Skip to content

A RAG based genAI application that can retrieve relevant products from the database that match user's requirements and that can do cross reference search to retrieve most comparable products to a given product datasheet

License

Notifications You must be signed in to change notification settings

dauhoangganh/RAG-based-product-search

Repository files navigation

Analog Assist

This is a RAG based genAI application that can retrieve relevant products from the databse that meet user"s requirements. This repository contains a GenAI-powered application built using LangChain as the main framework and Streamlit for GUI development. The LLM model used is AZURE openAI model, but user can freely use their preferred model. Vector database used int his project is PineCone.

Features

  • Product Search Tool: Enter the necessary information, the tool recommends suitable ADI products that meet the customer's needs.
  • Cross Reference Search: Upload a competitor's datasheet, the tool suggests ADI products with the same or similar specifications.

Installation and run

To run the app locally, follow these steps:

  1. Clone this repository:

    git clone https://github.com/Anh-Do_adi/ChocoMango
    cd ChocoMango
  2. Install dependencies:

    pip install -r requirements.txt
  3. Input your AZURE openAI key, AZURE embedding model API key, pinecone API key, pinecone index to .env file

  4. Run the app:

    streamlit run .\homepage.py

Usage

Feature 1: Product Search Tool

  • Enter your query in the form. Only the Application/Purpose field is required, other fields are optional. But the LLM's accuracy can be imrpoved if these fields' information is provided.
  • Analog Assist processes your input and generates a PST.

Input Fields

Field Description
Application/Purpose Describe your intended use case
Category Select a product category from the dropdown list
Min Voltage Specify the minimum operating voltage
Max Voltage Specify the maximum operating voltage
Supply Current Max Limit Define the maximum allowable supply current
Min Temperature Range Set the minimum operating temperature
Max Temperature Range Set the maximum operating temperature
Package Define the preferred package type
Other Requirements Additional constraints or preferences

Feature 2: Cross Reference Search

  • THe user uploads a competitor's datasheet.
  • Analog Assist analyzes the datasheet and provides top 2 most comparables products.
  • You can also download the corresponding ADI datasheet simultaneously.

Backend code flow Diagram

The following diagram illustrates the workflow of the application:

Product Search Tool

Cross Reference Search

Requirements

  • Python 3.11.x
  • OpenAI API Key (LLM: gpt-4o-mini, Embedding: text-embedding-3-large)
  • Pinecone Vector DB

About

A RAG based genAI application that can retrieve relevant products from the database that match user's requirements and that can do cross reference search to retrieve most comparable products to a given product datasheet

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages