← All Posts

📂 AI Agents & Applications

13 posts

Part 3.3: Implementing RAG from scratch

Build a simple RAG chatbot using ChromaDB and the GPT-5-nano model

#rag#chromadb#gpt-5-nano

Part 3.2: Understanding Vector Stores for RAG

Deep dive into vector stores—the specialized databases that power semantic search in RAG systems. Learn how they work, their evolution, and how to choose the right one for your Q&A chatbot.

#vector-store#embeddings#rag

Part 3.1: Building Q&A Chatbots Over Large Knowledge Bases

Learn how to build production-ready Q&A chatbots that can search across multiple documents and enterprise knowledge bases using RAG, embeddings, and vector stores to handle real-world scale and complexity.

#llm#rag#knowledge-base

Part 3: Q&A Chatbots with RAG

Master Retrieval-Augmented Generation (RAG) to build intelligent chatbots that answer questions over large knowledge bases using vector stores, retrievers, and LLMs with LangChain and LangSmith.

#llm#rag#chatbot

Part 2.3.1: Building Agentic Workflows with LangGraph - Practical Implementation

Hands-on guide to transforming a LangChain web research assistant into an agentic workflow using LangGraph with state management and conditional routing.

#llm#langgraph#agents

Part 2.3: Agentic Workflows with LangGraph

Learn how to build agentic workflows using LangGraph fundamentals, state management, and transition from LangChain chains to structured multistep processes.

#llm#langgraph#agents

Part 2.1: Summarizing Text with LangChain

Learn practical techniques for summarizing large documents and multiple documents using LangChain, LCEL, and advanced strategies like MapReduce.

#llm#langchain#summarization

Part 2.2: Summarizing Across Documents

Learn how to summarize information from multiple data sources using MapReduce and Refine techniques with LangChain document loaders.

#llm#langchain#summarization

Part 2: Summarization

Learn practical techniques for summarizing documents, building research engines, and creating agentic systems with LangChain and LangGraph.

#llm#summarization#langchain

Part 1.4: Executing Prompts Programmatically

Master prompt engineering techniques for text classification, sentiment analysis, summarization, composing text, question answering, and reasoning with practical examples.

#llm#prompt-engineering#chatgpt

Part 1.1: Understanding AI Applications

Learn about LLM-based applications, chatbots, and AI agents—understand their differences and when to use each pattern.

#llm#ai-agents#chatbots

Part 1.2: LangChain Framework

Explore LangChain architecture, core object model, and how it simplifies building production-grade LLM applications.

#llm#langchain#architecture

Part 1.3: Making LLMs Smarter

Master prompt engineering, RAG, fine-tuning, and learn how to choose the right LLM for your application needs.

#llm#prompt-engineering#rag