Browse categories
Explore
Fiverr Pro
English
$
USD
I will make a custom rag application using openai gpt or opensource model
Sarab Dar
About this gig
Looking to build AI systems that understand and query your private data intelligently?
Im a Computer Vision & Applied AI Engineer with 4+ years of experience building real-world AI systems, including LLM apps, RAG pipelines, and multimodal AI solutions.
I build Retrieval-Augmented Generation (RAG) systems that let you chat with your data (PDFs, docs, CSVs, databases) using accurate, context-aware LLM responses.
WHAT I CAN BUILD
- RAG systems for PDFs, docs, CSVs, databases
- Chatbots powered by OpenAI / Llama / Mistral / Groq
- Vector DB systems (FAISS, Pinecone, Chroma)
- LLM Q&A systems with reduced hallucinations
- API-based AI backends using FastAPI
- AI apps using Streamlit
DEPLOYMENT OPTIONS
- Streamlit (interactive dashboards)
- FastAPI (scalable backends)
- API integration into systems
TECH STACK
Python, LangChain, LlamaIndex, OpenAI API, Groq, FAISS, Pinecone, ChromaDB, FastAPI, Streamlit
WHAT I NEED
- Data source (PDFs, docs, DBs)
- Project goal
- Model API
- I build practical, production-ready AI systems tailored to real use cases.
Please contact me before ordering.
Let Collaborate!
Get to know Sarab Dar
Sarab Dar
ML Engineer
- FromPakistan
- Avg. response time1 hour
Languages
Urdu, English, Spanish, German, French
Computer Vision & Applied AI Engineer with 4+ years of experience building real-time intelligent systems for surveillance, automation, and video analytics.
I specialize in computer vision systems including object detection, tracking, segmentation, RTSP/CCTV pipelines, as well as training and fine-tuning deep learning models. I also build LLM-based applications such as chatbots, voice assistants, and multimodal AI systems.
Currently working at HyperVisionWorld Pvt. Ltd. developing production-grade AI surveillance systems and scalable real-time solutions.
My Portfolio
FAQ
Can the chatbot "talk" to specific documents (PDF, CSV, SQL)?
Absolutely! This is the core of a RAG (Retrieval-Augmented Generation) system. I will build a pipeline that "indexes" your private data into a Vector Database so the AI can retrieve and answer questions based solely on your provided information.
What is the benefit of a FastAPI vs. a Streamlit interface?
Streamlit is perfect if you need a beautiful, ready-to-use web dashboard to interact with your AI immediately. FastAPI is best if you are a developer or have an existing website/app and just need a high-performance "brain" (API endpoint) to plug into your current system.
How do i ensure the AI doesn't "hallucinate" or make things up?
I implement advanced RAG techniques, including strict system prompting and "Source Attribution." This means the AI is instructed to only answer based on the provided context. If the answer isn't in your data, the bot will honestly state it doesn't know rather than making up a fact.
