Skip to content

AI & LLM · Machine Learning

AIPAS

AI procurement automation & RAG system

Role
Full Stack & AI Engineer
Year
2023 — 2024
Status
Live
Stack
13 technologies
Visit live siteWatch the demo Source code
aipas.duckdns.org
AIPAS — AI procurement automation & RAG system

  • 92%

    Decision accuracy

  • 1,000+

    Documents / hour

  • 35%

    Cost reduction

Screens

02 · click to zoom

Overview

AIPAS — live as ProcureHub — connects buyers and vendors on one platform and automates the slow parts of procurement: reading documents, extracting requirements, comparing quotations and choosing the right vendor.

On top sits a RAG comparison system that benchmarks vector stores and retrieval strategies, so every answer the assistant gives can be measured.

What I built

  1. 01OCR + NLP pipeline for automated document processing and intelligent vendor selection.
  2. 02Separate buyer, vendor and admin portals — buyers raise requests and track open requests, quotations received and completed deals.
  3. 03AI-driven quotation analysis and an in-app AI chat assistant for procurement questions.
  4. 0492% accuracy on automated procurement decisions through ML algorithms.
  5. 05RAG comparison system deployed on Hugging Face Spaces with a Gradio UI and an MCP server.
  6. 06Hierarchical metadata classification with a 3-level taxonomy (domain / section / topic).
  7. 07Vector search across Chroma, FAISS and Pinecone with metadata filtering.
  8. 08Evaluation framework with Hit@k, MRR, semantic similarity and latency metrics; presets for hospital, bank and fluid-simulation domains.