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.

Docker deployment is the simplest path to a production-ready instance of RAG PDF Highlighter. The image bundles all system and Python dependencies — including PyMuPDF and its native libraries — so there is nothing to install on the host beyond Docker itself.

​
Dockerfile

The project ships with the following Dockerfile: 
FROM python:3.12-slim

# Set working directory
WORKDIR /app

# Install system dependencies required by PyMuPDF
RUN apt-get update && \
    apt-get upgrade -y && \
    apt-get install -y --no-install-recommends \
    libmupdf-dev \
    && rm -rf /var/lib/apt/lists/*

# Copy application code and install from pyproject.toml
COPY . .
RUN pip install --no-cache-dir .

# Expose the port Uvicorn will listen on
EXPOSE 8000

# Run with Uvicorn
CMD ["uvicorn", "rag_pdf_highlighter.main:app", "--host", "0.0.0.0", "--port", "8000"]

​
Steps

1

Clone the repository

git clone https://github.com/MuhammadSalmanAhmad/rag-pdf-highlighter.git
2

Build the image

From the repository root, build and tag the image:
docker build -t rag-pdf-highlighter .
The build installs libmupdf-dev and all Python dependencies. This takes a minute on the first run; subsequent builds use the layer cache.
3

Run the container

Start the container and map port 8000 on the host to port 8000 inside the container:
docker run -p 8000:8000 rag-pdf-highlighter
4

Test the health check

Confirm the service is responding:
curl http://localhost:8000/
Expected response:
{"status": "ok the app is running"}
5

Send a highlight request

Submit a PDF URL and text chunks to annotate:
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
The response is a binary PDF saved to highlighted.pdf in the current directory.

​
Port mapping

The -p 8000:8000 flag maps port 8000 on your host machine to port 8000 inside the container (the port Uvicorn listens on, as declared by EXPOSE 8000 in the Dockerfile). To serve on a different host port, change the left side of the mapping — for example, -p 9090:8000 makes the API available at http://localhost:9090.
To run the container in the background so it does not block your terminal, add the -d (detached) flag:
docker run -d -p 8000:8000 rag-pdf-highlighter
Use docker logs <container-id> to inspect Uvicorn’s output, and docker stop <container-id> to shut it down.
The container installs libmupdf-dev at image build time. No additional system dependencies are needed on the host at runtime — all native libraries are self-contained inside the image.

Build docs developers (and LLMs) love

Get started for freeTalk to us