The complete RAG platform for AI application developers
What is IngestIQ?#
IngestIQ is a comprehensive Retrieval-Augmented Generation (RAG) platform that enables AI application developers to easily integrate enterprise data sources without building RAG infrastructure from scratch.
Key Features#
Process PDFs, CSV, Excel, and video content with intelligent parsing powered by Google Gemini AI.
AI-powered document chunking that understands context and meaning, not just character counts.
High-performance semantic search using OpenAI embeddings and PostgreSQL with pgvector.
Native Model Context Protocol (MCP) server for seamless AI tool integration.
Automated data ingestion with cron-based scheduling via BullMQ.
Organizations with role-based access control for enterprise deployments.
Data Connectors#
IngestIQ supports multiple data sources out of the box:
| Connector | Description | Status |
|---|---|---|
| File Upload | PDF, CSV, Excel direct uploads | Available |
| Web Scraping | Crawl4AI integration for web content | Available |
| Google Drive | OAuth2-based document sync | Available |
| Video/YouTube | FFmpeg + Whisper transcription | Available |
Tech Stack#
TypeScript with Express.js
With pgvector extension
Event-driven messaging
Job scheduling
Object storage
AI processing