added support for multiple pdfs and text

app.py

@@ -1,3 +1,6 @@
+# adding support for multiple pdf files
+# working
+# Final one for PR
 import gradio as gr
 import anthropic
 import base64
@@ -12,20 +15,20 @@ def read_pdf_as_base64(file_path: str) -> str:
         return base64.b64encode(file.read()).decode('utf-8')
 
 def user_message(
-    user_input: str, 
-    history: list, 
+    user_input: str,
+    history: list,
     enable_citations: bool,
     doc_type: str,
     text_content: str,
     pdf_file: str,
     api_key: str
 ) -> tuple:
-    # logging
+    # Logging 
     print("\n----------- User Message -------------")
     print(f"User Input: {user_input}")
     print(f"Citations Enabled: {enable_citations}")
     print(f"Document Type: {doc_type}")
-    
+
     history.append({
         "role": "user",
         "content": user_input,
@@ -33,15 +36,15 @@ def user_message(
     return "", history
 
 def format_message_history(
-    history: list, 
+    history: list,
     enable_citations: bool,
     doc_type: str,
     text_content: str,
-    pdf_file: str
+    pdf_files: str
 ) -> List[Dict]:
     """Convert Gradio chat history to Anthropic message format."""
     formatted_messages = []
-    
+
     # Add previous messages
     for msg in history[:-1]:
         if msg["role"] == "user":
@@ -55,45 +58,71 @@ def format_message_history(
                     "role": "assistant",
                     "content": msg["content"]
                 })
-    
+
     # Prepare the latest message
     latest_message = {
         "role": "user",
         "content": []
     }
-    
-    # Add document if citations are enabled
+
+    # Add documents if citations are enabled
     if enable_citations:
-        if doc_type == "plain_text":
+        # Handle plain text input
+        if doc_type in ["plain_text", "combined"] and text_content.strip():
             latest_message["content"].append({
                 "type": "document",
                 "source": {
                     "type": "text",
                     "media_type": "text/plain",
-                    "data": text_content.strip() if text_content.strip() else DEFAULT_DOC
+                    "data": text_content.strip()
                 },
-                "title": "User Document" if text_content.strip() else "Sample Document",
+                "title": "User Text Document",
                 "citations": {"enabled": True}
             })
-        elif doc_type == "pdf" and pdf_file:
-            pdf_base64 = read_pdf_as_base64(pdf_file)
+
+        # Handle PDF input
+        if doc_type in ["pdf", "combined"] and pdf_files:
+            # Handle pdf_files as a list
+            if isinstance(pdf_files, str):
+                pdf_files = [pdf_files]  # Convert single path to list
+            
+            # Add each PDF as a separate document
+            for i, pdf_file in enumerate(pdf_files):
+                try:
+                    pdf_base64 = read_pdf_as_base64(pdf_file)
+                    latest_message["content"].append({
+                        "type": "document",
+                        "source": {
+                            "type": "base64",
+                            "media_type": "application/pdf",
+                            "data": pdf_base64
+                        },
+                        "title": f"User PDF Document {i+1}",
+                        "citations": {"enabled": True}
+                    })
+                except Exception as e:
+                    print(f"Error processing PDF {i+1}: {str(e)}")
+                    continue
+
+        # If no documents were added and citations are enabled, use default document
+        if not latest_message["content"]:
             latest_message["content"].append({
                 "type": "document",
                 "source": {
-                    "type": "base64",
-                    "media_type": "application/pdf",
-                    "data": pdf_base64
+                    "type": "text",
+                    "media_type": "text/plain",
+                    "data": DEFAULT_DOC
                 },
-                "title": "User PDF Document",
+                "title": "Sample Document",
                 "citations": {"enabled": True}
             })
-    
+
     # Add the user's question
     latest_message["content"].append({
         "type": "text",
         "text": history[-1]["content"]
     })
-    
+
     formatted_messages.append(latest_message)
     return formatted_messages
 
