test1

README.md

@@ -11,11 +11,9 @@ pinned: false
 
 LlamaIndex delivers the world’s most accurate agentic OCR and document-specific AI workflows, powering complete enterprise automation.
 
-On HuggingFace and in our open-source repos, we are pushing forward document parsing, OCR, and extraction with several projects:
+On HuggingFace and in our open-source repos, we are pushing forward document parsing and OCR with several projects:
 
 - [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) -- A comprehensive dataset for evaluating document parsing pipelines and OCR models
-- [ExtractBench](https://huggingface.co/datasets/llamaindex/ExtractBench) -- A benchmark dataset for evaluating schema-guided extraction from enterprise documents
-- [ExtractBench Pro](https://huggingface.co/datasets/llamaindex/ExtractBenchPro) -- A challenging benchmark dataset for evaluating long-tail document extraction
 - [LiteParse](https://github.com/run-llama/liteparse) -- Our lightweight, open-source document parser. Handles multiple formats, runs locally, and integrates with any OCR model
 - [Visual Document Retrieval](https://huggingface.co/collections/llamaindex/visual-document-retrieval) -- An exploration into training models purely for document screenshot retrieval
 
@@ -28,3 +26,4 @@ LlamaParse provides end-to-end document understanding with AI-powered parsing, e
 - [Classify](https://developers.llamaindex.ai/python/cloud/llamaclassify/getting_started/) -- Classify documents into a subset of classes
 - [Split](https://developers.llamaindex.ai/python/cloud/split/getting_started/) -- Split documents according to specific categories
 - [Index](https://developers.llamaindex.ai/python/cloud/llamacloud/getting_started/) -- Index and retrieve your data
+