extract-structured-data-from-unstructured-files-pdf-pptx-docx

run-llama's avatarfrom run-llama

Invoke this skill BEFORE implementing any structured data extraction from documents to learn the correct llama_cloud_services API usage. Required reading before writing extraction code. Requires llama_cloud_services package and LLAMA_CLOUD_API_KEY as an environment variable.

⭐173stars🔀26forks📁View on GitHub🕐Updated Nov 3, 2025
[Document Data Extraction]

When & Why to Use This Skill

This Claude skill enables automated structured data extraction from unstructured files like PDFs, PPTX, and DOCX using the llama_cloud_services API. It provides a comprehensive framework for defining Pydantic schemas and implementing high-accuracy extraction workflows that support multimodal processing, high-resolution OCR, and AI-driven reasoning to transform complex documents into machine-readable data.

Use Cases

  • Automated Resume Parsing: Extracting specific candidate details such as names, contact information, and technical skills from various CV formats into a structured database.
  • Financial Document Digitization: Converting unstructured invoices, receipts, and financial statements into structured JSON for automated accounting and auditing.
  • Legal Contract Analysis: Identifying and pulling key clauses, dates, and parties from legal documents to streamline contract lifecycle management.
  • Research Data Harvesting: Systematically extracting data points, tables, and citations from academic papers and technical manuals for knowledge base population.
nameExtract structured data from unstructured files (PDF, PPTX, DOCX...)
descriptionInvoke this skill BEFORE implementing any structured data extraction from documents to learn the correct llama_cloud_services API usage. Required reading before writing extraction code. Requires llama_cloud_services package and LLAMA_CLOUD_API_KEY as an environment variable.

Structured Data Extraction

Quick start

  • Define a schema for the for the data you would like to extract:
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")

NOTE: Use basic types when possible. Avoid nested dictionaries. Lists are ok.

  • Create a LlamaExtract instance:
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"),
)
  • Define the extraction configuration:
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)
)
  • Extract the data from the document:
result = extractor.extract(Resume, config, "resume.pdf")

# result.data has our model as a python dict
print(Resume.model_validate(result.data))

For more detailed code implementations, see REFERENCE.md.

Requirements

The llama_cloud_services package must be installed in your environment (with it come the pydantic and llama_cloud packages):

pip install llama_cloud_services

And the LLAMA_CLOUD_API_KEY must be available as an environment variable:

export LLAMA_CLOUD_API_KEY="..."