autogen.retrieve_utils.query_vector_db

query_vector_db

query_vector_db(
    query_texts: list[str],
    n_results: int = 10,
    client: API = None,
    db_path: str = 'tmp/chromadb.db',
    collection_name: str = 'all-my-documents',
    search_string: str = '',
    embedding_model: str = 'all-MiniLM-L6-v2',
    embedding_function: Callable = None
) -> QueryResult

Query a vector db. We support chromadb compatible APIs, it’s not required if you prepared your own vector db and query function.

Parameters:

Name	Description
query_texts	the list of strings which will be used to query the vector db. Type: list[str]
n_results	the number of results to return. Default is 10. Type: int Default: 10
client	the chromadb compatible client. Default is None, a chromadb client will be used. Type: API Default: None
db_path	the path to the vector db. Default is “tmp/chromadb.db”. The default was /tmp/chromadb.db for version =0.2.24. Type: str Default: ‘tmp/chromadb.db’
collection_name	the name of the collection. Default is “all-my-documents”. Type: str Default: ‘all-my-documents’
search_string	the search string. Only docs that contain an exact match of this string will be retrieved. Default is "". Type: str Default: ”
embedding_model	the embedding model to use. Default is “all-MiniLM-L6-v2”. Will be ignored if embedding_function is not None. Type: str Default: ‘all-MiniLM-L6-v2’
embedding_function	the embedding function to use. Default is None, SentenceTransformer with the given embedding_model will be used. If you want to use OpenAI, Cohere, HuggingFace or other embedding functions, you can pass it here, follow the examples in https://docs.trychroma.com/embeddings. Type: Callable Default: None

Returns:

Type	Description
QueryResult	The query result. The format is: python class QueryResult(TypedDict): ids: List[IDs] embeddings: Optional[List[List[Embedding]]] documents: Optional[List[List[Document]]] metadatas: Optional[List[List[Metadata]]] distances: Optional[List[List[float]]]