Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/MuhammadSalmanAhmad/rag-pdf-highlighter/llms.txt

Use this file to discover all available pages before exploring further.

This guide walks you through deploying the RAG PDF Highlighter FastAPI application with Uvicorn and calling it over HTTP. Once running, any client that can make HTTP requests — curl, Python, JavaScript, or any other language — can submit a PDF URL and a list of text chunks and receive an annotated PDF in return.

​
Prerequisites

  • Python >= 3.10
  • pip available in your environment

​
Steps

1

Install the package

Install RAG PDF Highlighter from PyPI:
pip install rag-pdf-highlighter
2

Start the server

Launch the FastAPI application with Uvicorn, binding to all interfaces on port 8000:
uvicorn rag_pdf_highlighter.main:app --host 0.0.0.0 --port 8000
3

Verify the health check

Confirm the service is up by hitting the root endpoint:
curl http://localhost:8000/
A running service returns:
{"status": "ok the app is running"}
4

Send a highlight request

Submit a PDF URL and a list of text chunks to annotate. The request body requires a pdf_url string and a documents array where each item has a page_content string and a metadata object with a zero-indexed page number:
curl -X POST http://localhost:8000/highlight \
  -H "Content-Type: application/json" \
  -d '{
    "pdf_url": "https://example.com/report.pdf",
    "documents": [
      {
        "page_content": "Text to highlight in the PDF",
        "metadata": {"page": 0}
      }
    ]
  }' \
  --output highlighted.pdf

​
Response

When the request succeeds, the service streams back a binary PDF with Content-Type: application/pdf and the filename highlighted.pdf. Save it directly to disk with --output in curl, or read the response bytes in your HTTP client of choice.

​
Error handling

HTTP statusMeaning
400Bad PDF URL (download failed) or no documents were provided
422Invalid request payload — check that pdf_url is a string and documents is a non-empty array with the correct fields
500Unexpected server-side error during highlighting
All temporary files — both the downloaded PDF and the annotated output — are deleted automatically after each request via FastAPI background tasks. No files accumulate on the server between requests.
For the complete field-by-field breakdown of the request and response schemas, see the API reference.

Build docs developers (and LLMs) love

Get started for freeTalk to us