From 4236d81cfcc8603de3446fe5f532cfe09dc23e6c Mon Sep 17 00:00:00 2001 From: lei Date: Wed, 19 Mar 2025 18:04:03 +0800 Subject: [PATCH] Docs: Update accelerate_doc_indexing.mdx (#6268) ### What problem does this PR solve? The word is written incorrectly ### Type of change - [x] Documentation Update --- docs/guides/dataset/accelerate_doc_indexing.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/guides/dataset/accelerate_doc_indexing.mdx b/docs/guides/dataset/accelerate_doc_indexing.mdx index 05fb473bd..84212bb6c 100644 --- a/docs/guides/dataset/accelerate_doc_indexing.mdx +++ b/docs/guides/dataset/accelerate_doc_indexing.mdx @@ -15,5 +15,5 @@ Please note that some of your settings may consume a significant amount of time. - Use GPU to reduce embedding time. - On the configuration page of your knowledge base, switch off **Use RAPTOR to enhance retrieval**. - Extracting knowledge graph (GraphRAG) is time-consuming. -- Disable **Auto-keyword** and **Auto-question** on the configuration page of yor knowledge base, as both depend on the LLM. -- **v0.17.0+:** If your document is plain text PDF and does not require GPU-intensive processes like OCR (Optical Character Recognition), TSR (Table Structure Recognition), or DLA (Document Layout Analysis), you can choose **Naive** over **DeepDoc** or other time-consuming large model options in the **Document parser** dropdown. This will substantially reduce document parsing time. \ No newline at end of file +- Disable **Auto-keyword** and **Auto-question** on the configuration page of your knowledge base, as both depend on the LLM. +- **v0.17.0+:** If your document is plain text PDF and does not require GPU-intensive processes like OCR (Optical Character Recognition), TSR (Table Structure Recognition), or DLA (Document Layout Analysis), you can choose **Naive** over **DeepDoc** or other time-consuming large model options in the **Document parser** dropdown. This will substantially reduce document parsing time.