document-processing-generator

Name: document-processing-generator
Availability: InStock
Author: web3br1

Generate and modify document processing pipelines for RAG with Qdrant.

Updated Jun 18, 2026

Search Tags:#document processing #OpenAI #RAG #Qdrant #pipeline generation

Ready to run

npx skills add https://github.com/web3br1/luminaristest --skill document-processing-generator

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: document-processing-generator
Source: https://github.com/web3br1/luminaristest/tree/main/.claude/skills/document-processing-generator
Command: npx skills add https://github.com/web3br1/luminaristest --skill document-processing-generator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, qdrant, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the generation or modification of document processing pipelines for RAG (Retrieval-Augmented Generation), simplifying the extraction, embedding, and indexing of documents.

Core Features & Use Cases

Document Extraction: Extract text from various document formats (PDF, DOCX, TXT, MD).
Chunking and Embedding: Process extracted text into chunks and generate embeddings using OpenAI.
Upsert in Qdrant: Store embeddings in Qdrant for efficient retrieval.
Status Tracking: Track document processing status (PENDING, PROCESSING, COMPLETED/ERROR).
Use Case: Ideal for supporting new file types, modifying chunking strategies, or debugging document processing issues.

Quick Start

Generate a new document processing pipeline for a new file type using the document-processing-generator skill with the argument 'new-type'.

Frequently Asked Questions about document-processing-generator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate a document processing pipeline for RAG?▼

You can generate a document processing pipeline for RAG by specifying the target file type, which automates text extraction, chunking, embedding with OpenAI, and indexing in Qdrant for efficient retrieval.

What document formats can I extract text from for RAG indexing?▼

You can extract text from PDF, DOCX, TXT, and MD document formats. The pipeline processes these extracted formats into chunks and generates embeddings before storing them in Qdrant.

Do I need a Qdrant instance and OpenAI API key to build RAG pipelines?▼

Yes, a Qdrant instance and OpenAI API key are required. The pipeline relies on OpenAI to generate text embeddings and Qdrant to store and index these embeddings for retrieval.

How can I modify chunking strategies for an existing RAG document processing workflow?▼

You can modify chunking strategies to adjust how extracted text is segmented before embedding. This is ideal for debugging document processing issues or optimizing retrieval performance for specific file types.

How does RAG document processing track the status of extracted files?▼

RAG document processing tracks the status of files throughout the workflow using distinct stages: PENDING, PROCESSING, and either COMPLETED or ERROR, ensuring visibility into extraction and indexing operations.