{"id":15063739,"url":"https://github.com/pramod-zillella/Agentic-Rag-Chatbot","last_synced_at":"2025-03-09T19:42:21.086Z","repository":{"id":270176901,"uuid":"909553901","full_name":"pramod-zillella/Agentic-Rag-Chatbot","owner":"pramod-zillella","description":"The Agentic RAG Fitness Chatbot is an AI-powered application designed to provide personalized fitness guidance and workout recommendations.","archived":false,"fork":false,"pushed_at":"2025-02-19T23:00:02.000Z","size":16014,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-19T23:29:24.819Z","etag":null,"topics":["agentic-rag","langgraph","langsmith","prompt-engineering"],"latest_commit_sha":null,"homepage":"https://fitness-coach.streamlit.app/","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/pramod-zillella.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":"2024-12-29T04:00:19.000Z","updated_at":"2025-02-19T23:00:05.000Z","dependencies_parsed_at":"2025-01-26T06:31:33.334Z","dependency_job_id":null,"html_url":"https://github.com/pramod-zillella/Agentic-Rag-Chatbot","commit_stats":null,"previous_names":["pramod-zillella/agenticragchatbot","pramod-zillella/agentic-rag-chatbot"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pramod-zillella%2FAgentic-Rag-Chatbot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pramod-zillella%2FAgentic-Rag-Chatbot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pramod-zillella%2FAgentic-Rag-Chatbot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pramod-zillella%2FAgentic-Rag-Chatbot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pramod-zillella","download_url":"https://codeload.github.com/pramod-zillella/Agentic-Rag-Chatbot/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242744061,"owners_count":20178171,"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":["agentic-rag","langgraph","langsmith","prompt-engineering"],"created_at":"2024-09-25T00:06:40.584Z","updated_at":"2025-03-09T19:42:21.076Z","avatar_url":"https://github.com/pramod-zillella.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Agentic RAG Fitness Chatbot\n\n## Overview\nThe Agentic RAG Fitness Chatbot is an AI-powered application designed to provide personalized fitness guidance and workout recommendations. Uses Retrieval-Augmented Generation (RAG), multi-agent systems, and a curated knowledge base, to deliver context-aware and actionable fitness advice. The chatbot focuses on empowering beginners with evidence-based fitness recommendations, real-time video demonstrations, and safety guidelines.\n\n### LangGraph Workflow\nThe LangGraph Workflow outlines the sequence of nodes in the system’s architecture. Each node represents a specific function, from query handling to generating responses. Below is the compiled workflow:\n\n![LangGraph Workflow](https://github.com/pramod-zillella/Agentic-Rag-Chatbot/blob/main/LangGraph-Workflow.png)\n\n## Architecture\nThe system consists of the following components:\n\n1. **User Input**: Accepts user queries through a Streamlit-based chat interface.\n2. **Query Refinement**: Transforms user input into an optimized format using an LLM-based query rewriting mechanism.\n3. **Retrieval System**:\n   - Encodes user queries using Sentence Transformers.\n   - Queries the Pinecone vector database to fetch relevant fitness data.\n   - Retrieves video demonstrations and transcripts.\n4. **Response Generation**: Synthesizes retrieved information using GPT-4o, ensuring the response is actionable and grounded in context.\n5. **Video Recommendations**: Displays video thumbnails, titles, and links alongside detailed transcripts.\n6. **Langsmith Integration**: Tracks agent-level decisions and improves overall system reliability.\n\n## Langsmith Trace and LangGraph Workflow\nTo provide transparency and insights into the system's behavior, the Langsmith trace and LangGraph workflow have been visualized:\n\n### Langsmith Trace\nThe Langsmith Trace captures the flow of the chatbot’s decision-making process, including tool calls and their respective responses. Below is an example trace showcasing a user query and the system's response:\n\n![Langsmith Trace](https://github.com/pramod-zillella/AgenticRagChatbot/blob/main/Langsmith-Trace.png)\n\n## Installation\n\n### Steps\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/pramod-zillella/AgenticRagChatbot.git\n   cd agentic-rag-fitness-chatbot\n   ```\n2. Install dependencies:\n   ```bash\n   pip install -r requirements.txt\n   ```\n3. Set up environment variables:\n   - Create a `.env` file in the project directory.\n   - Add your API keys:\n     ```\n     OPENAI_API_KEY=your_openai_api_key\n     PINECONE_API_KEY=your_pinecone_api_key\n     LANGCHAIN_API_KEY_V2=your_langchain_api_key\n     ```\n4. Run the Streamlit application:\n   ```bash\n   streamlit run interface.py\n   ```\n\n## Usage\n- **Predefined Questions**: Select from common fitness-related queries or type your own.\n- **Custom Queries**: Ask personalized questions about workouts, nutrition, or injury prevention.\n- **Interactive Recommendations**: View suggested video demonstrations and detailed response within the chat interface.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpramod-zillella%2FAgentic-Rag-Chatbot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpramod-zillella%2FAgentic-Rag-Chatbot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpramod-zillella%2FAgentic-Rag-Chatbot/lists"}