{"id":27813261,"url":"https://github.com/maheshsunuwar/rag_qa_system","last_synced_at":"2026-03-03T08:14:53.628Z","repository":{"id":290496477,"uuid":"974162446","full_name":"maheshsunuwar/rag_qa_system","owner":"maheshsunuwar","description":"Retrieval-Augmented Generation (RAG) QA System — An interactive system that retrieves relevant documents from a vector database and generates accurate answers using LLMs. Built with Streamlit, FAISS, and LangChain.","archived":false,"fork":false,"pushed_at":"2025-05-26T00:16:31.000Z","size":348,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-05-26T00:29:22.089Z","etag":null,"topics":["faiss","langchain","llm","mlops","ollama","openai","question-answering","rag","retrieval-augmented-generation","streamlit"],"latest_commit_sha":null,"homepage":"https://pdfchat.machinelearningdev.com","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/maheshsunuwar.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}},"created_at":"2025-04-28T10:54:24.000Z","updated_at":"2025-05-25T23:48:57.000Z","dependencies_parsed_at":"2025-04-29T06:22:32.645Z","dependency_job_id":"8fa13b85-2c75-447d-a5a8-dfd8ad145118","html_url":"https://github.com/maheshsunuwar/rag_qa_system","commit_stats":null,"previous_names":["maheshsunuwar/rag_qa_system"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/maheshsunuwar/rag_qa_system","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maheshsunuwar%2Frag_qa_system","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maheshsunuwar%2Frag_qa_system/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maheshsunuwar%2Frag_qa_system/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maheshsunuwar%2Frag_qa_system/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/maheshsunuwar","download_url":"https://codeload.github.com/maheshsunuwar/rag_qa_system/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maheshsunuwar%2Frag_qa_system/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259599326,"owners_count":22882354,"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":["faiss","langchain","llm","mlops","ollama","openai","question-answering","rag","retrieval-augmented-generation","streamlit"],"created_at":"2025-05-01T12:01:31.096Z","updated_at":"2026-03-03T08:14:53.570Z","avatar_url":"https://github.com/maheshsunuwar.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Retrieval-Augmented Generation (RAG) QA System\nWelcome to my project! This is a lightweight Retrieval-Augmented Generation (RAG) system where users can ask questions, and the system retrieves the most relevant documents and generates accurate answers using a language model (LLM).\n\n## Features\n- Build a vector database (FAISS) from document corpus\n- Retrieve top-k relevant contexts based on semantic similarity\n- Answer user questions grounded on retrieved documents\n- Streamlit Frontend for interactive querying\n- Embedding and Inference from Ollama models\n- Modular design for easy extensions and improvements\n\n## Technologies Used\n- Python 3.10+\n- Streamlit\n- FAISS\n- LangChain\n- Ollama/openai\n\n\n## Project Structure\n```\nrag_qa_system/\n├── README.md\n├── data/\n│   └── docs/\n│       └── sample_docs.txt\n├── app/\n│   ├── main.py\n│   ├── rag/\n│   │   ├── vector_store.py\n│   │   ├── retriever.py\n│   │   └── qa_pipeline.py\n│   └── config.py\n├── requirements.txt\n└── scripts/\n    └── initialize_embeddings.py\n```\n\n## Getting Started\n### Clone the repository:\n```\ngit clone https://github.com/yourusername/rag_qa_system.git\ncd rag_qa_system\n```\n\n### Install dependencies:\n```\npip install -r requirements.txt\n```\n\n### Set your OpenAI API key:\n#### Create a .env file:\n```\nIf you use openai instead of ollama\n```\n\n### Launch the app:\n```\nstreamlit run app/main.py\n```\n\n## How It Works\n- Ingest Documents → Split into smaller chunks\n- Embed Documents → Using Ollama Embeddings\n- Store Embeddings → In FAISS vector database\n- Retrieve Relevant Chunks → Based on user question\n- Generate Answer → Using llama3.2 based on retrieved context\n\n## Future Enhancements\n- Upload and ingest PDFs and Docs\n- Fine-tune retrieval for domain-specific datasets\n- Add evaluation metrics (e.g., retrieval precision, latency)\n- Deploy live on HuggingFace Spaces/AWS/Azure/GCP/self deploy\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaheshsunuwar%2Frag_qa_system","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmaheshsunuwar%2Frag_qa_system","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaheshsunuwar%2Frag_qa_system/lists"}