{"id":28826478,"url":"https://github.com/atithi4dev/vectraq-server","last_synced_at":"2026-04-28T17:02:25.375Z","repository":{"id":299515569,"uuid":"1003273633","full_name":"atithi4dev/VectraQ-server","owner":"atithi4dev","description":"End-to-end intelligent document Q\u0026A system using LangChain, OpenAI, and vector databases. Upload PDFs and get GPT-powered answers instantly.","archived":false,"fork":false,"pushed_at":"2025-06-16T23:46:49.000Z","size":54,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-17T00:25:18.433Z","etag":null,"topics":["document-ai","langc","openai","pdf-cahtbot","vector-search"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","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/atithi4dev.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":"2025-06-16T22:35:54.000Z","updated_at":"2025-06-16T23:46:53.000Z","dependencies_parsed_at":"2025-06-17T00:25:43.467Z","dependency_job_id":"bb722d7e-fe91-484b-9939-9dc14853bc98","html_url":"https://github.com/atithi4dev/VectraQ-server","commit_stats":null,"previous_names":["atithi4dev/vectraq-server"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/atithi4dev/VectraQ-server","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atithi4dev%2FVectraQ-server","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atithi4dev%2FVectraQ-server/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atithi4dev%2FVectraQ-server/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atithi4dev%2FVectraQ-server/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/atithi4dev","download_url":"https://codeload.github.com/atithi4dev/VectraQ-server/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atithi4dev%2FVectraQ-server/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32390067,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-28T14:34:11.604Z","status":"ssl_error","status_checked_at":"2026-04-28T14:32:37.009Z","response_time":56,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["document-ai","langc","openai","pdf-cahtbot","vector-search"],"created_at":"2025-06-19T03:04:37.043Z","updated_at":"2026-04-28T17:02:25.368Z","avatar_url":"https://github.com/atithi4dev.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ⚡ VectraQ-server\n\n## 📌 Status\n\u003e 💤 Currently on hold. Basic PDF parsing was prototyped, but the full “chat with PDF” pipeline is paused for now.\n\n---\n\n**VectraQ** is a document-based Q\u0026A system designed to let users upload PDFs, extract text, and eventually interact with the content using natural language queries powered by LLMs and vector embeddings.\n\nThis repo serves as the **monorepo** for both backend and frontend components.\n\n---\n\n## 🎯 Project Goals (Planned)\n\n- Upload and parse PDFs  \n- Chunk and embed text using LangChain + OpenAI  \n- Store embeddings in a vector database (Pinecone)  \n- Enable Q\u0026A over documents with context-aware responses  \n- Provide a clean UI for interacting with extracted text  \n\n---\n\n## 🛠️ Tech Stack (Planned)\n\n| Layer      | Tech                       |\n|------------|----------------------------|\n| Frontend   | React, Vite, Tailwind CSS  |\n| Backend    | Node.js, Express.js        |\n| NLP        | LangChain, OpenAI API      |\n| Vector DB  | Pinecone                   |\n| Utilities  | Multer, pdf-parse, Axios   |\n\n---\n\n## 📄 License\n\nMIT License.\n\n---\n\n## 🤝 Contributions\n\nWill open once active development resumes.\n\n---\n\nTurning documents into conversation — **VectraQ** (paused but not forgotten).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatithi4dev%2Fvectraq-server","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fatithi4dev%2Fvectraq-server","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatithi4dev%2Fvectraq-server/lists"}