From 981c8701d4a430ed76a8cd076065fd7cd18de93c Mon Sep 17 00:00:00 2001 From: chengke <404835780@qq.com> Date: Fri, 15 May 2026 21:51:45 +0800 Subject: [PATCH 1/2] docs: move positioning statement to after benchmark chart --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 0f3429367..93b633a74 100644 --- a/README.md +++ b/README.md @@ -33,8 +33,6 @@ ## What We Are -**We're not developing the next MinerU, instead, we're building document memory infrastructure that agents can effectively consume.** - Knowhere turns unstructured documents into persistent, navigable memory for AI agents. It handles parsing, hierarchy extraction, multi-modal structuring, and graph construction, giving your agents structured, high-quality context for *Agentic RAG*, *traditional RAG*, or any LLM workflow. > [!TIP] @@ -85,6 +83,8 @@ Knowhere enhances the accuracy of AI agents when performing tasks (e.g., searchi Benchmark Performance: Agent + Knowhere vs Others

+> **We're not developing the next MinerU — we're building document memory infrastructure that agents can effectively consume.** + ### Key Advantages - **Superior Accuracy**: Knowhere drastically improves both **First-time Accuracy** (+36% over raw docs) and **Recall** (+10%), ensuring agents find the right evidence faster. From 27b11266cd68b3c0dfcfed39bb9fc390528a2491 Mon Sep 17 00:00:00 2001 From: chengke <404835780@qq.com> Date: Fri, 15 May 2026 21:57:12 +0800 Subject: [PATCH 2/2] docs: refine What We Are text --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 93b633a74..4a1bc3dca 100644 --- a/README.md +++ b/README.md @@ -33,7 +33,7 @@ ## What We Are -Knowhere turns unstructured documents into persistent, navigable memory for AI agents. It handles parsing, hierarchy extraction, multi-modal structuring, and graph construction, giving your agents structured, high-quality context for *Agentic RAG*, *traditional RAG*, or any LLM workflow. +Knowhere turns unstructured documents into persistent, navigable memory for AI agents. It handles parsing, hierarchy identification, multi-modal extraction and labeling, and graph construction, giving your agents structured, high-quality context for information retrieval or any LLM workflow. > [!TIP] > Knowhere stands on the shoulders of giants like MinerU and Pymupdf. We take their output, optimize it, and then build **hierarchical structure** and **multi-modal cross-document graphs** on top. The result is a persistent, citable memory layer purpose-built for agent consumption.