chatbot using RAG&LangChain

We are looking to hire a skilled and reliable developer to help build a conversational chatbot using Retrieval-Augmented Generation (RAG). The chatbot will answer user queries based on a custom knowledge base (e.g., CSV, documents, or structured metadata). The solution should be scalable, accurate, and capable of handling context-rich, domain-specific questions.

Responsibilities:
Set up the complete RAG pipeline using LLMs + Vector Database (e.g., FAISS, Chroma, or Pinecone)

Preprocess and chunk custom data (text, CSV, or documents) for embedding

Use embedding models (e.g., OpenAI, Hugging Face) to create vector representations

Build a retriever + LLM-based generator workflow using LangChain or similar frameworks

Implement conversational memory for multi-turn interaction

Optimize response relevance, speed, and factual accuracy

Optionally integrate via a simple API or web UI

✅ Requirements:
Strong experience with RAG architecture, vector databases, and LLMs

Proficiency in Python and libraries like LangChain, Transformers, and FAISS

Familiarity with prompt engineering, retrieval scoring, and data cleaning

Experience deploying chatbot or QA systems is a big plus

Budget & Timeline:
Competitive hourly/fixed rate depending on experience

Immediate start – short-term with potential for extension

How to Apply:
Please share:

Your experience with RAG or LLM-based chatbots

Relevant GitHub projects or demos

Availability and preferred rate