Retrieval

VectorDBSettings:

Retrieval base settings.

provider_id: `VectorDBEnum`

Description: VectorDB provider id. Available options: "qdrant" | "pgvector".

config: `Union[QdrantSettings, PGVectorSettings]`

Description: VectorDB provider settings.\

prompt_utils: `Optional[PromptUtilsSettings]`

Description: Prompt utils settings. Default: None

extract_utils: `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]]`

Description: List of keys names to extract. Default: None

keys_mapping: `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"

Description: The model type. Default: "vector-db"

host: `str`

Description: Hostname of the PostgreSQL server. Default: "localhost"

port: `int`

Description: Port of the PostgreSQL server. Defualt: 5432

database: `str`

Description: Name of the PostgreSQL database.

user: `str`

Description: Username to authenticate with.

password: `str`

Description: Password to authenticate with.

table: `str`

Description: Name of the table to query. Default: "embedding_table"

embedding_column: `str`

Description: Name of the column containing embeddings. Default: "embedding"

search_parameters: `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`

Description: Qdrant collection name

init_kwargs: `Optional[dict]`

Description: Initialization kwargs for QdrantClient Default: None

search_parameters: `Optional[dict]`

Description: Additional parameters for the vector database. Default: None

PreviousLocal NextPromptUtils

Last updated 5 months ago

Was this helpful?

hashtagVectorDBSettings:

hashtagprovider_id: VectorDBEnum

hashtagconfig: Union[QdrantSettings, PGVectorSettings]

hashtagprompt_utils: Optional[PromptUtilsSettings]

hashtagextract_utils: Optional[ExtractUtilsSettings]

hashtagExtractUtilsSettings

hashtagkeys: Optional[List[str]]

hashtagkeys_mapping: Optional[Dict[str, str]]

hashtagDistances

hashtagPGVectorSettings

hashtagmodel_type: Literal["vector-db"] = "ector-db"

hashtaghost: str

hashtagport: int

hashtagdatabase: str

hashtaguser: str

hashtagpassword: str

hashtagtable: str

hashtagembedding_column: str

hashtagsearch_parameters: Optional[dict]

hashtagQdrantSettings:

hashtagmodel_type: Literal["vector-db"]*

hashtagcollection_name: str

hashtaginit_kwargs: Optional[dict]

hashtagsearch_parameters: Optional[dict]

VectorDBSettings:

provider_id: `VectorDBEnum`

config: `Union[QdrantSettings, PGVectorSettings]`

prompt_utils: `Optional[PromptUtilsSettings]`

extract_utils: `Optional[ExtractUtilsSettings]`

ExtractUtilsSettings

keys: `Optional[List[str]]`

keys_mapping: `Optional[Dict[str, str]]`

Distances

PGVectorSettings

model_type: `Literal["vector-db"]` = "ector-db"

host: `str`

port: `int`

database: `str`

user: `str`

password: `str`

table: `str`

embedding_column: `str`

search_parameters: `Optional[dict]`

QdrantSettings:

model_type: Literal["vector-db"]*

collection_name: `str`

init_kwargs: `Optional[dict]`

search_parameters: `Optional[dict]`