I will build a rag chatbot that answers from your pdfs and documents

M
manvik_77
M
manvik_77
Manvik T

About this gig

Want a chatbot that answers questions from YOUR documents and doesn't make things up?


I build retrieval-augmented (RAG) chatbots that read your PDFs, docs or website content and answer with clickable source citations, so your team and customers can verify every answer. If the documents don't contain the answer, the bot says so instead of guessing.


What you get:

  • A chatbot trained on your documents (PDF, DOCX, TXT, web pages)
  • Source citations on every answer
  • A clean chat page, embeddable on your website (Standard and Premium)
  • Setup guide and source code you own
  • Works with OpenAI, Azure OpenAI, or a local model if your data can't leave your servers

Why me: I deployed an enterprise document assistant at Path Infotech using Azure Cognitive Search with a citation layer, and built LLM systems at Niva Bupa that route low-confidence cases to humans instead of guessing.


Send me a sample of your documents before ordering and I'll tell you honestly whether RAG fits your use case.

Get to know Manvik T

Manvik T

AI Engineer for RAG Chatbots, LLM Agents and Web Apps

  • FromIndia
  • Member sinceSep 2026
  • Avg. response time1 hour
  • Languages

    Hindi, English
I build AI chatbots and automations that stay accurate and stay under your control. Past work: an assistant that answers from company PDFs with clickable source citations (Path Infotech), an LLM claims-review engine that sends uncertain cases to a human instead of guessing (Niva Bupa), and an agent platform with approval gates and full audit logs. I also build fast React / Next.js sites and FastAPI backends. You get clear milestones, plain-English updates and code you own. B.Tech in AI & ML, based in India, replies within a few hours.

My Portfolio