Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

FERRADJI-TAREK/chatbot-djezzy-rag-finetuning

Domaine:

natural language processing

Type de record:

project
Créateur:
FER
Hôte:
This project involves designing an intelligent chatbot to improve customer support at Djezzy, a major telecom provider in Algeria. It explores key aspects of Generative AI as part of a practical internship. # **INTELLIGENT CUSTOMER SUPPORT CHATBOT FOR DJEZZY** ## **Project Overview** This project focuses on the design and implementation of an **intelligent chatbot** aimed at enhancing customer support at **Djezzy**, one of Algeria's leading telecommunications providers. Conducted as part of a practical internship within the company, it explores key aspects of **Generative AI**, including **fine-tuning large language models (LLMs)**, optimizing responses, and integrating a **Retrieval-Augmented Generation (RAG) system**. ## **Project Stages** ### **1. Data Collection and Extraction** - Utilized **web scraping** techniques to extract relevant data from various online sources. - Preprocessed raw data to ensure quality and relevance before training. ### **2. Data Processing and Preparation** - Cleaned, annotated, and structured data to optimize chatbot performance. ### **3. Model Training and Optimization** - **Fine-tuned** a **Large Language Model (LLM)** on a **Djezzy-specific corpus**, ensuring accurate and context-aware responses. - Integrated a **RAG system**, combining **retrieval-based search and text generation**, to provide precise and contextualized answers based on company documents. ### **4. Implementation and Deployment** - Developed a **user-friendly interface** for chatbot interactions. ### **5. Performance Evaluation and Optimization** - Measured chatbot efficiency using **performance metrics** such as **precision, recall, and F1-score**. - Adjusted and improved responses based on user feedback and test results to enhance customer experience. ## **Conclusion** This project demonstrates the impact of **Generative AI** in automating customer service. By combining **fine-tuned LLMs and a RAG system**, the chatbot provides **highly relevant** and **optimized** responses, improving customer interaction. By **reducing workload on support teams** and offering **instant assistance**, the chatbot significantly enhances the user experience. ## **Technologi …

Visit

github.com

Similaires

djpapzin/malawi-rag-sql-chatbotahmedkhairysaleh-boop/etisalat-rag-chatbotzakariae-boui/onssa-rag-chatbotCliff-Ezra/RAG-chatbot-v2GilbertoBotas/Mozambican-Road-Code-Chatbot-RAGojoluwasegun/Nigeria-Tax-Reform-RAG-Chatbot-HuggingFace

djpapzin/malawi-rag-sql-chatbot

# Dziwani - Infrastructure Transparency Chatbot A specialized chatbot for querying and exploring Ma

ahmedkhairysaleh-boop/etisalat-rag-chatbot

Bilingual RAG chatbot over e& Egypt package documentation, built with LangGraph and ChromaDB # e& E

zakariae-boui/onssa-rag-chatbot

Customer-assistance RAG chatbot for the ONSSA website (Morocco) — Streamlit, Ollama (Mistral 7B), FA

Cliff-Ezra/RAG-chatbot-v2

This repository is for the implementation of a RAG based chatbot for Kenya Law. It is the second ver

GilbertoBotas/Mozambican-Road-Code-Chatbot-RAG

RAG-powered assistant for the Mozambique Road Code. Ask questions about traffic rules, penalties, an

ojoluwasegun/Nigeria-Tax-Reform-RAG-Chatbot-HuggingFace

This project is an intelligent Question-Answering (QA) chatbot built to help users explore and under