{"id":24807143,"url":"https://github.com/aksherwal/asksitare","last_synced_at":"2026-04-16T04:32:28.137Z","repository":{"id":264921458,"uuid":"894676824","full_name":"Aksherwal/AskSitare","owner":"Aksherwal","description":"It's an AI chatbot based on RAG pipeline for answering queries related to Sitare University.","archived":false,"fork":false,"pushed_at":"2025-03-10T16:08:09.000Z","size":57,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-25T10:14:14.080Z","etag":null,"topics":["chatbot","cosine-similarity","embeddings","llama","postgresql","rag-pipeline"],"latest_commit_sha":null,"homepage":"","language":"Python","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/Aksherwal.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}},"created_at":"2024-11-26T19:30:55.000Z","updated_at":"2025-03-10T16:08:15.000Z","dependencies_parsed_at":"2025-01-21T14:24:55.068Z","dependency_job_id":"bac1b156-bf4b-481f-99dd-7a8d43c24c8e","html_url":"https://github.com/Aksherwal/AskSitare","commit_stats":null,"previous_names":["aksherwal/asksitare"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aksherwal%2FAskSitare","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aksherwal%2FAskSitare/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aksherwal%2FAskSitare/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aksherwal%2FAskSitare/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Aksherwal","download_url":"https://codeload.github.com/Aksherwal/AskSitare/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245440582,"owners_count":20615633,"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","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":["chatbot","cosine-similarity","embeddings","llama","postgresql","rag-pipeline"],"created_at":"2025-01-30T09:17:16.736Z","updated_at":"2026-04-16T04:32:28.126Z","avatar_url":"https://github.com/Aksherwal.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AskSitare\n\nAskSitare is an intelligent chatbot web application designed specifically for Sitare University. It uses natural language processing and semantic search to provide accurate responses to university-related queries.\n\n## Features\n\n- Real-time chat interface for student queries\n- Semantic search using sentence transformers\n- Integration with Groq's LLaMA 3.3 70B model for generating responses\n- Feedback system for response quality tracking\n- Admin dashboard for monitoring feedback\n- PostgreSQL database for storing questions and feedback\n- Vector similarity search for finding relevant responses\n\n## Technologies Used\n\n- **Backend**: Flask (Python)\n- **Database**: PostgreSQL with psycopg2\n- **AI/ML**:\n  - Groq API for LLM integration\n  - Sentence Transformers for text embeddings\n  - LLaMA 3.3 70B model for response generation\n- **Frontend**: HTML, CSS, Tailwind, JavaScript\n\n## Live Link:\n👉[click here ](https://asksitare.onrender.com/)\n## Installation\n\n1. Clone the repository\n2. Install the required dependencies:\n```bash\npip install flask psycopg2-binary groq sentence-transformers\n```\n\n3. Set up environment variables:\n```bash\nexport GROQ_API_KEY=\"your_groq_api_key\"\nexport PORT=5000  # Optional, defaults to 5000\n```\n\n4. Configure the database connection in the code by updating `DB_PARAMS`:\n```python\nDB_PARAMS = {\n    \"dbname\": \"your_db_name\",\n    \"user\": \"your_db_user\",\n    \"password\": \"your_db_password\",\n    \"host\": \"your_db_host\",\n    \"port\": 5432\n}\n```\n\n## Usage\n\n1. Start the server:\n```bash\npython app.py\n```\n\n2. Access the chatbot interface at `http://localhost:5000`\n\n3. For admin access:\n   - Navigate to `/login`\n   - Use the admin credentials to access the dashboard\n   - View user feedback and interaction data\n\n## Features in Detail\n\n### Semantic Search\n- Uses sentence transformers to convert questions into embeddings\n- Performs vector similarity search to find relevant matches\n- Returns top 5 most similar questions and their associated answers\n\n### Chat Interface\n- Real-time response generation\n- Streaming responses for better user experience\n- Feedback system for users to rate responses\n\n### Admin Dashboard\n- Secure login system\n- View and analyze user feedback\n- Monitor chatbot performance\n\n### Database Schema\n\nThe application uses the following main tables:\n- `questions`: Stores questions and their embeddings\n- `topics`: Stores detailed answers/paragraphs\n- `feedback`: Stores user feedback on responses\n\n## ML Analysis\nClick here to see the ML analysis of the datasets we have👉 @ [ML Analysis](https://github.com/deepalitomar021/ML_Analysis_SU_Chatbot/blob/main/ML_analysis_suChatbot.ipynb)\n\n## Security\n- Secure admin login system\n- Environment variable based configuration\n- Database connection security\n- Session management for admin access\n\n## Contributing\n\nPlease follow these steps to contribute:\n1. Fork the repository\n2. Create a new branch for your feature\n3. Submit a pull request with a clear description of your changes\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faksherwal%2Fasksitare","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faksherwal%2Fasksitare","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faksherwal%2Fasksitare/lists"}