PageIndex Blog

Introducing PageIndex Flash

PageIndex Flash runs entirely on your own machine and is designed for text-based PDFs. It builds a hierarchical tree index from a PDF's own layout, indexing a 1,000-page document in minutes for about a dollar.

PageIndex File System: Massive-Scale Document Search

PageIndex File System is a file-level tree layer that sits above your documents and scales the same PageIndex tree search from a single document to millions of documents in one index.

PageIndex Featured on The Open-Source Growth Index (OSSCAR)

PageIndex was recognized on the Open Source Growth Index (OSSCAR) Q1 2026 by Supabase × Commit VC, ranking #14 in GitHub Star Growth and #38 Overall in the Scaling Tier.

OpenKB: An Open-Source LLM Knowledge Base

We built what Andrej Karpathy described, and solved the hard part. OpenKB is an open-source CLI that compiles raw documents into a structured, interlinked wiki, powered by PageIndex for long PDFs.

PageIndex Selected for GitHub Secure Open Source Fund

PageIndex has been selected for GitHub's Secure Open Source Fund, supporting a broader security roadmap for long-document AI infrastructure.

Context Blindness: A Fundamental Limitation of Vector RAG

We argue that context blindness — the inability of vector-based retrieval to condition on full conversational and reasoning context — is a fundamental limitation of vector RAG, and outline a paradigm shift from semantic similarity to context-dependent relevance classification.

PageIndex Featured in VentureBeat: A Tree Search Framework That Hits 98.7% Where Vector Search Fails

VentureBeat covers PageIndex, the vectorless, reasoning-based RAG framework that uses tree search over document structure to reach 98.7% accuracy on FinanceBench, where vector-based retrieval typically fails.

PageIndex Hit #1 GitHub Trending

RAG for Technical Manuals

How PageIndex’s vectorless, reasoning-based RAG overcomes the challenges of traditional vector RAG in long, complex technical manuals.

PageIndex vs ChatGPT 5.1

We benchmarked PageIndex Chat against ChatGPT 5.1 on real-world long documents. PageIndex achieved 100% accuracy compared to ChatGPT 5.1's 59-82%, with faster response times and page-level traceability.

Do We Still Need OCR?

We examine the inherent limitations of OCR from an information-theoretic perspective and show why a direct, vision-based approach with PageIndex is more effective.

Introducing PageIndex Chat

Experience the power of reasoning-based RAG with PageIndex Chat - our new conversational interface for intelligent document understanding.

PageIndex: Next-Generation Vectorless, Reasoning-based RAG

PageIndex is a vectorless, reasoning-based retrieval framework that simulates how human experts extract knowledge from complex documents. Instead of relying on vector similarity search, it builds a tree-structured index from documents and enables LLMs to perform agentic reasoning over that…

From Claude Code to Agentic RAG

The same bet behind both PageIndex and Claude Code: skip the vector DB and let the LLM itself drive retrieval. We explore the rise of agentic retrieval over vector indexing and PageIndex's agentic, vectorless RAG framework.

PageIndex Leads Financial QA Benchmark

We introduce Mafin2.5, which is built based on PageIndex, with a 98.7% accuracy rate on the finance industry question-answering benchmark.

Enhancing Black-Box Embeddings with Model Augmented Fine-Tuning

We introduce Model Augmented Fine-tuning (Mafin) — a novel approach for fine-tuning a black-box embedding model by augmenting it with a trainable embedding model.

Active Preference Learning for Large Language Models

We propose a practical acquisition function for prompt/completion pairs based on the predictive entropy of the language model and a measure of certainty of the implicit preference model optimized by DPO.