Agents
We got extremely good at extracting a scanned from layer by layer š - from printed fields, overlaid text, handwriting, and reviewer annotatā¦
We got extremely good at extracting a scanned from layer by layer š - from printed fields, overlaid text, handwriting, and reviewer annotations. For instance, on an annotated permit, our Extract agent
We got extremely good at extracting a scanned from layer by layer š - from printed fields, overlaid text, handwriting, and reviewer annotations. For instance, on an annotated permit, our Extract agents can extract out both the original permit number but also any drawn/handwritten annotations on top. they're also grounded exactly in the source text. our agents reduce error rates by 2x+, at a small fraction of the price compared to using a frontier model. Our Extract v2.5 agents are SOTA in price/performance, and scanned forms are just one example. Come check it out! Extract v2.5: https://www.llamaindex.ai/blog/introducing-extract-v2-5 Available in LlamaParse: https://cloud.llamaindex.ai/ Media Today weāre introducing Extract v2.5 - a series of frontier agents tuned for document extraction. The agents (cost-effective, agentic, agentic plus) are tuned for value accuracy and grounding. Our extraction agents outperform Opus 5.5 and GPT-6 Sol while being 30%-4x cheaper. Weāā¦
Related
- Today weāre introducing Extract v2.5 - a series of frontier agents tuned for document extraction. The agents (cost-effective, agentic, agentā¦
- We built revision tracking in LlamaParse āļø You can now extract Word-style tracked changes and reviewer comments as additional structured meā¦
- Document extraction just got a new gear. ā”ļø Introducing Turbo mode for Extract, our fastest way yet to pull structured data from documents. ā¦
- We've built a new feature in LlamaParse that lets you automatically extract any complex form into a structured JSON output šš¤ The best parā¦
Source: Jerry Liu (X) | 2026-10-04