PDF Data Extraction Pipeline

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY")

namespace = client.namespaces.create(name="pdf-data")
collection = client.collections.create(
    namespace_id=namespace.id,
    name="invoices",
    extractors=["pdf-extraction", "table-extraction", "ocr"]
)

# Upload PDFs
client.buckets.upload(
    collection_id=collection.id,
    url="s3://your-bucket/invoices/"
)

# Search extracted data
results = client.documents.search(
    namespace_id=namespace.id,
    query="invoices over $10,000 from Q4"
)