
intDescription: Port of the PostgreSQL server.
Defualt: 5432
database: str
strDescription: Name of the PostgreSQL database.
user: str
strDescription: Username to authenticate with.
password: str
strDescription: Password to authenticate with.
table: str
strDescription: Name of the table to query.
Default: "embedding_table"
embedding_column: str
strDescription: Name of the column containing embeddings.
Default: "embedding"
search_parameters: Optional[dict]
Optional[dict]Description: Additional parameters for the vector database.
Default: None
QdrantSettings:
model_type: Literal["vector-db"]*
Description: The model type. Default: "vector-db"
collection_name: str
strDescription: Qdrant collection name
init_kwargs: Optional[dict]
Optional[dict]Description: Initialization kwargs for QdrantClient
Default: None
search_parameters: Optional[dict]
Optional[dict]Description: Additional parameters for the vector database.
Default: None
Last updated
Was this helpful?