retrieve_docs

Retrieve relevant documents from Morphik

Sync

def retrieve_docs(
    query: str,
    filters: Optional[Dict[str, Any]] = None,
    k: int = 4,
    min_score: float = 0.0,
    use_colpali: bool = True,
) -> List[DocumentResult]

def retrieve_docs(
    query: str,
    filters: Optional[Dict[str, Any]] = None,
    k: int = 4,
    min_score: float = 0.0,
    use_colpali: bool = True,
) -> List[DocumentResult]

async def retrieve_docs(
    query: str,
    filters: Optional[Dict[str, Any]] = None,
    k: int = 4,
    min_score: float = 0.0,
    use_colpali: bool = True,
) -> List[DocumentResult]

Parameters

• query (str): Search query text
• filters (Dict[str, Any], optional): Optional metadata filters
• k (int, optional): Number of results. Defaults to 4.
• min_score (float, optional): Minimum similarity threshold. Defaults to 0.0.
• use_colpali (bool, optional): Whether to use ColPali-style embedding model to retrieve the documents (only works for documents ingested with use_colpali=True). Defaults to True.

Returns

• List[DocumentResult]: List of document results

Examples

Sync

from morphik import Morphik

db = Morphik()

docs = db.retrieve_docs(
    "machine learning",
    k=5,
    min_score=0.5
)

for doc in docs:
    print(f"Score: {doc.score}")
    print(f"Document ID: {doc.document_id}")
    print(f"Metadata: {doc.metadata}")
    print(f"Content: {doc.content}")
    print("---")

from morphik import Morphik

db = Morphik()

docs = db.retrieve_docs(
    "machine learning",
    k=5,
    min_score=0.5
)

for doc in docs:
    print(f"Score: {doc.score}")
    print(f"Document ID: {doc.document_id}")
    print(f"Metadata: {doc.metadata}")
    print(f"Content: {doc.content}")
    print("---")

from morphik import AsyncMorphik

async with AsyncMorphik() as db:
    docs = await db.retrieve_docs(
        "machine learning",
        k=5,
        min_score=0.5
    )
    
    for doc in docs:
        print(f"Score: {doc.score}")
        print(f"Document ID: {doc.document_id}")
        print(f"Metadata: {doc.metadata}")
        print(f"Content: {doc.content}")
        print("---")

DocumentResult Properties

The DocumentResult objects returned by this method have the following properties:

• score (float): Relevance score
• document_id (str): Document ID
• metadata (Dict[str, Any]): Document metadata
• content (DocumentContent): Document content or URL