Browse categories
Explore
Fiverr Pro
English
$
USD
I will build a custom rag chatbot or llm app with langchain, faiss, and fastapi
Farheenfathimaa
About this gig
Are you drowning in documents? Need a chatbot that actually knows your data not just generic internet answers?
I build production-grade Retrieval-Augmented Generation (RAG) systems and LLM applications tailored to your use case whether that's a PDF Q&A bot, a database query interface, or a full multi-agent workflow.
What I build:
- RAG pipelines over PDFs, CSVs, websites, or databases
- LLM chatbots with conversation memory and source citations
- NL-to-SQL agents (ask your database in plain English)
- Multi-agent systems for complex reasoning workflows
- FastAPI backends + Streamlit/React frontends
- Dockerized, deployment-ready packages
Tech stack: LangChain · LangGraph · FAISS · ChromaDB · OpenAI / Groq / HuggingFace · FastAPI · Docker · Python
Why me: I'm an AI/ML engineer with hands-on experience deploying RAG chatbots for real clients (see my portfolio: github.com/farheenfathimaa/project-portfolio). I write clean, documented code not just working demos.
You get: well-structured GitHub repo, environment setup instructions, and a README you can actually follow.
Let's discuss your use case before you order I want make sure I deliver exactly what you need.
Get to know Farheenfathimaa
Farheenfathimaa
I Build RAG Chatbots and AI Automation for Businesses
- FromIndia
- Member sinceMay 2024
- Last delivery1 year
Languages
Urdu, English, Telugu, Hindi
I'm an AI/ML Engineer building production-ready RAG pipelines, LLM apps, and Python automation — not just prototypes.
Built: retail RAG chatbot with RBAC + Docker; multilingual speech pipeline on HuggingFace; multi-agent system with 99%+ accuracy; NL-to-SQL with FastAPI; ELK on Kubernetes handling 100K+ daily logs.
Need a document chatbot, automation script, or custom ML model? I deliver it deploy-ready.
Stack: Python, LangChain, FastAPI, FAISS, Docker, PyTorch, Groq, Kubernetes
My Portfolio
FAQ
Q: Which LLM provider do you use?
A: OpenAI (GPT-4o/3.5) by default. I can also use Groq, Gemini, Mistral, Claude, or any HuggingFace model — let me know your preference or budget.
Q: Do I need to provide my own API keys?
A: Yes, you'll need an API key for the LLM provider (e.g. OpenAI). I'll show you exactly where to add it — it stays private to you.
Q: Can you integrate with my existing database or app?
A: Yes — share your schema/API docs and I'll build the integration. Mention this before ordering so we can scope it correctly.
Q: What format do you deliver the code in?
A: A private GitHub repo with full source code, Dockerfile, .env template, and README with setup steps.
Q: Can you also host/deploy it for me?
A: Deployment guidance is included at Premium tier. For managed hosting, that's a separate arrangement — message me.
