Build a customer support chatbot that leverages custom knowledge from an FAQ help center using an open-source LLM and free embeddings through LangChain. Learn to create a chatbot capable of delivering real-time responses with streaming on a single GPU (T4). Explore the process of constructing the chatbot, including setting up Google Colab, creating a dataset, integrating an LLM from HuggingFace, embedding data, implementing conversational and QA chains, and developing a chatbot class. Evaluate the chatbot's response quality by testing it with various questions and gain insights into building effective AI-powered customer support solutions.
Customer Support Chatbot Using Custom Knowledge Base with LangChain and Private LLM
Overview
Syllabus
- Introduction
- Text Tutorial
- FAQ Data Source
- Google Colab Setup
- Create Dataset
- LLM from HuggingFace in LangChain
- Embedding Data
- Conversational Chain
- QA Chain
- Chatbot Class
- Conclusion
Taught by
Venelin Valkov
Related Courses
-
Chat with Multiple PDFs Using Llama 2 and LangChain - Use Private LLM and Free Embeddings for QA
-
Fine-Tuning Llama 3 on a Custom Dataset for RAG Q&A - Training LLM on a Single GPU
-
Fine-Tuning LLM with QLoRA on Single GPU - Training Falcon-7b on ChatBot Support FAQ Dataset
-
Advanced RAG with Llama 3 in LangChain - Building a PDF Chat System
-
Build ChatGPT Chatbots with LangChain Memory - Understanding and Implementing Memory in Conversations
-
RAG from Scratch with Llama 3.1 - Building a Custom Data Chatbot
