Sriyanshi Sinha

Built Retrieval-Augmented Generation (RAG) pipelines using LangChain, LlamaIndex, and vector databases (Pinecone, FAISS, ChromaDB). Developed AI-powered chatbots and virtual assistants with context-aware conversations and memory management. Engineered prompt templates and prompt optimization techniques to improve response quality, accuracy, and reduce hallucinations. Integrated LLM APIs with backend services using Python, FastAPI, Flask, and REST APIs.