BACK TO ALL PROJECTS

Car Recommendation Chat Bot

AI-Powered conversational advisor leveraging GPT-3.5 and LangChain.

ROLEAI Developer & Full-Stack Engineer
TIMELINE2024
§01

Overview

An AI chatbot designed to help buyers find their ideal vehicle by processing user preferences, budget, and performance requirements through natural language.

§02

The Problem

Car buyers face information overload when comparing vehicle specs, fuel efficiency, pricing, and features across multiple manufacturers.

§03

Research

Researched prompt engineering strategies, dataset structured search, and LangChain memory modules to maintain context during multi-turn conversations.

§04

The Solution

Engineered an interactive Django web app integrated with OpenAI GPT-3.5 Turbo LLM and LangChain. Queries are matched against a structured automobile dataset for accurate recommendations.

§05

Architecture

Django web server connected to LangChain chain pipelines, OpenAI API gateway, and structured dataset querying.

TECHNOLOGY STACK
Python
Django
GPT-3.5 Turbo LLM
LangChain
HTML/CSS
§06

Challenges

  • 01Preventing LLM hallucinations by grounding responses in structured automobile data
  • 02Managing API rate limits and optimizing prompt latency for interactive chat
§07

Results

Delivered tailored car recommendations with high user satisfaction during testing, significantly reducing research time for prospective buyers.

0%
Recommendation Accuracy
0s
LLM Response Time
0%
User Preference Match
§08

Lessons Learned

Retrieval and grounding with LangChain transforms raw LLMs into accurate domain advisors

UI feedback during stream generation improves perceived responsiveness