I will build a rag ai chatbot on AWS bedrock for your documents


About this gig
Want an AI assistant that actually knows your business? I'll build a chatbot that answers questions from your own documents (PDFs, manuals, policies, FAQs) using Retrieval-Augmented Generation (RAG) on AWS Bedrock.
I helped launch an insurance company's AI Lab, where I built and deployed AI tools on AWS (Bedrock, Lambda, API Gateway) with Pinecone and DynamoDB, used by teams across the company.
What you get:
- A chatbot that answers from YOUR data, with sources, and fewer made-up answers
- Claude or Llama models through AWS Bedrock, so your data stays in your AWS account
- Vector search with Pinecone
- A secure REST API you can plug into your website, app or internal tools
- Deployment on AWS Lambda + API Gateway (Premium)
- Full source code and documentation
Why work with me:
- Senior backend developer: production-quality, secure code
- Clear communication and honest advice on what AI can and can't do
Message me before ordering so we can scope your use case.
Get to know Michael G
Senior Backend Developer, Spring Boot and AWS AI
- FromGreece
- Member sinceOct 2026
Languages
English, Greek
FAQ
Is my data safe? Will it be used to train AI models?
Your documents stay in your own AWS and Pinecone accounts. AWS Bedrock does not use your prompts or data to train its models. I can also sign an NDA if you need one.
Do I need my own AWS account?
For Standard and Premium, yes, so you own everything and pay AWS directly (usually a few dollars a month for small projects). For the Basic proof of concept, I can run the demo for you first. I'll guide you through setup and never need your root login.
What kinds of documents can the chatbot use?
PDFs, Word files, text, web pages and FAQs work well. Scanned images or complex tables may need extra processing. Send me a sample before ordering and I'll tell you honestly what to expect.
