The LlamaParse Platform community node (v5 and v6) is now an officially verified n8n community node. It exposes five LlamaCloud resources (Parse, Classify, Split, Extract, Retrieve) that can be used as tools in n8n AI Agents. v5 rewrote the foundation with direct HTTP calls and configurable API base URL. v6 consolidated multiple nodes into one and added index actions. The post presents three example workflows: retrievers as agent tools, a classify-extract-verify pipeline, and evaluating parsed outputs across different parsing modes.
LlamaParse Platform node provides five resources: Parse, Classify, Split, Extract, and Retrieve, all usable as AI Agent tools.
v5 replaced the SDK with direct HTTP calls, migrated Extract to V2, and made the API base URL configurable.
LiteParse v2.1 introduces the fastest open-source, model-free PDF-to-markdown pipeline, achieving top scores on three benchmarks and offering speed and portability across multiple runtimes.
LiteParse 2.1 delivers heuristic PDF-to-markdown without AI models.
Leads in overall scores on ParseBench, opendataloader-bench, and olmOCR-bench.
This article details how the authors improved their LiteParse document parsing skill for Claude agents through iterative evaluation, trace analysis, and optimization, achieving a 37% cost reduction and higher answer quality. Key anti-patterns like re-parsing, unnecessary OCR, and excessive grep turns were identified and fixed.
Using the pdfQA benchmark and trace analysis, the team systematically optimized the LiteParse skill, addressing anti-patterns such as repeated parsing, OCR misuse, and excessive grep calls.
Hard rules like parse-once and no-OCR, combined with tools (grep, sed, BM25 retriever), reduced cache write costs by over 3x.
Major updates include ParseBench at CVPR 2026, Parse-Flow for visual document intelligence, Anthropic Fable 5 benchmark results, new Granular Bounding Boxes in LlamaParse, and The Agent Open pickleball tournament.
ParseBench debuts at CVPR 2026 as the first document parsing benchmark for AI agents.
Anthropic Fable 5 achieves 90.02% content faithfulness on ParseBench, leading competitors by 12+ points.
This article explores the true meaning of PDF searchability. Quick OCR methods like Adobe Acrobat and free online tools work for clean documents but fail on tables, multi-column layouts, and poor scans. Even a 95% accurate text layer leaves errors that cause searches to miss targets. For large-scale or AI-driven processing, structured output from tools like LlamaParse is necessary to preserve reading order and table structure. True searchability depends on accuracy and structure, not just the presence of a text layer.
Quick OCR methods work for simple docs but fail on tables, columns, and low-quality scans.
A 95% accurate text layer still leaves ~150 errors per page, causing missed searches.
Organizations face significant challenges in extracting structured metadata from complex legal contracts due to variability in language, structure, and formatting. Modern systems combine layout-aware parsing, machine learning, semantic extraction, and schema mapping to transform unstructured legal agreements into machine-readable data. LlamaParse offers a structured platform integrating these capabilities for production workflows.
Contract metadata extraction goes beyond OCR, requiring understanding of legal language and document structure.
Key steps include document ingestion, layout-aware parsing, clause detection, and schema mapping.
Parse-Flow is an open-source project that combines a visual workflow designer, async worker, and live event dashboard to orchestrate document processing primitives — parsing, extraction, classification, and splitting. Built on llama-agents workflows, it uses Redis and Postgres for job queuing and event persistence, with a three-step state machine (bootstrap, worker, router) that interprets user-defined flows defined in JSON. This article details its architecture, design rationale, and the importance of robust document intelligence for enterprise AI systems.
Parse-Flow integrates parsing, extraction, classification, and splitting into a visual workflow designer with real-time event streaming.
The backend uses a LlamaAgent workflow with three steps (bootstrap, worker, router) to execute flows defined as JSON. New pipelines require no code.
This post compares grep (lexical search) and RAG (semantic search) for AI agents. Grep is fast and precise on small plain-text corpora but cannot handle unstructured documents and doesn't scale. RAG solves scalability via parsing, chunking, embedding, and vector indexing, enabling vocabulary-agnostic search. The recommended approach is layered: parse unstructured documents, use semantic search at scale, and keep grep for suitable cases.
Grep excels on small plain-text corpora for exact matching, but fails with unstructured formats and large scale.
Semantic search (RAG) overcomes scalability, recall, and noise issues via embeddings and ANN indexes.
This week's LlamaIndex newsletter highlights ParseBench, the first OCR benchmark for AI agents, along with new open-source tools: a sandboxed CLI agent for secure document interactions and a self-hostable document parsing server. Community events in Singapore and NYC are also recapped.
