From b2b090157952ef4a61fb3d3229e9579834a45a33 Mon Sep 17 00:00:00 2001 From: Ray Date: Sun, 19 Jul 2026 15:43:49 +0800 Subject: [PATCH] docs: note the CLI (PyPDF2) vs SDK local mode (PyMuPDF) parsing difference --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 5327af7..e9410f1 100644 --- a/README.md +++ b/README.md @@ -205,7 +205,7 @@ Omitting `doc_ids` queries the **entire collection** and lets the agent pick whi # ⚙️ Package Usage -> **Note:** This package uses standard PDF parsing. For use cases with complex PDFs, our [cloud service](https://pageindex.ai/developer) (via MCP and API) offers enhanced OCR, tree building, and retrieval. +> **Note:** This package uses standard PDF parsing. The CLI parses PDFs with PyPDF2 (as in previous releases), while the SDK's local mode parses with PyMuPDF and also extracts images — extracted text can differ slightly, so the two entry points may produce different trees for the same PDF. For use cases with complex PDFs, our [cloud service](https://pageindex.ai/developer) (via MCP and API) offers enhanced OCR, tree building, and retrieval. You can follow these steps to generate a PageIndex tree from a PDF document.