Generative AI with LangChain
In this section, I explore the inner workings of LangChain for building systems with Large Language Models (LLMs). The projects cover integration with both OpenAI and Hugging Face models, demonstrating hands-on experience with chat models and conversational prompting. From foundational concepts like Prompt Templates and Output Parsers to advanced techniques like cost tracking, streaming, and caching to improve performance and response time, enabling smoother, cost-effective interactions with generative models.