Added materials for Docling vs LlamaParse tutorial

Author: nunombispo

pdf-table-extraction-docling-vs-llamaparse/docling_extraction.py

@@ -0,0 +1,22 @@
+"""Parse a PDF with Docling and print Markdown output."""
+
+from pathlib import Path
+
+from docling.document_converter import DocumentConverter
+
+PDF_PATH = Path("sample_report.pdf")
+
+
+def main() -> None:
+    converter = DocumentConverter()
+    result = converter.convert(PDF_PATH)
+
+    markdown = result.document.export_to_markdown()
+    print(markdown[:3000])
+    print("\n---\n")
+    print(f"Pages parsed: {len(result.document.pages)}")
+    print(f"Tables found: {len(result.document.tables)}")
+
+
+if __name__ == "__main__":
+    main()

pdf-table-extraction-docling-vs-llamaparse/docling_formats.py

@@ -0,0 +1,34 @@
+"""Export Docling parse results to Markdown, JSON, HTML, and pandas DataFrames."""
+
+import json
+from pathlib import Path
+
+from docling.document_converter import DocumentConverter
+
+PDF_PATH = Path("sample_report.pdf")
+
+
+def main() -> None:
+    converter = DocumentConverter()
+    document = converter.convert(PDF_PATH).document
+
+    markdown = document.export_to_markdown()
+    Path("output_docling.md").write_text(markdown, encoding="utf-8")
+
+    payload = document.export_to_dict()
+    Path("output_docling.json").write_text(
+        json.dumps(payload, indent=2),
+        encoding="utf-8",
+    )
+
+    html = document.export_to_html()
+    Path("output_docling.html").write_text(html, encoding="utf-8")
+
+    for index, table in enumerate(document.tables):
+        frame = table.export_to_dataframe(doc=document)
+        print(f"Table {index} shape: {frame.shape}")
+        print(frame.head(), end="\n\n")
+
+
+if __name__ == "__main__":
+    main()

pdf-table-extraction-docling-vs-llamaparse/llamaparse_extraction.py

@@ -0,0 +1,31 @@
+"""Parse a PDF with LlamaParse (llama-cloud SDK) and print Markdown output."""
+
+import os
+from pathlib import Path
+
+from llama_cloud import LlamaCloud
+
+PDF_PATH = Path("sample_report.pdf")
+
+
+def main() -> None:
+    client = LlamaCloud(api_key=os.environ["LLAMA_CLOUD_API_KEY"])
+
+    uploaded = client.files.create(file=PDF_PATH, purpose="parse")
+    result = client.parsing.parse(
+        file_id=uploaded.id,
+        tier="agentic",
+        version="latest",
+        expand=["markdown"],
+    )
+
+    pages = ""
+    for page in result.markdown.pages:
+        pages += page.markdown
+        pages += "\n---\n"
+
+    print(pages[:3000])
+    print(f"Pages parsed: {len(result.markdown.pages)}")
+
+if __name__ == "__main__":
+    main()

pdf-table-extraction-docling-vs-llamaparse/llamaparse_formats.py

@@ -0,0 +1,63 @@
+"""Export LlamaParse results to Markdown, Text, and schema-driven JSON."""
+
+import json
+import os
+from pathlib import Path
+
+from llama_cloud import LlamaCloud
+from pydantic import BaseModel, Field
+
+PDF_PATH = Path("sample_report.pdf")
+
+
+class RevenueRow(BaseModel):
+    quarter: str = Field(description="Fiscal quarter label, e.g. Q1 2024")
+    revenue_millions: float = Field(description="Revenue in millions of USD")
+    growth_percent: float | None = Field(
+        default=None,
+        description="Year-over-year growth percentage if stated",
+    )
+
+
+class RevenueTable(BaseModel):
+    rows: list[RevenueRow] = Field(description="One row per quarter in the table")
+
+
+def main() -> None:
+    client = LlamaCloud(api_key=os.environ["LLAMA_CLOUD_API_KEY"])
+
+    uploaded = client.files.create(file=PDF_PATH, purpose="parse")
+
+    parsed = client.parsing.parse(
+        file_id=uploaded.id,
+        tier="agentic",
+        version="latest",
+        expand=["markdown", "text"],
+    )
+
+    markdown_pages = "\n\n".join(page.markdown for page in parsed.markdown.pages)
+    Path("output_llamaparse.md").write_text(markdown_pages, encoding="utf-8")
+
+    if parsed.text and parsed.text.pages:
+        text_pages = "\n".join(page.text for page in parsed.text.pages)
+        Path("output_llamaparse.text").write_text(text_pages, encoding="utf-8")
+
+    extract_file = client.files.create(file=PDF_PATH, purpose="extract")
+    job = client.extract.run(
+        file_input=extract_file.id,
+        configuration={
+            "data_schema": RevenueTable.model_json_schema(),
+            "extraction_target": "per_doc",
+            "tier": "agentic",
+        },
+    )
+
+    Path("output_llamaparse.json").write_text(
+        json.dumps(job.extract_result, indent=2),
+        encoding="utf-8",
+    )
+    print(json.dumps(job.extract_result, indent=2))
+
+
+if __name__ == "__main__":
+    main()

pdf-table-extraction-docling-vs-llamaparse/requirements.txt

@@ -0,0 +1,4 @@
+docling==2.102.2
+llama-cloud>=2.9.0
+pandas>=2.0.0
+pydantic>=2.0.0