run-llama/vibe-llama/structured-data-extraction

from pydantic import BaseModel, Field
class Resume(BaseModel):
    name: str = Field(description="Full name of candidate")
    email: str = Field(description="Email address")
    skills: list[str] = Field(description="Technical skills and technologies")

from llama_cloud_services import LlamaExtract
# Initialize client
extractor = LlamaExtract(
    show_progress=True,
    check_interval=5,
    # Optional API key, else reads from env
    # api_key=os.environ.get("LLAMA_CLOUD_API_KEY"),
)

from llama_cloud import ExtractConfig, ExtractMode
# Configure extraction settings
extract_config = ExtractConfig(
    # Basic options
    extraction_mode=ExtractMode.MULTIMODAL,  # FAST, BALANCED, MULTIMODAL, PREMIUM
    extraction_target=ExtractTarget.PER_DOC,  # PER_DOC, PER_PAGE
    system_prompt="<Insert relevant context for extraction>",  # set system prompt - can leave blank
    # Advanced options
    high_resolution_mode=True,  # Enable for better OCR
    nvalidate_cache=False,  # Set to True to bypass cache
    # Extensions
    cite_sources=True,  # Enable citations
    use_reasoning=True,  # Enable reasoning (not available in FAST mode)
    confidence_scores=True,  # Enable confidence scores (MULTIMODAL/PREMIUM only)
)

result = extractor.extract(Resume, config, "resume.pdf")
# result.data has our model as a python dict
print(Resume.model_validate(result.data))

pip install llama_cloud_services

export LLAMA_CLOUD_API_KEY="..."