{"id":27499489,"url":"https://github.com/gokulgowthams/askdocs_gen-ai","last_synced_at":"2026-04-11T11:38:52.550Z","repository":{"id":286784617,"uuid":"962533375","full_name":"GokulGowthamS/AskDocs_GEN-AI","owner":"GokulGowthamS","description":"Private Document Questioning and Answering Application which can answer any question that has been asked, by uploading the desired document the user can ask questions","archived":false,"fork":false,"pushed_at":"2025-04-12T14:02:30.000Z","size":2207,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-22T04:47:32.950Z","etag":null,"topics":["chromadb","deeplearning","docx2txt","faiss","generativeai","huggingface","langchain","llama2","llamaindex","openaiembeddings","pdfplumber","pinecone","pymupdf","sentencetransformer","streamlit"],"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/GokulGowthamS.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":"2025-04-08T09:46:30.000Z","updated_at":"2025-04-22T06:55:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"79fc88cf-ae6b-4fcc-ac9f-1e00e7e70184","html_url":"https://github.com/GokulGowthamS/AskDocs_GEN-AI","commit_stats":null,"previous_names":["gokulgowthams/askdocs_gen-ai"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/GokulGowthamS/AskDocs_GEN-AI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GokulGowthamS%2FAskDocs_GEN-AI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GokulGowthamS%2FAskDocs_GEN-AI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GokulGowthamS%2FAskDocs_GEN-AI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GokulGowthamS%2FAskDocs_GEN-AI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GokulGowthamS","download_url":"https://codeload.github.com/GokulGowthamS/AskDocs_GEN-AI/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GokulGowthamS%2FAskDocs_GEN-AI/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270962391,"owners_count":24675965,"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","status":"online","status_checked_at":"2025-08-18T02:00:08.743Z","response_time":89,"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":["chromadb","deeplearning","docx2txt","faiss","generativeai","huggingface","langchain","llama2","llamaindex","openaiembeddings","pdfplumber","pinecone","pymupdf","sentencetransformer","streamlit"],"created_at":"2025-04-17T09:33:03.596Z","updated_at":"2026-04-11T11:38:47.521Z","avatar_url":"https://github.com/GokulGowthamS.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 💬 AskDocs AI\n\n\u003e *From documents to decisions — powered by AI, secured locally.*\n\n## 🔍 What is AskDocs AI?\n\n**AskDocs AI** is a early stage startup comprising a powerful and private document question-answering app powered by **LLaMA 2** and **LangChain**. Upload your PDF, DOCX, or TXT files, and ask intelligent questions. All data is processed locally to maintain maximum privacy.\n\n---\n\n## 🎯 Features\n\n- 📄 Supports PDF, DOCX, and TXT files\n- 🧠 Local LLaMA 2 model inference (no cloud dependencies)\n- 🔍 Intelligent search \u0026 similarity-based retrieval\n- 📦 Built with Streamlit for an interactive UI\n- 🖼️ Custom dark-themed background support\n- 🧵 Efficient multi-threaded document parsing\n\n---\n\n## 🚀 Getting Started\n\n### 📦 Prerequisites\n\n- Python 3.9+\n- Download the LLaMA 2 model from [HERE!](https://huggingface.co/gokulgowtham01/AskDocs_GEN-AI/tree/main)  \n\n### 📁 Folder Structure  \n  \n```  \nproject_root/\n├── gen_ai.py                           # Streamlit application  \n├── images/\n│   └── freepik__adjust__9850.jpeg\n│   └── 767.jpg\n├── faiss_index/                        # Generated vector store  (auto-created)\n├── evaluation_logs/                    # Generated json file  (auto-created)  \n├── documents/\n│   ├── empty.txt\n│   ├── sample_doc.docx\n│   ├── Advanced_Facts_Octopus.pdf  \n│   └── sample_txt.txt\n└── requirements.txt  \n```\n\n---\n\n## 🧰 Installation\n\n```bash\n# Clone the repo\ngit clone https://github.com/yourusername/AskDocs_GEN-AI.git\ncd AskDocs_GEN-AI\n\n# (Optional) Create a virtual environment\npython -m venv venv\nsource venv/bin/activate  # On Windows: venv\\Scripts\\activate\n\n# Install dependencies\npip install -r requirements.txt\n\n```  \n## 🧠 Usage  \n\n```bash\n# Run\nstreamlit run app.py\n```\n\n1.  Upload one or more PDF, DOCX, or TXT documents.  \n2.  Click Start The Fun!  \n3.  Ask your question in natural language.  \n4.  Get answers with cited document sources.\n\n## 📦 Dependencies  \n \n- streamlit  \n- PyMuPDF  \n- python-docx  \n- docx2txt  \n- requests  \n- numpy  \n- langchain  \n- sentence-transformers  \n- nltk  \n- rouge-score  \n- ctransformers  \n- faiss-cpu  \n- huggingface-hub  \n\n## 📎 Notes  \n\n- You need to download and manually place the LLaMA model.\n- Ensure GPU support is configured if needed (set gpu_layers accordingly).\n- Image background is customizable — make sure the image path is valid.\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgokulgowthams%2Faskdocs_gen-ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgokulgowthams%2Faskdocs_gen-ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgokulgowthams%2Faskdocs_gen-ai/lists"}