{"id":29371695,"url":"https://github.com/samay-jain/voice_assistant_rag_system_using_langchain_and_streamlit","last_synced_at":"2026-04-10T11:32:40.688Z","repository":{"id":303264374,"uuid":"1014904663","full_name":"samay-jain/Voice_Assistant_RAG_System_using_LangChain_and_Streamlit","owner":"samay-jain","description":"Voice Assistant RAG System using LangChain, Whisper, and Streamlit - A voice-enabled assistant that lets you ask questions by speaking, processes your custom documents, and responds with natural speech. Built with LangChain, Ollama, Whisper, ElevenLabs, and Streamlit.","archived":false,"fork":false,"pushed_at":"2025-07-06T17:22:11.000Z","size":376,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-06T17:46:22.010Z","etag":null,"topics":["ai-assistant","document-processing","elevenlabs","faiss","langchain","llm","ollama","python","rag","retrieval-augmented-generation","speech-recognition","streamlit","text-to-speech","voice-assistant","whisper"],"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/samay-jain.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":"2025-07-06T16:26:46.000Z","updated_at":"2025-07-06T17:25:56.000Z","dependencies_parsed_at":"2025-07-06T17:46:25.657Z","dependency_job_id":"68de5c8e-cf01-4d11-bf90-5bb4b91811dc","html_url":"https://github.com/samay-jain/Voice_Assistant_RAG_System_using_LangChain_and_Streamlit","commit_stats":null,"previous_names":["samay-jain/voice_assistant_rag_system_using_langchain_and_streamlit"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/samay-jain/Voice_Assistant_RAG_System_using_LangChain_and_Streamlit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samay-jain%2FVoice_Assistant_RAG_System_using_LangChain_and_Streamlit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samay-jain%2FVoice_Assistant_RAG_System_using_LangChain_and_Streamlit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samay-jain%2FVoice_Assistant_RAG_System_using_LangChain_and_Streamlit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samay-jain%2FVoice_Assistant_RAG_System_using_LangChain_and_Streamlit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/samay-jain","download_url":"https://codeload.github.com/samay-jain/Voice_Assistant_RAG_System_using_LangChain_and_Streamlit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samay-jain%2FVoice_Assistant_RAG_System_using_LangChain_and_Streamlit/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":264492281,"owners_count":23617025,"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":["ai-assistant","document-processing","elevenlabs","faiss","langchain","llm","ollama","python","rag","retrieval-augmented-generation","speech-recognition","streamlit","text-to-speech","voice-assistant","whisper"],"created_at":"2025-07-09T16:00:45.645Z","updated_at":"2026-04-10T11:32:40.646Z","avatar_url":"https://github.com/samay-jain.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🎙️ Voice Assistant RAG\n\n\u003e A fully interactive, voice-controlled AI assistant powered by Retrieval-Augmented Generation (RAG), Whisper speech-to-text, and ElevenLabs voice synthesis.\n\n---\n\n![RAG Voice Assistant Demo](https://img.shields.io/badge/LLM-Ollama-blue?style=flat-square)\n![Built with Streamlit](https://img.shields.io/badge/Frontend-Streamlit-orange?style=flat-square)\n![License](https://img.shields.io/badge/License-MIT-green.svg?style=flat-square)\n\n---\n\n## 🚀 Features\n\n- 🔍 **RAG-based Q\u0026A**: Ask voice questions, get accurate answers sourced from your documents.\n- 🗂️ **Knowledge Base Setup**: Upload `.pdf`, `.txt`, or `.md` files and embed them using local FAISS vector store.\n- 🎧 **Whisper Integration**: High-quality speech-to-text transcription using OpenAI's Whisper model.\n- 🗣️ **ElevenLabs TTS**: Convert AI responses into realistic voice output.\n- 🧠 **Chat Memory**: Keeps track of your conversation context.\n- 🖥️ **Streamlit UI**: Clean, interactive web interface — no CLI needed.\n\n---\n## Demonstration\n![image](https://github.com/user-attachments/assets/0ed75a54-c751-47e4-a2c0-1fe5d637c44f)\n![image](https://github.com/user-attachments/assets/d45c4579-5b77-4006-b72a-e395d867b9f7)\n![image](https://github.com/user-attachments/assets/6461935d-8896-40f8-ae73-4f89787dac94)\n\n\n---\n## 🛠️ Tech Stack\n\n| Layer       | Technology             |\n|------------|-------------------------|\n| Frontend   | Streamlit               |\n| LLM        | `llama3.2` via Ollama |\n| Embedding  | `nomic-embed-text` via Ollama |\n| Vector DB  | FAISS                   |\n| STT        | Whisper (`base` model)  |\n| TTS        | ElevenLabs              |\n\n---\n\n### Clone the repo and navigate into it\n```git clone https://github.com/samay-jain/Voice_Assistant_RAG_System_using_LangChain_and_Streamlit```\n\n### Create and activate virtual environment\n```python -m venv venv \u0026\u0026 source venv/bin/activate  # On Windows use: venv\\Scripts\\activate```\n\n### Install dependencies\n```pip install -r requirements.txt```\n\n### Add your ElevenLabs API key in a .env file\n```echo \"ELEVEN_LABS_API_KEY=your_api_key_here\" \u003e .env```\n\n### Pull required Ollama models\n```ollama pull llama3.2 \u0026\u0026 ollama pull nomic-embed-text```\n\n### Run the app\n```streamlit run main.py```\n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsamay-jain%2Fvoice_assistant_rag_system_using_langchain_and_streamlit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsamay-jain%2Fvoice_assistant_rag_system_using_langchain_and_streamlit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsamay-jain%2Fvoice_assistant_rag_system_using_langchain_and_streamlit/lists"}