Lex Fridman Podcast Chatbot with LangChain Agents + GPT 3.5
In this video, we will build a conversational (chatbot) agent using LangChain agents. The agent uses vector search retrieval to find relevant snippets from Lex's podcast and serve them as context to the LLM (we use the OpenAI ChatGPT model called gpt-3.5-turbo). 🔗 Code notebook: https://github.com/pinecone-io/examples/blob/master/learn/generation/chatbots/conversational-agents/langchain-lex-agent.ipynb 🎙️ Support me on Patreon: https://patreon.com/JamesBriggs 🎨 AI Art: https://www.etsy.com/uk/shop/IntelligentArtEU 🤖 70% Discount on the NLP With Transformers in Python course: https://bit.ly/3DFvvY5 🎉 Subscribe for Article and Video Updates! https://jamescalam.medium.com/subscribe https://medium.com/@jamescalam/membership 👾 Discord: https://discord.gg/c5QtDB9RAP 00:00 Building conversational agents in LangChain 00:14 Tools and Agents in LangChain 03:57 Notebook setup and prerequisites 05:23 Data preparation 11:00 Initialize LangChain vector store 13:12 Initializing everything needed by agent 13:41 Using RetrievalQA chain in LangChain 15:59 Creating Lex Fridman DB tool 17:37 Initializing a LangChain conversational agent 21:49 Conversational memory prompt 27:41 Testing a conversation with the Lex agent #langchain #artificialintelligence #nlp #openai
