Update app.py

app.py

@@ -11,6 +11,8 @@ from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_core.documents import Document
 from huggingface_hub import InferenceClient
 import logging
+import pandas as pd
+import tempfile
 
 # Set up basic configuration for logging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
@@ -41,6 +43,43 @@ Your goal is to synthesize the given context into a coherent and detailed respon
 Please ensure that your response is well-structured, factual.
 If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags."""
 
+def process_excel_file(file, model, temperature, num_calls, use_embeddings, system_prompt):
+    try:
+        df = pd.read_excel(file.name)
+        results = []
+        
+        for _, row in df.iterrows():
+            question = row['Question']
+            custom_system_prompt = row['System Prompt']
+            
+            # Use the existing get_response_with_search function
+            response_generator = get_response_with_search(question, model, num_calls, temperature, use_embeddings, custom_system_prompt)
+            
+            full_response = ""
+            for partial_response, _ in response_generator:
+                full_response = partial_response  # Keep updating with the latest response
+            
+            if not full_response:
+                full_response = "No response generated. Please check the input parameters and try again."
+            
+            results.append(full_response)
+        
+        df['Response'] = results
+        
+        # Save to a temporary file
+        with tempfile.NamedTemporaryFile(delete=False, suffix='.xlsx') as tmp:
+            df.to_excel(tmp.name, index=False)
+            return tmp.name
+    except Exception as e:
+        logging.error(f"Error processing Excel file: {str(e)}")
+        return None
+
+def upload_file(file):
+    return file.name if file else None
+
+def download_file(file_path):
+    return file_path
+
 def get_embeddings():
     return HuggingFaceEmbeddings(model_name="sentence-transformers/stsb-roberta-large")
 
@@ -199,36 +238,47 @@ def initial_conversation():
                 "To get started, ask me a question!")
     ]
 
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=True, render=False),
-    additional_inputs=[
-        gr.Dropdown(choices=MODELS, label="Select Model", value=MODELS[3]),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.2, step=0.1, label="Temperature"),
-        gr.Slider(minimum=1, maximum=5, value=1, step=1, label="Number of API Calls"),
-        gr.Checkbox(label="Use Embeddings", value=False),
-        gr.Textbox(label="System Prompt", lines=5, value=DEFAULT_SYSTEM_PROMPT),
-    ],
-    title="AI-powered Web Search Assistant",
-    description="Ask questions and get answers from web search results.",
-    theme=gr.Theme.from_hub("allenai/gradio-theme"),
-    css=css,
-    examples=[
-        ["What are the latest developments in artificial intelligence?"],
-        ["Can you explain the basics of quantum computing?"],
-        ["What are the current global economic trends?"]
-    ],
-    cache_examples=False,
-    analytics_enabled=False,
-    textbox=gr.Textbox(placeholder="Ask a question", container=False, scale=7),
-    chatbot = gr.Chatbot(  
-        show_copy_button=True,
-        likeable=True,
-        layout="bubble",
-        height=400,
-        value=initial_conversation()
+# Modify the Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# AI-powered Web Search Assistant")
+    gr.Markdown("Ask questions and get answers from web search results.")
+    
+    with gr.Row():
+        chatbot = gr.Chatbot(
+            show_copy_button=True,
+            likeable=True,
+            layout="bubble",
+            height=400,
+            value=initial_conversation()
+        )
+    
+    with gr.Row():
+        message = gr.Textbox(placeholder="Ask a question", container=False, scale=7)
+        submit_button = gr.Button("Submit")
+    
+    with gr.Accordion("⚙️ Parameters", open=False):
+        model = gr.Dropdown(choices=MODELS, label="Select Model", value=MODELS[3])
+        temperature = gr.Slider(minimum=0.1, maximum=1.0, value=0.2, step=0.1, label="Temperature")
+        num_calls = gr.Slider(minimum=1, maximum=5, value=1, step=1, label="Number of API Calls")
+        use_embeddings = gr.Checkbox(label="Use Embeddings", value=False)
+        system_prompt = gr.Textbox(label="System Prompt", lines=5, value=DEFAULT_SYSTEM_PROMPT)
+    
+    with gr.Accordion("Batch Processing", open=False):
+        excel_file = gr.File(label="Upload Excel File", file_types=[".xlsx"])
+        process_button = gr.Button("Process Excel File")
+        download_button = gr.File(label="Download Processed File")
+    
+    # Event handlers
+    submit_button.click(chatbot_interface, inputs=[message, chatbot, model, temperature, num_calls, use_embeddings, system_prompt], outputs=chatbot)
+    message.submit(chatbot_interface, inputs=[message, chatbot, model, temperature, num_calls, use_embeddings, system_prompt], outputs=chatbot)
+    
+    # Excel processing
+    excel_file.change(upload_file, inputs=[excel_file], outputs=[excel_file])
+    process_button.click(
+        process_excel_file,
+        inputs=[excel_file, model, temperature, num_calls, use_embeddings, system_prompt],
+        outputs=[download_button]
     )
-)
 
 if __name__ == "__main__":
     demo.launch(share=True)