GenAI

Relerance feedback: from ancient history to LLMs Why relevance feedback techniques are good on paper but not popular in neural search and what we can do about it

Contribute to labdmitriy/llm-rag development by creating an account on GitHub.

GraphRAG is a powerful retrieval mechanism that improves Generative AI applications by taking advantage of the rich context in graph data structures.

Learn about the Query Agent, our new agentic search service that redefines how you interact with Weaviate’s database!

Late interaction allow for semantically rich interactions that enable a precise retrieval process across different modalities of unstructured data, including text and images.

Run a remote MCP server on Azure functions.

Azure API Management as AI Gateway to Remote MCP servers. - Azure-Samples/remote-mcp-apim-functions-python

Learn about the built-in authentication and authorization support in Azure App Service and Azure Functions, and how it can help secure your app.

Contribute to Azure-Samples/remote-mcp-functions-python development by creating an account on GitHub.

How do we create LLMs that can reason? Exploring Test-Time Compute Techniques and DeepSeek-R1.

A blog post for developers, describing a new method for complex tool-use situations

We have discovered a critical vulnerability in the Model Context Protocol (MCP) that allows for

Understanding multi-agent handoffs Handoffs are a central concept in multi-agent systems. LangGraph swarm is built on them. But, they can be hard to understand. Here, we break-down the swarm handoff mechanism. 📽️: https://t.co/YkSCFeg9A8

Document Index System for Reasoning-Based RAG

Discover how to build a knowledge graph in 7 simple steps, from defining your use case to creating a model to ingesting your data.

Enterprise-grade security, privacy, with features like agents, MCP, prompt templates, and more.

Extend your agent's capabilities with Model Context Protocol servers.

Given the widespread adoption and usage of Large Language Models (LLMs), it is crucial to have flexible and interpretable evaluations of their instruction-following ability. Preference judgments between model outputs have become the de facto evaluation standard, despite distilling complex, multi-faceted preferences into a single ranking. Furthermore, as human annotation is slow and costly, LLMs are increasingly used to make these judgments, at the expense of reliability and interpretability. In this work, we propose TICK (Targeted Instruct-evaluation with ChecKlists), a fully automated, interpretable evaluation protocol that structures evaluations with LLM-generated, instruction-specific checklists. We first show that, given an instruction, LLMs can reliably produce high-quality, tailored evaluation checklists that decompose the instruction into a series of YES/NO questions. Each question asks whether a candidate response meets a specific requirement of the instruction. We demonstrate that using TICK leads to a significant increase (46.4% $\to$ 52.2%) in the frequency of exact agreements between LLM judgements and human preferences, as compared to having an LLM directly score an output. We then show that STICK (Self-TICK) can be used to improve generation quality across multiple benchmarks via self-refinement and Best-of-N selection. STICK self-refinement on LiveBench reasoning tasks leads to an absolute gain of $+$7.8%, whilst Best-of-N selection with STICK attains $+$6.3% absolute improvement on the real-world instruction dataset, WildBench. In light of this, structured, multi-faceted self-improvement is shown to be a promising way to further advance LLM capabilities. Finally, by providing LLM-generated checklists to human evaluators tasked with directly scoring LLM responses to WildBench instructions, we notably increase inter-annotator agreement (0.194 $\to$ 0.256).

The Model Context Protocol gives users a wide range of services they can connect to from the comfort of their AI client.

Discover how the Model Context Protocol (MCP) simplifies building AI applications by seamlessly integrating Anthropic Claude with Docker Desktop, enhancing developer productivity and workflow efficiency.

Connecting Claude Desktop to Your Documentation Through MCP and Qdrant

Model-Agnostic MCP Library for LLMs

It's MCP week apparently! Yesterday we showed you how to use LlamaCloud as an MCP server, today see how to use LlamaIndex as a client to any MCP…

RAG 2.0 is really about grounding general purpose agents in proprietary enterprise context. Instead of simply one-shot answering a simple question, the agent…

We introduce THINK-AND-EXECUTE, a framework that performs reasoning with a pseudocode that contains the common logical structure of a given task.

Model Context Protocol Servers

Model Context Protocol (MCP) is actually a concept that is a few months old, but getting so hot...