Update app.py

app.py

@@ -216,22 +216,23 @@ def answer_question(images, question):
 
 
 with gr.Blocks() as app:
-    gr.Markdown("# Memex: OCR-free Visual Document Embedding Model as Your Personal Librarian")
-    gr.Markdown("""The model only takes images as document-side inputs and produce vectors representing document pages. Memex is trained with over 200k query-visual document pairs, including textual document, visual document, arxiv figures, plots, charts, industry documents, textbooks, ebooks, and openly-available PDFs, etc. Its performance is on a par with our ablation text embedding model on text-oriented documents, and an advantages on visually-intensive documents.
-
-Our model is capable of:
+    gr.Markdown("# MiniCPMV-RAG-PDFQA: Two Vision Language Models Enable End-to-End RAG")
+    
+    gr.Markdown("""
+- A Vision Language Model Dense Retriever ([MiniCPM-Visual-Embedding](https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0)) **directly reads** your PDFs **without need of OCR**, produce **multimodal dense representations** and build your personal library. 
 
-- Help you read a long visually-intensive or text-oriented PDF document and find the pages that answer your question.
+- **Ask a question**, it retrieve most relavant pages, then [MiniCPM-V-2.6](https://huggingface.co/spaces/openbmb/MiniCPM-V-2_6) will answer your question based on pages recalled, with strong multi-image understanding capability. 
 
-- Help you build a personal library and retireve book pages from a large collection of books.
+1. It helps you read a long **visually-intensive** or **text-oriented** PDF document and find the pages that answer your question.
 
-- It works like human: read and comprehend with vision and remember multimodal information in hippocampus.""")
+2. It helps you build a personal library and retireve book pages from a large collection of books.
 
-    gr.Markdown("- Our model is proudly based on MiniCPM-V series [MiniCPM-V-2.6](https://huggingface.co/openbmb/MiniCPM-V-2_6) [MiniCPM-V-2](https://huggingface.co/openbmb/MiniCPM-V-2).")
+3. It works like a human: read, store, retrieve, and answer with full vision.
+""")
     
-    gr.Markdown("- We open-sourced our model at [RhapsodyAI/minicpm-visual-embedding-v0](https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0)")
+    gr.Markdown("- We **open-sourced** our visual embedding model at [RhapsodyAI/minicpm-visual-embedding-v0](https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0)")
     
-    gr.Markdown("- Currently we support PDF document with less than 50 pages, PDF over 50 pages will reach GPU time limit.")
+    gr.Markdown("- Currently online demo support PDF document with less than 50 pages.")
     
     with gr.Row():
         file_input = gr.File(type="binary", label="Upload PDF")