{"id":50338261,"url":"https://github.com/busrarafa/knowledge-augmented-academic-assistant","last_synced_at":"2026-05-29T15:00:50.784Z","repository":{"id":353718403,"uuid":"1202710842","full_name":"BusraRafa/Knowledge-Augmented-Academic-Assistant","owner":"BusraRafa","description":"A smart academic assistant powered by AI that helps students discover universities, get personalized guidance, and access trusted educational insights through an intelligent knowledge system.","archived":false,"fork":false,"pushed_at":"2026-05-10T04:22:28.000Z","size":680,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-10T06:43:12.737Z","etag":null,"topics":["aiassistant","deeplearning","deeplearning-ai","llm","nlp","openai","python","rag","vectordatabase"],"latest_commit_sha":null,"homepage":"https://clasia.io/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BusraRafa.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-06T10:11:31.000Z","updated_at":"2026-05-10T05:39:10.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/BusraRafa/Knowledge-Augmented-Academic-Assistant","commit_stats":null,"previous_names":["busrarafa/knowledge-augmented-academic-assistant"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/BusraRafa/Knowledge-Augmented-Academic-Assistant","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BusraRafa%2FKnowledge-Augmented-Academic-Assistant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BusraRafa%2FKnowledge-Augmented-Academic-Assistant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BusraRafa%2FKnowledge-Augmented-Academic-Assistant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BusraRafa%2FKnowledge-Augmented-Academic-Assistant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BusraRafa","download_url":"https://codeload.github.com/BusraRafa/Knowledge-Augmented-Academic-Assistant/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BusraRafa%2FKnowledge-Augmented-Academic-Assistant/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33657690,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-29T02:00:06.066Z","response_time":107,"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":["aiassistant","deeplearning","deeplearning-ai","llm","nlp","openai","python","rag","vectordatabase"],"created_at":"2026-05-29T15:00:49.710Z","updated_at":"2026-05-29T15:00:50.775Z","avatar_url":"https://github.com/BusraRafa.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🎓 Knowledge-Augmented Academic Assistant (AI Module)\n\nThis repository contains the **AI core** of a Knowledge-Augmented Academic Assistant designed to help students explore universities, get guidance, and receive accurate academic information.\n\nThe system is built using a **Retrieval-Augmented Generation (RAG)** approach, combining:\n- 📊 Structured university data\n- 🤖 Large Language Models (OpenAI)\n- 🎙️ Voice input + transcription pipeline\n\n---\n\n🌐 Live Website: Visit [clasia.net](https://clasia.io/)\n\n---\n\n## 🚀 Key Features\n\n- 🤖 **AI Chatbot for Students**\n  - Provides guidance on universities, programs, and decisions\n  - Answers contextual and follow-up questions\n\n- 📚 **RAG-Based Knowledge System**\n  - Retrieves relevant university data\n  - Augments LLM responses with real information\n  - Improves factual accuracy and reduces hallucinations\n\n- 🎙️ **Voice Input Support**\n  - Accepts audio queries\n  - Converts speech → text → AI response\n\n- 🧠 **Context-Aware Conversations**\n  - Maintains chat history\n  - Generates more relevant responses over time\n\n---\n\n## 🧠 RAG Architecture (Core Idea)\n\nThis project follows a **Retrieval-Augmented Generation pipeline**, which works in two main stages:\n\n### 1. Retrieval Stage\n- User query is processed\n- Relevant university data is selected from the internal dataset\n- Context is prepared dynamically\n\n### 2. Generation Stage\n- Retrieved context + user query is sent to the LLM\n- OpenAI model generates a grounded response\n\nThis approach improves reliability because:\n- The model does not rely only on pre-trained knowledge\n- It uses **real, up-to-date, domain-specific data**\n\n\u003e RAG systems enhance LLM outputs by injecting external knowledge before generation, improving accuracy and reducing hallucination. :contentReference[oaicite:0]{index=0}\n\n---\n\n## ⚙️ How the System Works\n\n### Text Flow\n1. User sends a query\n2. System checks:\n   - Chat history\n   - University dataset\n3. Relevant context is retrieved\n4. OpenAI generates a structured response\n\n### Voice Flow\n1. User provides audio input (`.mp3`)\n2. Audio is processed and transcribed\n3. Transcribed text follows the same RAG pipeline\n4. Final response is generated\n\n---\n\n## 🗂️ Project Structure\n\n```\n├── main.py                       # Core RAG chatbot pipeline (text)\n├── modified_main.py              # Enhanced / structured response version\n├── audio_main.py                 # Voice input + transcription + RAG pipeline\n├── output/                       # Generated outputs and processed data\n├── dummy1.mp3 - dummy5.mp3       # Sample audio files for testing\n```\n\n---\n\n\n---\n\n## 🧩 Tech Stack\n\n- **Python**\n- **OpenAI API (LLM + reasoning)**\n- **Pydantic (structured outputs)**\n- **Audio processing (local handling)**\n- **RAG architecture (custom implementation)**\n\n\u003e Note: This project primarily uses **OpenAI** for intelligence. No external speech API dependency is strictly required in this version.\n\n---\n\n## 🛠️ Setup Instructions\n\n### 1. Clone the repository\n```bash\ngit clone https://github.com/BusraRafa/Knowledge-Augmented-Academic-Assistant.git\ncd Knowledge-Augmented-Academic-Assistant\n```\n### 2. Install dependencies\n```\npip install -r requirements.txt\n```\n(If requirements.txt is missing, install manually: openai, python-dotenv, pydantic, pydub)\n\n### 3. Set environment variables\n\nCreate a .env file:\n```\nOPENAI_API_KEY=your_openai_api_key\n```\n## ▶️ Usage\nRun Text-Based Chatbot\n```\npython main.py\n```\nRun Voice-Based Assistant\n```\npython audio_main.py\n```\n## 🎧 Sample Audio\n\nYou can test the system using provided files:\n\n- dummy1.mp3\n- dummy2.mp3\n- dummy3.mp3\n- dummy4.mp3\n- dummy5.mp3\n\n## 📌 Notes\n- This repository only contains the AI module\n- Frontend, UI/UX, and full application integration are handled separately\n- Designed to be integrated into:\n  - Web apps\n  - WhatsApp bots\n  - Student platforms\n\n## 💡 Future Improvements\n- Better retrieval optimization (vector DB / embeddings)\n- Multilingual support\n- Better personalization for students\n- Integration with live university APIs\n- Text-to-Speech (voice output)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbusrarafa%2Fknowledge-augmented-academic-assistant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbusrarafa%2Fknowledge-augmented-academic-assistant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbusrarafa%2Fknowledge-augmented-academic-assistant/lists"}