Rohit Gupta's contributions

Learn how to build a private, high-performance local AI assistant using Ollama and LangChain. This guide covers installation, setup, prompt orchestration, and integration with local data.

Learn advanced methods to implement and optimize semantic search using embeddings in Python. Covers model selection, vector databases, and hybrid retrieval systems.

Explore how LangChain’s Deep Research framework automates complex research workflows using multi-agent reasoning, retrieval, and synthesis — a game-changer for AI-driven insight generation.

Explore the “Stock Research Agent v3” from LangChain—a multi-agent, deep-research AI system built with LangGraph and LangSmith for advanced financial research. Understand architecture, capabilities, use-cases, limitations, and how you can apply it.

Explore Tokencrush for LangGraph and how tools like LLMCostOptimizer.com redefine enterprise LLM efficiency through deep cost analytics, optimization, and ROI-driven AI strategy.

Learn prompt engineering fundamentals tailored for Python developers. Includes examples, best practices, and 50 ready-to-use prompts for AI-assisted coding.

Learn how to integrate Large Language Models (LLMs) like GPT, Claude, or Mistral into a FastAPI backend. Covers architecture, prompt management, caching, and deployment.

Build, evaluate, and deploy a production-ready Retrieval-Augmented Generation (RAG) system in Python using FAISS, Pinecone, LangChain, and FastAPI. Includes code, Dockerfile, diagrams, and an evaluation workflow.

Learn how to use LangChain tools in Python to build advanced LLM workflows, integrate APIs, and automate reasoning pipelines with code examples and best practices.

Learn how to build a production-ready chatbot using Python, LangChain, and OpenAI in this step-by-step developer guide. Includes architecture, code examples, and deployment best practices.

Learn how LangRepl enables developers to build interactive REPL environments using Python. Understand its architecture, setup, customization options, and integration workflows.

Explore OpenAgent, a powerful open-source framework for building, orchestrating, and deploying multi-agent AI systems with modular tools, integrations, and workflows.

Explore MiniMax M2, Ollama’s latest open-source AI model built for coding and agentic automation. Learn its capabilities, benchmarks, integrations, and API setup.

Explore the v0.2 release of DeepAgents by LangChain: new pluggable backends, enhanced memory, conversation summarisation, and a decision framework on when to use DeepAgents vs LangChain vs LangGraph.

Learn how to create a fully customized chat model using LangChain, OpenAI API, and Python. Includes step-by-step implementation, architecture diagram, and optimization insights.

Explore Chatsky, the open-source Python framework for building chatbots. Learn architecture, script DSL, use-cases, limitations, deployment, and how to get started.

Learn how to create intelligent AI agents using LangChainJS and Azure’s Model Catalog with the MCP Agent sample. This detailed guide covers setup, architecture, and code examples for production-ready integrations.

Follow a detailed, step-by-step guide to create a natural-language Bash terminal agent using the open-source NVIDIA Nemotron Nano 9B v2 model. Learn prerequisites, architecture, code snippets, safety considerations, and how to extend this system for practical workflows.

OpenMemory is an open-source, self-hosted memory engine designed to add persistent, semantic, and contextual memory to AI agents and LLM applications. Learn architecture, setup, use-cases, limitations, and integration.

Learn how Vercel Agent brings AI to your development workflow—automated code reviews, production incident investigations, validated suggestions, and unified platform integration.