RAG Chatbot Developer Needed for Custom Knowledge Base & AI Q&A

We are looking for an experienced RAG (Retrieval-Augmented Generation) / AI Chatbot Developer to build a production-ready chatbot that can answer questions accurately based on our own documents and knowledge base. What We Need The core requirement is a chatbot that allows users to ask natural-language questions and receive accurate, context-aware answers from a private knowledge base. The system should include: - Document upload and processing - Text extraction and intelligent chunking - Embedding generation - Vector database integration - Semantic / vector search - RAG pipeline for retrieving relevant context - LLM-based answer generation - Conversation / chat history - Source / citation references where applicable - Proper handling of questions where the answer is not available in the knowledge base - REST API / backend integration - Clean and maintainable code Expected Workflow Documents → Processing → Chunking → Embeddings → Vector Database → Retrieval → Relevant Context → LLM → Final Answer We are open to your recommendations regarding the exact technologies and architecture. Preferred Technologies Experience with the following is highly preferred: - Python - FastAPI - LangChain / LangGraph - RAG architectures - OpenAI or similar LLM APIs - Vector databases such as Pinecone, Qdrant, Weaviate, or Chroma - Sentence Transformers / embedding models - REST APIs - PostgreSQL or MongoDB - Docker You do not need to use every technology listed above. We care more about building a reliable RAG system than using a particular framework. What We Expect From You You should have practical experience building RAG applications, not just basic chatbot integrations. Please be able to explain: 1. How you would design the RAG pipeline 2. How you would handle document chunking and embeddings 3. How you would improve retrieval accuracy 4. How you would prevent the LLM from hallucinating information that isn't present in the knowledge base 5. Which vector database and LLM you would recommend and why 6. How you would evaluate the quality of the RAG system Deliverables - Fully functional RAG chatbot - Document ingestion pipeline - Vector database setup - Retrieval + generation pipeline - Backend / API - Chat interface or API-ready chatbot functionality - Source / context references where appropriate - Environment / configuration setup - Clean, documented source code - Deployment / setup instructions Working Style We prefer someone who: - Communicates clearly and regularly - Gives realistic estimates - Can explain technical decisions in simple terms - Is comfortable working independently - Asks questions when requirements are unclear rather than making risky assumptions - Provides incremental progress and testing during development - Writes maintainable, production-quality code To Apply Please include: 1. A brief description of your RAG experience 2. 1-2 RAG/AI chatbot projects you have actually built 3. The technologies used in those projects 4. Your recommended architecture for this project 5. Your preferred LLM and vector database for this use case, with a brief reason 6. Estimated timeline 7. Your hourly rate or fixed-price estimate Note: Generic AI-generated proposals without relevant RAG experience will not be considered.