Web Support

app.py

@@ -9,7 +9,7 @@ import gradio as gr
 
 import torch
 from docquery import pipeline
-from docquery.document import load_bytes, load_document, ImageDocument
+from docquery.document import load_document, ImageDocument
 from docquery.ocr_reader import get_ocr_reader
 
 
@@ -84,10 +84,20 @@ examples = [
         "statement.png",
         "What are net sales for 2020?",
     ],
+    [
+        "docquery.png",
+        "How many likes does the space have?",
+    ],
+    [
+        "hacker_news.png",
+        "What is the title of post number 5?",
+    ],
 ]
 
 question_files = {
     "What are net sales for 2020?": "statement.pdf",
+    "How many likes does the space have?": "https://huggingface.co/spaces/impira/docquery",
+    "What is the title of post number 5?": "https://news.ycombinator.com",
 }
 
 

packages.txt

@@ -1,2 +1,4 @@
 poppler-utils
 tesseract-ocr
+chromium
+chromium-driver

requirements.txt

@@ -1,4 +1,3 @@
 torch
 git+https://github.com/huggingface/transformers.git@21f6f58721dd9154357576be6de54eefef1f1818
-git+https://github.com/impira/docquery.git@8d92692c36f63ef652f3c84cccedd5674ee7b383
-sentencepiece
+git+https://github.com/impira/docquery.git@a494fe5af452d20011da75637aa82d246a869fa0#egg=docquery[web,donut]