Debjeet Bhowmik Every developer knows the feeling: you’re starting on a new team or tackling an open-source project, and you’re faced with a mountain of unfamiliar code. You spend hours, even days, grep-ing through files, tracing function calls, and trying to decipher the architecture from scattered comments and documentation. What if you could just ask the codebase … Read more
Our RAG systems have been powerful, but so far, they’ve been like a library with only one section. We’ve built a single, monolithic index and queried it. But what happens when your knowledge is spread across multiple, distinct sources? You don’t want to search the “engineering team roster” when a user asks about the “Q3 … Read more
We’ve seen LlamaIndex’s incredible power for building knowledge bases with Query and Chat Engines. Separately, in our LangChain projects, we’ve explored the world of agents—autonomous entities that can reason and use tools. What happens when we merge these two worlds? We get an agent that not only acts but has a deep, queryable “long-term memory” … Read more
In our last tutorial, we built a powerful knowledge base and used a QueryEngine to ask it questions. It worked flawlessly. You ask, “What is Sodepur known for?” and get a perfect, fact-based answer. But then you try a natural follow-up: You: “Why is that important?” Engine: (Confused) “Why is what important?” Your expert Q&A … Read more
In our last post, we saw LlamaIndex create a queryable engine from a text file in just a few lines. It felt almost magical. But what was really happening under the hood? How do you go from a messy folder of raw documents—PDFs, web pages, text files—to a structured, intelligent knowledge base that an AI … Read more
For our entire journey so far, we’ve focused on the “agent”—the reasoning loop, the tools, the planner. Our framework of choice, LangChain, is a powerful “agent-first” toolkit, a general-purpose workshop for building any kind of AI application. But what if we’ve been looking at the problem from only one angle? What if, instead of starting … Read more
You ask your powerful AI agent, “What was the top news story yesterday?” It confidently replies, “As a large language model, my knowledge cutoff is in early 2023, so I cannot provide you with information about yesterday’s news.” This is the wall every agent developer hits. For an agent to be truly useful and intelligent, … Read more
We’ve explored two of the most powerful concepts in Agentic AI: Retrieval-Augmented Generation (RAG), which gives an agent deep knowledge from an “open-book exam,” and Tool Use, which gives an agent hands to act upon the world. But what happens when you combine these two superpowers? You get an agent that can not only answer … Read more
You’ve built a complex, multi-step agent. Remember the Plan-and-Execute agent from Post #36? It had a planner, an executor, and multiple tools to solve a logic puzzle. When you ran it with verbose=True, the output was a long, linear scroll of text. Now imagine that for one step, the calculator tool was passed the wrong … Read more
No writer publishes their first draft. They write, they pause, and they critique their own work: “Is this sentence clear? Is the tone right? Could this be more persuasive?” This iterative loop of creation and self-criticism is fundamental to producing high-quality work. What if we could teach our AI agents to do the same? So … Read more