-
Continue reading →: #30DaysOfLangChain – Day 30: Review, Best Practices & Next Steps
We’ve made it! Day 30 marks the grand finale of our #30DaysOfLangChain – LangChain 0.3 Edition challenge. It’s been an incredible journey of discovery, building, and learning. Today isn’t about new code, but about looking back at what we’ve accomplished, understanding how to transition our projects from development to production,…
-
Continue reading →: #30DaysOfLangChain – Day 29: Final Project Day: Build a Comprehensive GenAI Application
Welcome to Day 29 of #30DaysOfLangChain – LangChain 0.3 Edition! We’ve covered a vast landscape, from the fundamentals of LLMs and basic chains to building sophisticated LangGraph agents, creating interactive UIs with Streamlit, exposing APIs with FastAPI, and ensuring observability with LangSmith. Today is our capstone project: consolidating all this…
-
Continue reading →: #30DaysOfLangChain – Day 28: Advanced Multi-Agent Patterns & Agent Teams
Welcome to Day 28 of #30DaysOfLangChain – LangChain 0.3 Edition! So far, we’ve built powerful individual agents, but what happens when a problem is too complex for a single AI? Or when you need diverse perspectives, error checking, and iterative improvement? This is where advanced multi-agent patterns come into play!…
-
Continue reading →: #30DaysOfLangChain – Day 27: Evaluating LLM Applications: Metrics & Tools
Welcome to Day 27 of #30DaysOfLangChain – LangChain 0.3 Edition! We’ve spent weeks building sophisticated LLM chains and agents, exposing them via UIs and APIs, and even setting up observability with LangSmith. But how do we truly know if our GenAI application is good? How do we measure its performance,…
-
Continue reading →: #30DaysOfLangChain – Day 26: Observability with LangSmith & Tracing
Welcome to Day 26 of #30DaysOfLangChain – LangChain 0.3 Edition! We’ve built powerful LLM chains, complex LangGraph agents, and exposed them via interactive UIs and APIs. But as these applications grow, a critical question emerges: How do we understand what’s happening inside them? How do we debug when an LLM…
-
Continue reading →: #30DaysOfLangChain – Day 25: FastAPI for LangGraph Agents & Streaming Responses
Welcome to Day 25 of #30DaysOfLangChain – LangChain 0.3 Edition! Yesterday, we laid the groundwork for exposing our LangChain applications as RESTful APIs using FastAPI. Today, we’re taking that a significant step further: serving a more complex LangGraph agent and providing real-time streaming responses. When dealing with intelligent agents that…
-
Continue reading →: #30DaysOfLangChain – Day 24: Exposing LangChain Apps via FastAPI (Basic Chat API)
Welcome to Day 24 of #30DaysOfLangChain – LangChain 0.3 Edition! Over the past few days, we’ve built interactive UIs with Streamlit. While great for demos and internal tools, many real-world AI applications need to integrate with existing systems, mobile apps, or other services. This is where APIs (Application Programming Interfaces)…
-
Continue reading →: #30DaysOfLangChain – Day 23: Advanced Streamlit: Integrating RAG & File Uploads
Welcome to Day 23 of #30DaysOfLangChain – LangChain 0.3 Edition! Yesterday, we built a simple chat interface with Streamlit. While a great start, the real power of Generative AI often lies in its ability to interact with your specific, private data. Today, we’re taking our Streamlit skills to the next…
-
Continue reading →: #30DaysOfLangChain – Day 22: Building Interactive GenAI Apps with Streamlit (Chat Interface)
Welcome to Day 22 of #30DaysOfLangChain – LangChain 0.3 Edition! We’ve spent the last few weeks building sophisticated AI agents and workflows. But what good are these powerful tools if users can’t interact with them easily? Today, we pivot from backend logic to frontend experience, learning how to create intuitive,…
-
Continue reading →: #30DaysOfLangChain – Day 21: Integrating Local Models for Cost-Effective LangGraph Applications
Welcome to Day 21 of #30DaysOfLangChain – LangChain 0.3 Edition! So far, many of our sophisticated LangGraph agents have relied on cloud-hosted LLMs like OpenAI’s GPT models. While incredibly powerful, these come with per-token costs and send your data to external servers, which can be a concern for privacy and…
Hello,
I’m Arpan
I’m a Software Engineer driven by curiosity and a deep interest in Generative AI Technologies. I believe we’re standing at the frontier of a new era—where machines not only learn but create, and I’m excited to explore what’s possible at this intersection of intelligence and imagination.
When I’m not writing code or experimenting with new AI models, you’ll probably find me travelling, soaking in new cultures, or reading a book that challenges how I think. I thrive on new ideas—especially ones that can be turned into meaningful, impactful projects. If it’s bold, innovative, and GenAI-related, I’m all in.
“The future belongs to those who believe in the beauty of their dreams.” – Eleanor Roosevelt
“Imagination is more important than knowledge. For knowledge is limited, whereas imagination embraces the entire world.” – Albert Einstein
This blog, MLVector, is my space to share technical insights, project breakdowns, and explorations in GenAI—from the models shaping tomorrow to the code powering today.
Let’s build the future, one vector at a time.
ML Vector 