Blog Posts

In this blog, you'll explore how to design a robust and secure agent framework for interacting with LLMs and users. The code demonstrates integrating tools like Google Search, Wikipedia, and a calculator with advanced safety layers for moderation and compliance. This approach ensures the agent can reason, respond accurately, and adhere to ethical guidelines while preventing unsafe or malicious inputs and outputs. It integrates safeguards like content filtering, jailbreak detection, and contextual input moderation while maintaining the functionality of a dynamic ReAct agent.

In this post you will learn how to do investment analysis with a multi-agent-setup. For this, you will be using the following tools and will also learn the following:  Exa, after account login, get your API key here. To find the exact content you're looking for on the web using embeddings-based search. SerpApi here, after account login, get your API key to do look for existing patents. Python REPL, please note that Python REPL can execute arbitrary code on the host machine (e.g., delete files, make network requests). Use with caution. Tools to access and write to a .txt file and create a plot of historical prices. How to define utilities to help create the graph. How to create a team supervisor and the team of agents.

In this post, you explore how to build an interactive response model with structured outputs using OpenAI or Nebius API. With just Pydantic and Instructor—no LlamaIndex or LangChain needed—you’ll see how easy it can be to generate clean, structured responses for improved readability and reasoning transparency.

This post shows a memory-efficient approach to generating high-quality images using the PixArt-Σ model, a state-of-the-art diffusion transformer for ultra-high-resolution image synthesis.

In this post, you’ll learn how to build a Market Research Team and use essential tools like Taviliy, Exa, and SerpAPI. LangGraph will be your framework for integrating these tools effectively.