ParseBench is the first document OCR benchmark built specifically for AI agents, to be unveiled in a live webinar.
Sandboxed-Lit CLI Agent combines document parsing with sandboxed environments for safe interaction with PDFs, images, and Office files.
This post walks through a demo AI agent that ingests SEC filings, searches across them, and answers questions with precise citations that highlight the exact source text on the original PDF page. The key ingredient is LiteParse, which extracts text along with bounding box coordinates. The project uses a simple keyword search instead of vector databases, and integrates SEC EDGAR for direct filing retrieval.
LiteParse extracts text with bounding box coordinates enabling precise citation highlighting.
The agent uses keyword matching for search, suitable for small document sets.
Mortgage document automation leverages intelligent document processing to transform document-heavy workflows into structured, machine-driven processes, improving efficiency and reducing errors. This article examines the complexities of mortgage document handling, the automation workflow (ingestion, classification, extraction, validation, human review, and system integration), challenges, and best practices for implementation with LlamaParse.
Mortgage document processing is complex due to format variability, regulatory sensitivity, and accuracy requirements.
Intelligent document processing combines ML, computer vision, and structured parsing to convert documents into usable data.
This article examines the shortcomings of standard OCR in KYC workflows, including its inability to handle real-world identity documents with security features, varied layouts, and non-Latin scripts. It introduces agentic OCR (e.g., LlamaParse) that uses layout-aware segmentation, model orchestration, and self-correction loops to achieve over 90-95% straight-through processing, and discusses implications across banking, insurance, and crypto industries.
Standard OCR fails on real identity documents: worn edges, angled photos, holograms, and non-Latin scripts cause errors.
Field-level accuracy must reach 99.9% to avoid compliance risks; manual review fallback is costly and scales poorly.
This week's LlamaIndex newsletter highlights intelligent table extraction, LiteSearch for local document retrieval, improved Word document processing, and integrations with Gemini Live API, along with guides for legal discovery and community projects.
Intelligent table extraction advancements for complex documents.
Launch of LiteSearch, a fully local document retrieval system.
This edition introduces ParseBench, the first OCR benchmark designed for AI agents, along with LiteParse's explosive growth, structure-aware PDF QA pipeline, VLM-powered OCR production insights, NYC fintech workshop, and secure document agents.
Released ParseBench, the first OCR benchmark designed for AI agents
LiteParse reached 4K+ GitHub stars in just 3 weeks
Highlights include the launch of ParseBench, the first document OCR benchmark for AI agents; LiteParse officially joining the LlamaIndex ecosystem; comprehensive benchmarking of Anthropic's Opus 4.7; and an upcoming NYC FinTech Week AI event.
ParseBench launched: first document OCR benchmark for AI agents.
LiteParse gets official website, supports 50+ formats with zero cloud dependency.
The refactored LlamaParse Platform MCP shifts focus to document processing with Parse, Classify, and Split services. This post covers the MCP tools, connection methods, OAuth authentication, file upload solutions, observability, rate limiting, and deployment considerations.
MCP server at https://mcp.llamaindex.ai/mcp supports clients like Claude Desktop, Cursor, and GitHub Copilot. Authentication via WorkOS OAuth eliminates manual API keys.
File uploads handled via uploadFileByUrl (URL-based) and getUploadUrl (token-based temporary endpoint) to overcome MCP's lack of native file upload support.
liteparse-server is a self-hosted HTTP API wrapping the LiteParse document parsing engine, supporting PDFs, Office documents, and images with precise spatial layout text extraction and OCR. It addresses the latency, cost, and privacy concerns of cloud parsing, suitable for RAG and vision model workflows. Two deployment modes: slim (no dependencies) and full stack (with Redis caching, rate limiting, OpenTelemetry tracing, and Prometheus metrics).
Self-hosted document parsing API supporting PDFs, Word, Excel, PowerPoint, and images.
Structured text extraction with bounding boxes and page screenshot endpoints for vision models.
ParseBench is a new benchmark that measures document parsing quality for AI agents across enterprise documents, covering tables, charts, content faithfulness, semantic formatting, and visual grounding. Evaluation of 14 methods on ~2,000 pages with over 167,000 test rules shows that no single method excels everywhere, but LlamaParse Agentic achieves 84.9% overall, being the only method competitive across all five key dimensions.
ParseBench includes ~2,000 enterprise document pages and over 167,000 test rules across five capability dimensions.
Charts are the biggest challenge, with only four providers exceeding 50%.