Spaces:
Runtime error
Runtime error
hahahahahahahah3
commited on
Commit
•
74aff4c
1
Parent(s):
8288223
Update app.py
Browse files
app.py
CHANGED
@@ -1,3 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
import tqdm
|
2 |
from PIL import Image
|
3 |
import hashlib
|
@@ -209,13 +219,9 @@ with gr.Blocks() as app:
|
|
209 |
|
210 |
gr.Markdown("""
|
211 |
- A Vision Language Model Dense Retriever ([minicpm-visual-embedding-v0](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.
|
212 |
-
|
213 |
- **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.
|
214 |
-
|
215 |
- It helps you read a long **visually-intensive** or **text-oriented** PDF document and find the pages that answer your question.
|
216 |
-
|
217 |
- It helps you build a personal library and retireve book pages from a large collection of books.
|
218 |
-
|
219 |
- It works like a human: read, store, retrieve, and answer with full vision.
|
220 |
""")
|
221 |
|
|
|
1 |
+
#!/usr/bin/env python
|
2 |
+
# -*- coding: utf-8 -*-
|
3 |
+
#
|
4 |
+
# Copyright @2023 RhapsodyAI, ModelBest Inc. (modelbest.cn)
|
5 |
+
#
|
6 |
+
# @author: bokai xu <bokesyo2000@gmail.com>
|
7 |
+
# @date: 2024/07/13
|
8 |
+
#
|
9 |
+
|
10 |
+
|
11 |
import tqdm
|
12 |
from PIL import Image
|
13 |
import hashlib
|
|
|
219 |
|
220 |
gr.Markdown("""
|
221 |
- A Vision Language Model Dense Retriever ([minicpm-visual-embedding-v0](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.
|
|
|
222 |
- **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.
|
|
|
223 |
- It helps you read a long **visually-intensive** or **text-oriented** PDF document and find the pages that answer your question.
|
|
|
224 |
- It helps you build a personal library and retireve book pages from a large collection of books.
|
|
|
225 |
- It works like a human: read, store, retrieve, and answer with full vision.
|
226 |
""")
|
227 |
|