Update README.md

README.md

@@ -10,9 +10,9 @@ metrics:
 pipeline_tag: feature-extraction
 ---
 
-# MiniCPM-Visual-Embedding: An OCR-free Visual-Based Document Embedding Model Based on MiniCPM-V-2.0 as Your Personal Librarian
+# An OCR-free Visual-Based Document Embedding Model Based on MiniCPM-V-2.0 as Your Personal Librarian
 
-With MiniCPM-Visual-Embedding, it is possible to directly build knowledge base with raw PDF/Book/Document without any OCR technique nor OCR pipeline. The model only takes images as document-side inputs and produce vectors representing document pages. 
+With MiniCPM-Visual-Embedding, it is possible to directly build knowledge base with raw PDF/Book/Document without any OCR technique nor OCR pipeline. The model only takes images as document-side inputs and produce vectors representing document pages. minicpm-visual-embedding-v0 is trained with over 30k paired query - visual document pages, including textual document, visual document, arxiv figures, industry documents, textbooks, ebooks, etc. The performance of minicpm-visual-embedding-v0 is on a par with a text embedding on text-oriented documents, and an advantages on visually-intensive documents.
 
 [Github Repo](https://github.com/bokesyo/minicpm-visual-embedding)
 
@@ -101,4 +101,8 @@ print(scores)
 
 # tensor([[0.6506, 4.9630, 3.8614]], device='cuda:0')
 
-```
+```
+
+# Limitations
+
+Currently, please ensure that dpi of input images be a high value like `300` dpi, a lower dpi like `100` may cause the model performance degrade. We will augment data and fix this in our latest version.