LlamaIndex ‘legal-kb’: Agentic Retrieval over Index v2 with retrieve, find, read, and grep Tools
LlamaIndex has published legal-kb, a public reference application on GitHub. It is described as a knowledge base for legal documents, powered by LlamaIndex Index v2 (the LlamaParse Platform). The project demonstrates a pattern the team calls a Retrieval Harness for agentic retrieval. The approach differs from single-shot retrieval. Instead of one embedding search per query, an agent is given filesystem-style tools. It can then crawl a large, evolving knowledge base to solve a task. The tools
Get smart on it
LlamaIndex has released legal-kb, a web application that demonstrates a new approach to searching through document collections using AI agents. Instead of traditional single-step searches, the system gives agents multiple tools that work like filesystem operations: they can list files, search semantically or by keyword, grep for specific text patterns, and read file contents. This multi-step approach allows agents to navigate large, evolving knowledge bases more precisely, with visible citations showing exactly where answers came from in source documents. The design is particularly suited for domains like legal and financial work where users need to search through many documents and verify specific information with exact page references.
Related news
Structured PDF-to-JSON: A Guide to Open-Source Extraction Models in 2026
Most enterprise data still sits inside PDFs, scans, and slide decks. Large language models and agents cannot use that data until it becomes structured JSON. Open-source document extraction has become the standard way to do that conversion on your own hardware. Two different problems hide under the phrase ‘PDF to JSON.’ The first is schema-driven extraction: you define fields, and a model fills them with values. The second is document parsing: a model reconstructs the page into st
Qwen’s Former Lead on What Hybrid Thinking Got Wrong — and Why He Now Backs Agents
Junyang Lin was the technical lead of Alibaba’s Qwen project. He announced he was stepping down on March 3, 2026. He now lists himself as an independent researcher on his personal site. In a talk titled ‘Qwen: Towards a Generalist Model / Agent,‘ he walks through the Qwen family. It ends on a single line: “Training models -> training agents.” He later expanded that line into an detailed post as an independent researcher. This article reads the talk and the detai
