# RAG PDF Highlighter

## Docs

- [RAG PDF Highlighter — API Error Codes and Troubleshooting](https://docs.salmanahmad.online/api/errors.md): Reference for all HTTP error codes returned by RAG PDF Highlighter, including causes, error detail messages, and recommended fixes.
- [GET / Health Check — Verify the Service Is Running](https://docs.salmanahmad.online/api/health-check.md): The GET / endpoint returns a fixed JSON status payload confirming your RAG PDF Highlighter instance is live and ready to accept highlight requests.
- [POST /highlight — Annotate a PDF with RAG Text Chunks](https://docs.salmanahmad.online/api/highlight.md): POST /highlight accepts a PDF URL and document chunks, locates each chunk in the PDF, and returns an annotated binary PDF with highlights applied.
- [RAG PDF Highlighter API — Overview and Getting Started](https://docs.salmanahmad.online/api/overview.md): The RAG PDF Highlighter REST API accepts a PDF URL and document chunks, then returns an annotated PDF. Base URL, auth, and request format explained.
- [RAG PDF Highlighter — Request and Response Schemas](https://docs.salmanahmad.online/api/request-response.md): Full schema reference for the HighlightRequest and DocumentPayload request bodies, and all success and error response formats returned by the API.
- [Document Payload Format and Page Metadata in PDF Highlighter](https://docs.salmanahmad.online/concepts/document-format.md): Learn the document payload structure accepted by RAG PDF Highlighter, including the page_content field and how to set metadata page numbers.
- [How RAG PDF Highlighter Processes and Annotates Your PDFs](https://docs.salmanahmad.online/concepts/how-it-works.md): Learn how RAG PDF Highlighter fetches PDFs, locates text chunks, and returns a highlighted document in a single stateless request.
- [PDF Text Matching Strategies in RAG PDF Highlighter](https://docs.salmanahmad.online/concepts/text-matching.md): RAG PDF Highlighter applies three fallback strategies — exact, sentence-level, and collapsed-whitespace — to locate text in any PDF layout.
- [Run RAG PDF Highlighter with Docker — Quick Start](https://docs.salmanahmad.online/guides/docker-deployment.md): Deploy RAG PDF Highlighter as a Docker container in minutes. Learn how to build the image, configure ports, and verify your deployment.
- [Handle RAG PDF Highlighter Errors in Your Application](https://docs.salmanahmad.online/guides/error-handling.md): Understand error responses from RAG PDF Highlighter, including download failures, validation errors, and how to debug chunk-matching issues.
- [Use RAG PDF Highlighter as a Standalone Python Library](https://docs.salmanahmad.online/guides/library-usage.md): Import RAG PDF Highlighter directly into your Python application to highlight PDFs programmatically without running a separate API server.
- [Integrate PDF Highlighting into Your LangChain RAG Pipeline](https://docs.salmanahmad.online/guides/rag-integration.md): Add visual PDF highlighting to your LangChain RAG pipeline. Retrieve chunks and highlight source passages in the original PDF for transparent citations.
- [RAG PDF Highlighter Installation: pip and Docker Setup Guide](https://docs.salmanahmad.online/installation.md): Install RAG PDF Highlighter as a Python package via pip or as a self-contained Docker container. Python 3.10 or later is required to run the service.
- [RAG PDF Highlighter: How It Works and What It Does](https://docs.salmanahmad.online/introduction.md): RAG PDF Highlighter is a stateless FastAPI service and Python library that finds text chunks in PDFs and returns highlighted documents for RAG pipelines.
- [Quickstart Guide: Highlight PDFs with RAG PDF Highlighter](https://docs.salmanahmad.online/quickstart.md): Learn how to install RAG PDF Highlighter, start the local server, and send your first request to get back a highlighted PDF in under five minutes.