skills.rest
mattwoodco
mattwoodcoCOMMUNITY
Explore all skills by this author →
Website𝕏@mattwoodcoGitHub

ai-rag-ingest

Ingest large PDFs to S3 with parallel unpdf parsing and PostgreSQL status tracking.

3|Updated Feb 14, 2026
Search Tags:#pdf#rag#ingestion#s3#parsing#postgres
One-click install
npx skills add https://github.com/mattwoodco/skills --skill ai-rag-ingest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-rag-ingest
Source: https://github.com/mattwoodco/skills/tree/main/skills/ai-rag-ingest
Command: npx skills add https://github.com/mattwoodco/skills --skill ai-rag-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires unpdf, storage, db, auth, docker, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the process of ingesting large PDF documents, making their content searchable and manageable within your application.

Core Features & Use Cases

  • Large PDF Upload: Handles PDFs up to 2GB, storing them in S3-compatible storage.
  • Parallel Parsing: Efficiently parses and extracts text from PDFs page by page using unpdf.
  • Status Tracking: Monitors the ingestion and processing status via a PostgreSQL database.
  • Use Case: Set up a system to allow users to upload research papers or large reports for AI-powered analysis.

Quick Start

Use the ai-rag-ingest skill to set up PDF upload functionality for your application.

Frequently Asked Questions about ai-rag-ingest

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

FAQPage Schema
How do I ingest large PDF files up to 2GB into S3 and Postgres?▼

This pipeline ingests large PDF files up to 2GB by uploading them to S3-compatible storage, parsing text page by page using unpdf, and tracking processing status in a PostgreSQL database.

Can I parse PDFs in parallel with unpdf inside a Next.js App Router application?▼

You can parse PDFs in parallel with unpdf inside a Next.js App Router application, extracting text page by page efficiently while tracking ingestion status via a PostgreSQL database.

What is the best way to track PDF ingestion status using Drizzle ORM and Postgres?▼

Tracking PDF ingestion status using Drizzle ORM with PostgreSQL monitors the upload, parallel parsing, and processing stages of large documents stored in S3-compatible storage.

Does this PDF ingestion pipeline require Docker to set up S3 storage and Postgres?▼

Docker is required to set up the environment for S3-compatible storage and PostgreSQL, streamlining the deployment of the PDF ingestion pipeline.

Why use unpdf for parsing large PDF documents for AI analysis?▼

Using unpdf for parsing large PDF documents efficiently extracts text page by page in parallel, making content searchable and manageable for AI-powered analysis.

Related Skills

Explore More Software Engineering Skills→
JaylaelikeJaylaelike

supabase-nextjs

Configure Next.js App Router projects with Supabase authentication and Drizzle ORM.

Community
Intermediate
Greenmamba29Greenmamba29

vector-embedder

Generate and store vector embeddings for semantic search pipelines.

Community
Intermediate
applewaveapplewave
1

bkend-storage

Manage backend file storage with presigned uploads, metadata, and access control.

Community
Advanced
photon-hqphoton-hq
14

imessage

Send and receive iMessages programmatically via WebSockets and AppleScript.

Official
Advanced