ingest_files

from morphik import AsyncMorphik

async with AsyncMorphik() as db:
    # Batch ingest files with shared metadata
    result = await db.ingest_files(
        files=["document1.pdf", "document2.docx", "image.png"], 
        metadata={"category": "reports"},
        use_colpali=True,
        parallel=True
    )
    
    # Process the results
    for doc in result["documents"]:
        print(f"Successfully ingested: {doc.filename} (ID: {doc.external_id})")
    
    # Check for errors
    for error in result["errors"]:
        print(f"Error ingesting {error.get('filename')}: {error.get('error')}")

# Ingest files with different metadata for each file
files = ["report.pdf", "data.csv", "presentation.pptx"]

# Metadata must match the length of files list
metadata_list = [
    {"category": "reports", "author": "Alice"},
    {"category": "data", "source": "database"},
    {"category": "presentations", "department": "marketing"}
]

result = await db.ingest_files(
    files=files,
    metadata=metadata_list
)

import io
from pathlib import Path

# Mixing different file input types
file1 = "document.pdf"                       # Path string
file2 = Path("image.png")                    # Path object
file3 = open("data.csv", "rb")               # File object
file4 = b"Hello, world!"                     # Bytes (requires filename)
file5 = io.BytesIO(b"Some in-memory data")   # BytesIO (requires filename)

result = await db.ingest_files(
    files=[file1, file2, file3, file4, file5],
    metadata=[
        {"type": "document"},
        {"type": "image"},
        {"type": "data"},
        {"type": "text", "filename": "hello.txt"},
        {"type": "text", "filename": "memory-data.txt"}
    ]
)

# Don't forget to close file objects
file3.close()