This tutorial demonstrates how to integrate Google’s Gemini 2.0 with an in-process Model Context Protocol (MCP) server using FastMCP, creating tools for weather information and integrating them into Gemini's function calling workflow.
This article provides a hands-on guide to Anthropic’s Model Context Protocol (MCP), an open protocol designed to standardize connections between AI systems and data sources. It covers how to set up and use MCP with Claude Desktop and Open WebUI, along with potential challenges and future developments.
This article details the author's insights into AI function calling, its challenges, and the Agentica framework developed to address them, emphasizing the importance of JSON schema understanding, compiler support, and a document-driven approach.
This article details a comparison between Model Context Protocol (MCP) and Function Calling, two methods for integrating Large Language Models (LLMs) with external systems. It covers their architectures, security models, scalability, and suitable use cases, highlighting the strengths and weaknesses of each approach.
MCP is best suited for robust, complex applications within secure enterprise environments, while Function Calling excels in straightforward, dynamic task execution scenarios. The choice depends on the specific needs, security requirements, scalability needs, and resource availability of the project.
MCP is best suited for robust, complex applications within secure enterprise environments, while Function Calling excels in straightforward, dynamic task execution scenarios. The choice depends on the specific needs, security requirements, scalability needs, and resource availability of the project.
This article discusses using entropy and variance of entropy (VarEntropy) to detect hallucinations in LLM function calling, focusing on how structured outputs allow for identifying errors through statistical anomalies in token confidence.
The author discusses the development of a function calling large language model (LLM) that significantly improves latency for agentic applications. This LLM matches or even exceeds the performance of other frontier LLMs. It is integrated into an open-source intelligent gateway for agentic applications, allowing developers to focus on more differentiated aspects of their projects. The model and the gateway are available on Hugging Face and GitHub, respectively.
Notebook detailing the use of RAG (Retrieval-Augmented Generation) via function calling.
MCP is an open-source standard that enhances interaction between AI systems and various data sources, improving usability, response quality, and security.
TinyAgent is designed to enable complex reasoning and function calling capabilities in Small Language Models (SLMs) for secure and private edge deployment. It interacts with MacOS applications for tasks like composing emails, scheduling events, and organizing meetings.
Composio equip's your AI agents & LLMs with 100+ high-quality integrations via function calling
