Skip to content

An autonomous agentic AI that scans RSS feeds, predicts fair market prices via an ensemble of LLMs and ML models, and notifies you when a deal is too good to miss. Powered by QLoRA, embeddings, and multi-agent orchestration.

License

Notifications You must be signed in to change notification settings

laumek/pricer_agentic_ai

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

28 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PRICER agentic AI

Autonomous Multi-Agent Deal Hunter Using LLMs, RAG, Vector Databases, and Hybrid ML

This project builds a fully autonomous AI system that scans the web for deals, estimates the true market price using an ensemble of models, and sends real-time push notifications when something is genuinely undervalued. It combines LLMs, classical ML, vector search, fine-tuning, cloud GPUs, Gradio-based UI, and agentic workflows into a cohesive end-to-end system.

đź§® Features

  • Autonomous Deal Scanning: Constantly monitors RSS feeds for new listings.
  • Fair Price Estimation: Ensemble of LLM and ML models to infer realistic market value.
  • Push Notifications: Alerts when significant undervaluations are detected.
  • Gradio Dashboard: Interactive dashboard for viewing deals, model estimates, and alerts.
  • Multi-Agent Reasoning: Modular design with orchestrated agent collaboration.

Multi-Agent Architecture

Agent Purpose
Scanner Agent Scrapes RSS feeds in real-time for new deals
Frontier Agent (RAG) Retrieves similar items (RAG) via embeddings + uses frontier LLM (GPT-4o-mini / DeepSeek) to estimate price
Specialist Agent (Fine-Tuned LLM) QLoRA fine-tuned model deployed on Modal predicts clean prices
Random Forest Agent Traditional ML model predicting price, trained on sentence-transformer embeddings.
Ensemble Agent Linear model combining all price predictions
Planning Agent Central orchestrator that manages agent workflows and decision logic (picks best deal, calculates discount, triggers alerts)
Messaging Agent Sends Pushover alerts for high-value opportunities.
Screenshot 2025-12-03 at 15 53 19 Random Fort

đź§© Data Pipeline

  1. Data Collection
  • Curated Pricing Dataset (Hugging Face):
Loaded Amazon product metadata from McAuley-Lab/Amazon-Reviews-2023 across 8 categories:
Automotive, Electronics, Office Products, Tools & Home Improvement, Cell Phones & Accessories, Toys & Games, Appliances, Musical Instruments.
These entries provide product descriptions + prices used to train all pricing models.
  • Live Deal Scraping:
RSS feeds (e.g., SlickDeals, HotUKDeals) supply real-time deal descriptions and prices for inference.
  1. Data Cleaning & Transformation
  • Normalised product descriptions (titles + bullet points → clean text)
  • Extracted & validated pricing information
  • Removed duplicates and outliers
  • Result: a consistent price–description dataset suitable for model training and evaluation.
  1. Embeddings & Storage
  • Embedded all product descriptions using
sentence-transformers/all-MiniLM-L6-v2
  • Stored vectors + metadata in ChromaDB
→ Enables similarity search for the frontier RAG model
→ Provides neighbourhood price statistics (min/max) used in the ensemble
  1. Model Training
  • Specialist LLM: fine-tuned with QLoRA on curated dataset for price prediction
  • Frontier RAG Model: retrieves nearest embeddings → frontier LLM estimates fair value
  • Random Forest Baseline: trained on embeddings to provide a stable numeric estimate
  • Combined through a calibrated linear ensemble, using real learned coefficients.
  1. Real-Time Deal Scoring For every incoming deal:
  2. Embed description
  3. Retrieve similar items from ChromaDB
  4. Generate three independent predictions
  5. Combine via ensemble to compute fair market value
  6. Compare against scraped price to compute discount
  7. If discount exceeds threshold → push notification

Ensemble Model (Meta-Model)

The system doesn't rely on one model.
It learns how to weight them optimally using a trained linear regression: FinalPrice =
0.73 * SpecialistLLM +1 .03 * FrontierLLM + 0.44 * RandomForest - 0.64 * MinModel - 0.60 * MaxModel + 26.47

Specialist Model (Fine-Tuned LLM)

  • QLoRA fine-tuned on ~400k product descriptions
  • Runs in 4-bit quantized mode
  • Deployed to Modal as a GPU-backed inference service
  • Stateless, fast cold starts, cached weights

Model Architecture:

IMG_0187

📡 Modal Deployment

The specialist model is exposed via:

Pricer = modal.Cls.lookup("pricer-service", "Pricer")
pricer.price.remote("product description")

đź§± Tech Stack

Layer Technology
Language Python
LLM & Fine-tuning QLoRA, Transformers, PEFT
Embeddings SentenceTransformers / OpenAI embeddings
Vector DB ChromaDB
Frontend / UI Gradio
Agents / Orchestration LangChain / custom planning logic
Notifications Pushover.net API
Deployment Modal (GPU service) / Localhost

🖥️ Gradio Monitoring Dashboard

The UI includes:

  • a table of all discovered deals
  • real-time agent logs
  • 3D embedding visualization (vector DB)
  • automatic refresh (300s) The Price is laght - Autonomous Agent Framework that hurts lor deals

đź”§ Getting Started to run locally

  1. Clone the repository

git clone https://github.com/laumek/pricer_agentic_ai.git

cd pricer_agentic_ai

  1. Install dependencies from pyproject.toml file pip install -e .

  2. Set up environment variables

Use .env.example to create a .env file with your API keys and configuration:

HF_TOKEN=...
PUSHOVER_USER=...
PUSHOVER_TOKEN=...
etc.
  1. Run the system python src/price_intel/agents/main.py
  2. Launch the Gradio UI python src/price_intel/interface/gradio_app.py

🙌 Acknowledgements

  • Hugging Face datasets for curated product data.
  • SentenceTransformers for embeddings.
  • Modal for deployment and LLM inference.
  • Gradio for rapid UI prototyping.
  • OpenAI / DeepSeek models for RAG and reasoning layers.
  • This project builds on code from Ed Donner (https://github.com/ed-donner/llm_engineering) under the MIT License. Significant modifications, enhancements, and additional agents have been implemented independently.

About

An autonomous agentic AI that scans RSS feeds, predicts fair market prices via an ensemble of LLMs and ML models, and notifies you when a deal is too good to miss. Powered by QLoRA, embeddings, and multi-agent orchestration.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published