Tool calling

Search documents
X @Avi Chawla
Avi Chawla路 2025-07-26 06:30
To recall:1) Basic responder only generate text.2) Router pattern decides when to take a path.3) Tool calling picks & runs tools.4) Multi-Agent pattern manages several agents.5) Autonomous pattern works fully independently.Here's the visual again for your reference馃憞 https://t.co/3uhj0dAgcT ...
X @Avi Chawla
Avi Chawla路 2025-07-26 06:30
3锔忊儯 Tool calling- A human defines a set of tools the LLM can access to complete a task.- LLM decides when to use them and also the arguments for execution.Check this visual馃憞 https://t.co/HlxIDYRq6t ...
Open Deep Research
LangChain路 2025-07-16 16:01
Hi there. Today you're going to learn all about the Langchain deep research agent and how you can use it as a starting point for your projects. It's highly configurable and allows you to add your own MCP servers and is open source so you can tailor it to your own specific use cases.Let's see how it works. So later this year, my roommates and I want to take a trip to Amsterdam and Norway. We want to leave New York on September 12th and get back on the following Sunday.I want to ask Deep Research if it can he ...
Kimi K2 is INSANE... (Open-Source is BACK!)
Matthew Berman路 2025-07-14 17:43
This might be the next deepseek moment. A Chinese company just released another open-source model called Kimmy K2 and it is taking the industry by storm. The reason this graph right here, this is the training loss curve, and people are so surprised by how smooth it is.Typically, you get all of these spikes in here which cause issues that you need to correct. But for Kimmy, it was almost flawless. And the especially cool thing, it is based on a trillion tokens.That is a massive model. So they came up with th ...
Context Engineering for Agents
LangChain路 2025-07-02 15:54
Hey, this is Lance from Langchain. You might have heard this term context engineering recently. It's a nice way to capture many of the different things that we do when we're building agents.Of course, agents need context. They need instructions. They need external knowledge.They also will use feedback from tool calls. Context engineering is just the art and science of filling the context window with just the right information at each step of the agent's trajectory. Now I want to talk about a few different s ...