Browse categories
Explore
Fiverr Pro
English
$
USD
I will build a production rag pipeline with langchain, chromadb, and fastapi
Manas J
About this gig
Are you building an AI product that needs to actually work in production not just a demo?
I build production-grade RAG pipelines using LangChain, ChromaDB, and FastAPI. I've shipped RAG systems with multi-document retrieval, semantic search, conversation memory, and voice interfaces including a project recognized at the Google GenAI Hackathon 2025. I've also published an open-source AutoML library on PyPI and built a 7-metric LLM evaluation framework from scratch.
What you get:
Multi-document RAG pipeline with LangChain + ChromaDB
Async FastAPI backend with clean REST endpoints
Semantic search with smart chunking strategy
Conversation memory + source citation
Docker deployment ready to ship
Source code + detailed documentation
I don't prototype. I architect systems built for real users and real scale.
Message me before ordering I want to understand your use case and make sure I deliver exactly what you need.
Get to know Manas J
Manas J
Freelance AI Engineer
- FromIndia
- Member sinceMay 2026
- Avg. response time1 hour
Languages
Hindi, Oriya, English, Punjabi
I am an AI Engineer and Backend Developer specializing in RAG pipelines, multi-agent systems, and LLM fine-tuning. I have extensive experience building production-grade backends with FastAPI, Celery, and Docker, and I have successfully led teams in high-stakes environment to deliver complex ML solutions.
My Portfolio
FAQ
What kind of documents or data sources can the RAG pipeline handle?
PDF, plain text, Word documents, and web-scraped content. The pipeline uses a smart chunking strategy to handle large documents efficiently, preserving context across chunks for accurate retrieval.
Which LLMs can I use with this RAG system?
OpenAI (GPT-4o, GPT-3.5), Google Gemini, Anthropic Claude, or open-source models via Ollama/HuggingFace. The architecture is model-agnostic — swapping the LLM requires minimal changes.
Will I be able to run this on my own server?
Yes. The entire system is containerized with Docker and Docker Compose. You get a self-hostable setup with no vendor lock-in. I'll also provide clear deployment instructions.
Do I need to know Python or AI to use the delivered system?
No. I deliver a working API with documentation. If you have a development team, they can extend it easily. If not, the system works out of the box via the FastAPI endpoints.
What do you need from me to get started?
A brief description of your use case, the data/documents you want the system to query, and which LLM provider you prefer. I'll confirm scope before starting.
