Charts tab

app.py

@@ -9,6 +9,11 @@ from langchain.embeddings import OpenAIEmbeddings
 from langchain.vectorstores import Chroma
 from langchain.chains import ConversationalRetrievalChain
 from langchain import PromptTemplate
+from transformers import Pix2StructForConditionalGeneration, Pix2StructProcessor
+import requests
+from PIL import Image
+import torch
+
 
 
 # _template = """Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.
@@ -28,6 +33,26 @@ from langchain import PromptTemplate
 # =========
 # Answer in Markdown:"""
 
+torch.hub.download_url_to_file('https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/val/png/20294671002019.png', 'chart_example.png')
+torch.hub.download_url_to_file('https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/test/png/multi_col_1081.png', 'chart_example_2.png')
+torch.hub.download_url_to_file('https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/test/png/18143564004789.png', 'chart_example_3.png')
+torch.hub.download_url_to_file('https://sharkcoder.com/files/article/matplotlib-bar-plot.png', 'chart_example_4.png')
+
+
+model_name = "google/matcha-chartqa"
+model = Pix2StructForConditionalGeneration.from_pretrained(model_name)
+processor = Pix2StructProcessor.from_pretrained(model_name)
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+def filter_output(output):
+    return output.replace("<0x0A>", "")
+
+def chart_qa(image, question):
+    inputs = processor(images=image, text=question, return_tensors="pt").to(device)
+    predictions = model.generate(**inputs, max_new_tokens=512)
+    return filter_output(processor.decode(predictions[0], skip_special_tokens=True))
+
 def loading_pdf():
     return "Loading..."
 
@@ -169,11 +194,10 @@ def respond(message, chat_history):
     return "", chat_history
 
 
-
 with gr.Blocks() as demo:
     with gr.Column(elem_id="col-container"):
         gr.HTML(title)
-        openai_key = gr.Textbox(
+        key = gr.Textbox(
                 show_label=False,
                 placeholder="Your OpenAI key",
                 type = 'password',
@@ -209,7 +233,7 @@ with gr.Blocks() as demo:
                 clr_btn = gr.Button("Clear!")
                 
     load_pdf.click(loading_pdf, None, langchain_status, queue=False)    
-    load_pdf.click(pdf_changes, inputs=[pdf_doc, openai_key], outputs=[langchain_status], queue=True)
+    load_pdf.click(pdf_changes, inputs=[pdf_doc, key], outputs=[langchain_status], queue=True)
     question.submit(add_text, [chatbot, question], [chatbot, question]).then(
         bot, chatbot, chatbot
     )
@@ -244,16 +268,20 @@ with gr.Blocks() as demo:
                 clr_btn = gr.Button("Clear!")
             
     load_table.click(load_file, None, status_sh, queue=False)    
-    load_table.click(table_loader, inputs=[raw_table, openai_key], outputs=[status_sh], queue=False)
+    load_table.click(table_loader, inputs=[raw_table, key], outputs=[status_sh], queue=False)
    
     question_sh.submit(respond, [question_sh, chatbot_sh], [question_sh, chatbot_sh])
     clr_btn.click(lambda: None, None, chatbot_sh, queue=False)
     
-                
+
     with gr.Tab("Charts"):
-        gr.Text('Soon!')
-        
-        
+            image = gr.Image(type="pil", label="Chart")
+            question = gr.Textbox(label="Question")
+            load_chart = gr.Button("Load chart and question!")
+            answer = gr.Textbox(label="Model Output")
+            
+    load_chart.click(chart_qa, [image, question], answer)
+
         
 demo.queue(concurrency_count=3)
 demo.launch()