batch_get_chunks

Retrieve specific chunks by their document ID and chunk number

Sync

def batch_get_chunks(
    sources: List[Union[ChunkSource, Dict[str, Any]]],
    folder_name: Optional[Union[str, List[str]]] = None,
    use_colpali: bool = True,
    output_format: Optional[str] = None,
) -> List[FinalChunkResult]

Async

async def batch_get_chunks(
    sources: List[Union[ChunkSource, Dict[str, Any]]],
    folder_name: Optional[Union[str, List[str]]] = None,
    use_colpali: bool = True,
    output_format: Optional[str] = None,
) -> List[FinalChunkResult]

Parameters

• sources (List[Union[ChunkSource, Dict[str, Any]]]): List of ChunkSource objects or dictionaries with document_id and chunk_number
• folder_name (str | List[str], optional): Optional folder scope. Accepts canonical paths or a list of paths/names.
• use_colpali (bool, optional): Whether to request multimodal chunks when available. Defaults to True.
• output_format (str, optional): Controls how image chunks are returned. Set to "url" to receive presigned URLs; omit or set to "base64" (default) to receive base64 content.

Returns

• List[FinalChunkResult]: List of chunk results

Examples

Sync

from morphik import Morphik
from morphik.models import ChunkSource

db = Morphik()

# Using dictionaries
sources = [
    {"document_id": "doc_123", "chunk_number": 0},
    {"document_id": "doc_456", "chunk_number": 2}
]

# Or using ChunkSource objects
sources = [
    ChunkSource(document_id="doc_123", chunk_number=0),
    ChunkSource(document_id="doc_456", chunk_number=2)
]

chunks = db.batch_get_chunks(sources)
for chunk in chunks:
    print(f"Chunk from {chunk.document_id}, number {chunk.chunk_number}: {chunk.content[:50]}...")

Async

from morphik import AsyncMorphik
from morphik.models import ChunkSource

async with AsyncMorphik() as db:
    # Using dictionaries
    sources = [
        {"document_id": "doc_123", "chunk_number": 0},
        {"document_id": "doc_456", "chunk_number": 2}
    ]
    
    # Or using ChunkSource objects
    sources = [
        ChunkSource(document_id="doc_123", chunk_number=0),
        ChunkSource(document_id="doc_456", chunk_number=2)
    ]
    
    chunks = await db.batch_get_chunks(sources)
    for chunk in chunks:
        print(f"Chunk from {chunk.document_id}, number {chunk.chunk_number}: {chunk.content[:50]}...")

FinalChunkResult Properties

Each FinalChunkResult object in the returned list has the following properties:

• content (str | PILImage): Chunk content (text or image)
• score (float): Relevance score
• document_id (str): Parent document ID
• chunk_number (int): Chunk sequence number
• metadata (Dict[str, Any]): Document metadata
• content_type (str): Content type
• filename (Optional[str]): Original filename
• download_url (Optional[str]): URL to download full document