{"id":28577022,"url":"https://github.com/ridenefiras/kagglexgoogle","last_synced_at":"2026-05-16T01:32:24.310Z","repository":{"id":289001319,"uuid":"969792714","full_name":"RideneFiras/KagglexGoogle","owner":"RideneFiras","description":null,"archived":false,"fork":false,"pushed_at":"2025-04-21T00:17:47.000Z","size":180,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-11T00:08:53.402Z","etag":null,"topics":["embedding-models","genai","generative-ai","llm","rag"],"latest_commit_sha":null,"homepage":"https://www.kaggle.com/code/firasridene/5day-hopefully-final","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/RideneFiras.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-04-20T23:57:13.000Z","updated_at":"2025-04-21T15:45:00.000Z","dependencies_parsed_at":"2025-04-21T01:27:20.331Z","dependency_job_id":"cceed151-b2d2-4037-83aa-216835dbdb21","html_url":"https://github.com/RideneFiras/KagglexGoogle","commit_stats":null,"previous_names":["ridenefiras/kagglexgoogle"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/RideneFiras/KagglexGoogle","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RideneFiras%2FKagglexGoogle","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RideneFiras%2FKagglexGoogle/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RideneFiras%2FKagglexGoogle/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RideneFiras%2FKagglexGoogle/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RideneFiras","download_url":"https://codeload.github.com/RideneFiras/KagglexGoogle/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RideneFiras%2FKagglexGoogle/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274291325,"owners_count":25258157,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-09T02:00:10.223Z","response_time":80,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["embedding-models","genai","generative-ai","llm","rag"],"created_at":"2025-06-11T00:08:53.281Z","updated_at":"2026-05-16T01:32:19.289Z","avatar_url":"https://github.com/RideneFiras.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ✈️ Airline Assistant – GenAI Capstone Project (Kaggle x Google)\n\n![Demo Screenshot 1](assets/demo.png)  \n![Demo Screenshot 2](assets/demo1.png)  \n![Demo Screenshot 3](assets/demo2.png)\n\n---\n\n## 📌 About This Project\n\nThis is a submission for the **Google x Kaggle 5-Day Generative AI Event**.\n\nOur project demonstrates how to build an interactive airline assistant using **Generative AI techniques** including:\n- **RAG (Retrieval-Augmented Generation)** for FAQ responses\n- **Embeddings-based similarity** using `text-embedding-004`\n- **Gemini 2.0 Flash** for intent classification and smart field extraction\n- **Multi-turn interaction logic** with **running state**\n- A clean **Gradio chat interface**\n\n---\n\n## 🤖 What the Assistant Can Do\n\nThe assistant interacts with users just like a real airline support agent:\n\n- 🧠 **Understands your input** using AI-based classification\n- 📘 **Answers travel questions** (e.g., \"Can I bring a cat on the plane?\")\n- 🗃️ **Differentiates between FAQ and personal information**\n- 📝 **Collects key fields**: name, flight number, issue, and email\n- 🧠 **Stores information across turns** using a persistent user state\n\n---\n\n## ⚙️ Setup Instructions (Important!)\n\nTo run this notebook, you must add your **Google Generative AI API key**:\n\n1. Go to **\"Add-ons\" \u003e \"Secrets\"** (in Kaggle)\n2. Add a new secret named:\n\n```\nGOOGLE_API_KEY\n```\n\n3. Paste your Gemini API key as the value (from https://makersuite.google.com/app/apikey)\n\n---\n\n## 🧠 How It Works\n\n| Component | Description |\n|----------|-------------|\n| `text-embedding-004` | Generates vector embeddings for FAQ retrieval |\n| `cosine similarity` | Finds the best-matching FAQ question |\n| `Gemini Flash` | Classifies whether the user input is a question or a personal detail |\n| `Field extraction` | AI-based slot-filling logic (e.g., extracting names from messy input) |\n| `State tracking` | Stores each user field (name, flight, issue, email) during chat |\n| `Gradio` | Provides an interactive chatbot interface for users |\n\n---\n\n## 💡 Why It Matters\n\nThis project simulates how a real-world **AI-powered airline assistant** might behave — blending FAQ search with intelligent form-filling, all within a lightweight notebook.\n\nIt showcases how we can combine **LLMs, embeddings, and interface tools** to build useful, responsive GenAI apps.\n\n---\n\n## 📁 Files\n\n- `notebook.ipynb` – full interactive assistant\n- `assets` – demo pictures\n\n\n---\n\n## 🙌 Thanks\n\nHuge thanks to **Kaggle**, **Google**, and the GenAI team for organizing the event!\n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fridenefiras%2Fkagglexgoogle","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fridenefiras%2Fkagglexgoogle","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fridenefiras%2Fkagglexgoogle/lists"}