分类 Python SDK

import os
from dotenv import load_dotenv
from llama_cloud.client import AsyncLlamaCloud
from llama_cloud.types import ClassifierRule, ClassifyParsingConfiguration, ParserLanguages
from llama_cloud_services.beta.classifier.client import LlamaClassify  # helper wrapper

load_dotenv()

client = AsyncLlamaCloud(token=os.environ["LLAMA_CLOUD_API_KEY"])
project_id = "your-project-id"
classifier = LlamaClassify(client, project_id=project_id)

rules = [
    ClassifierRule(
        type="invoice",
        description="Documents that contain an invoice number, invoice date, bill-to section, and line items with totals."
    ),
    ClassifierRule(
        type="receipt",
        description="Short purchase receipts, typically from POS systems, with merchant, items and total, often a single page."
    ),
]

parsing = ClassifyParsingConfiguration(
    lang=ParserLanguages.EN,
    max_pages=5,            # optional, parse at most 5 pages
    # target_pages=[1]        # optional, parse only specific pages (1-indexed), can't be used with max_pages
)

# for async usage, use `await classifier.aclassify(...)`
results = classifier.classify(
    rules=rules,
    files=[
        "/path/to/doc1.pdf",
        "/path/to/doc2.pdf",
    ],
    parsing_configuration=parsing,
)

for item in results.items:
    # in cases of partial success, some of the items may not have a result
    if item.result is None:
        print(f"Classification job {item.classify_job_id} error-ed on file {item.file_id}")
        continue
    print(item.file_id, item.result.type, item.result.confidence)
    print(item.result.reasoning)