TIRA Beauty AI Assistant

An intelligent beauty advisor built by Julep AI that helps users discover beauty products, understand ingredients, and get personalized beauty advice.

Overview

The TIRA Beauty AI Assistant is a proof-of-concept chatbot that demonstrates:

• Product recommendations from TIRA's catalog
• Ingredient explanations and beauty advice
• Personalized skincare/beauty routines
• Real-time product availability checks

Key Features

• Smart Search: Uses hybrid search combining vector and text-based approaches.
• RAG Pipeline: Leverages Retrieval-Augmented Generation to provide accurate, factual responses.
• Product Knowledge: Current deployed agent contains ~1K products.
• Beauty Expertise: Can explain ingredients, suggest routines, and compare products.
• Real-time Data: Integrates with TIRA's systems to check stock and availability.

Technical Implementation

• Built using Julep AI
• Uses Claude 3.7 Sonnet as the base model for the chatbot.
• Used Claude 3.5 Haiku / gpt-4o mini for contextualization
• Used openai text-embeddings-3-large for embedding
• Implements hybrid RAG search (vector search + BM25 + trigram search) with MMR for better result diversity.
• Automated product indexing and FAQ generation.

Try It Out

🔗 Chat with TIRA Beauty Assistant

Development

To run this project locally:

1. Clone the repository
2. Run the notebook to populate the document store.
3. Chat with the session that is created in the notebook.

Setup

1. Clone the repository

   git clone https://github.com/julep-ai/reliance-pocs.git

2. Install dependencies

   pip install -r requirements.txt

3. Create and configure a .env file

   cp .env.example .env

4. Run the notebook to populate the document store.

5. Chat with the session that is created in the notebook.

   Run the cells after Create a Julep Session

Architecture

Benchmark

1. Go to the benchmark directory

   cd benchmark

2. Create and configure the .env file (if not already done)

   cp .env.example .env

3. Run the benchmark script

   python benchmark/test_rag.py --agent_uuid=your_agent_uuid

4. Analyze the results

   python benchmark/analyze_result.py

Results

The benchmark results are saved in the following locations:

1. Raw Results:

   • CSV files in the current working directory (e.g., benchmark_results_{agent_uuid}.csv)

2. Visualizations (automatically generated during analysis):

   • benchmark_success_rates.png - Bar plot of success rates
   • benchmark_success_comparison.png - Comparison between exact match and effective success rates