diff --git a/README.md b/README.md index 4d70a18..e797a01 100644 --- a/README.md +++ b/README.md @@ -75,10 +75,15 @@ PageIndex powers a reasoning-based RAG system that achieved [98.7% accuracy](htt - Experiment with the [*Vision-based Vectorless RAG*](https://github.com/VectifyAI/PageIndex/blob/main/cookbook/vision_RAG_pageindex.ipynb) — no OCR; a minimal, reasoning-native RAG pipeline that works directly over page images.

- - Open in Colab +

+ + Open in Colab: Vectorless RAG -

+    + + Open in Colab: Vision RAG + +
--- @@ -188,13 +193,13 @@ To address this, we introduced PageIndex OCR — the first long-context OCR mode --- --> -# 📈 Case Study: Mafin 2.5 on FinanceBench +# 📈 Case Study: SOTA on Finance QA Benchmark -[Mafin 2.5](https://vectify.ai/mafin) is a state-of-the-art reasoning-based RAG model designed specifically for financial document analysis. Powered by **PageIndex**, it achieved a market-leading [**98.7% accuracy**](https://vectify.ai/blog/Mafin2.5) on the [FinanceBench](https://arxiv.org/abs/2311.11944) benchmark — significantly outperforming traditional vector-based RAG systems. +[Mafin 2.5](https://vectify.ai/mafin) is a reasoing-based RAG system for financial document analysis, powered by **PageIndex**. It achieved a state-of-the-art [**98.7% accuracy**](https://vectify.ai/blog/Mafin2.5) on the [FinanceBench](https://arxiv.org/abs/2311.11944) benchmark — significantly outperforming traditional vector-based RAG systems. PageIndex's hierarchical indexing enabled precise navigation and extraction of relevant content from complex financial reports, such as SEC filings and earnings disclosures. -👉 See the full [benchmark results](https://github.com/VectifyAI/Mafin2.5-FinanceBench) and our [blog post](https://vectify.ai/blog/Mafin2.5) for detailed comparisons and performance metrics. +👉 Explore the full [benchmark results](https://github.com/VectifyAI/Mafin2.5-FinanceBench) and our [blog post](https://vectify.ai/blog/Mafin2.5) for detailed comparisons and performance metrics.