Browse categories
Explore
Fiverr Pro
English
$
USD
I will build a custom rag chatbot with your data and vector database
Shihan Rahman
About this gig
Need an AI chatbot that answers from your trusted knowledge instead of relying only on general model training?
I will build a custom RAG chatbot using your approved documents, website content, knowledge base, or business data. Your content is prepared, chunked, embedded, stored in a vector database, and retrieved through semantic search before the model creates an answer.
Possible solutions:
Website or SaaS knowledge chatbot
Customer-support FAQ assistant
Internal company knowledge assistant
Product-documentation chatbot
Training or research assistant
Chatbot with citations and human handoff
Depending on your package, delivery can include PDF, DOCX, TXT, CSV, HTML, or website ingestion; metadata filtering; reranking; citations; memory; roles; feedback; APIs; tests; Docker; documentation; and deployment support.
Technologies may include Python, FastAPI, GPT, Claude, Gemini, LangChain, LangGraph, LlamaIndex, Pinecone, Qdrant, Weaviate, Chroma, pgvector, and Redis.
Please contact me before ordering if your data is private, large, multilingual, frequently updated, or spread across several systems. Third-party service and hosting fees are not included.
Get to know Shihan Rahman
Shihan Rahman
AI Engineer and Automation Specialist
- FromBangladesh
- Member sinceDec 2019
- Avg. response time1 hour
Languages
Bengali, English, Hindi, Urdu
I am an AI Engineer and Systems Architect who designs, builds, deploys, and operates AI, automation, API, and SaaS systems. I create AI agents, RAG chatbots, voice assistants, workflows, REST APIs, data pipelines, and full-stack applications.
I handle architecture, development, databases, testing, security, Docker, GitHub, CI/CD, Linux VPS, Nginx, monitoring, and support. I integrate payments, CRM, email, calendars, telephony, messaging, webhooks, and third-party APIs.
Stack: Python, FastAPI, LangGraph, OpenAI, Claude, Vector DB, PostgreSQL, Redis, React, Next.js, Pinecone, Qdrant, and n8n.
My Portfolio
FAQ
What is RAG?
RAG retrieves relevant information from approved knowledge before the model answers.
Which vector databases do you support?
Pinecone, Qdrant, Weaviate, Chroma, or pgvector, selected according to your needs.
Can the chatbot show sources?
Yes, when the design and source format support reliable references.
Can it use private documents and update its knowledge?
Yes, with an agreed privacy, access, storage, and update workflow.
Are model, vector database, and hosting fees included?
No. Third-party fees are paid by the buyer unless included in a custom offer.