@@ -112,22 +141,22 @@ def bot_response(
                 "content": "Please provide your Anthropic API key to continue."
             })
             return history
-            
+
         # Initialize client with provided API key
         client = anthropic.Anthropic(api_key=api_key)
-        
+
         messages = format_message_history(history, enable_citations, doc_type, text_content, pdf_file)
-        
+
         response = client.messages.create(
             model="claude-3-5-sonnet-20241022",
             max_tokens=1024,
             messages=messages
         )
-        
+
         # Initialize main response and citations
         main_response = ""
         citations = []
-        
+
         # Process each content block
         for block in response.content:
             if block.type == "text":
@@ -136,13 +165,13 @@ def bot_response(
                     for citation in block.citations:
                         if citation.cited_text not in citations:
                             citations.append(citation.cited_text)
-        
+
         # Add main response
         history.append({
             "role": "assistant",
             "content": main_response
         })
-        
+
         # Add citations if any were found and citations are enabled
         if enable_citations and citations:
             history.append({
@@ -150,9 +179,9 @@ def bot_response(
                 "content": "\n".join([f"• {cite}" for cite in citations]),
                 "metadata": {"title": "📚 Citations"}
             })
-        
+
         return history
-            
+
     except Exception as e:
         print(f"Error in bot_response: {str(e)}")
         error_message = str(e)
@@ -166,19 +195,19 @@ def bot_response(
 
 def update_document_inputs(enable_citations: bool, doc_type: str = "plain_text"):
     """Update visibility of document input components based on settings."""
-    text_visible = enable_citations and doc_type == "plain_text"
-    pdf_visible = enable_citations and doc_type == "pdf"
+    text_visible = enable_citations and (doc_type in ["plain_text", "combined"])
+    pdf_visible = enable_citations and (doc_type in ["pdf", "combined"])
     radio_visible = enable_citations
-    
+
     return {
         doc_type_radio: gr.Radio(visible=radio_visible),
         text_input: gr.Textbox(visible=text_visible),
         pdf_input: gr.File(visible=pdf_visible)
     }
 
-with gr.Blocks(fill_height=True, theme="ocean") as demo:
-    gr.Markdown("# Chat with Citations")
-    
+with gr.Blocks(theme="ocean", fill_height=True) as demo:
+    gr.Markdown("# Chat with Anthropic Claude's Citations")
+
     with gr.Row(scale=1):
         with gr.Column(scale=4):
             chatbot = gr.Chatbot(
@@ -187,13 +216,13 @@ with gr.Blocks(fill_height=True, theme="ocean") as demo:
                 show_label=False,
                 scale=1
             )
-            
+
             msg = gr.Textbox(
                 placeholder="Enter your message here...",
                 show_label=False,
                 container=False
             )
-            
+
         with gr.Column(scale=1):
             api_key = gr.Textbox(
                 type="password",
@@ -202,50 +231,50 @@ with gr.Blocks(fill_height=True, theme="ocean") as demo:
                 info="Your API key will not be stored",
                 interactive=True,
             )
-            
+
             enable_citations = gr.Checkbox(
                 label="Enable Citations",
                 value=True,
                 info="Toggle citation functionality"
             )
-            
+
             doc_type_radio = gr.Radio(
-                choices=["plain_text", "pdf"],
+                choices=["plain_text", "pdf", "combined"],
                 value="plain_text",
                 label="Document Type",
-                info="Choose the type of document"
+                info="Choose the type of document(s) to reference"
             )
-            
+
             text_input = gr.Textbox(
                 label="Document Content",
-                placeholder=f"Enter your document text here. Default doc is -- {DEFAULT_DOC}",
+                placeholder=f"Enter your document text here.\nDefault text will be picked if citations are enabled and you don't provide the documents. Default document is --"{DEFAULT_DOC}",
                 lines=10,
-                info="Enter the text you want to reference. If empty, default document will be used."
+                info="Enter the text you want to reference"
             )
-            
+
             pdf_input = gr.File(
                 label="Upload PDF",
-                file_count="single",
+                file_count="multiple",
                 file_types=[".pdf"],
                 type="filepath",
                 visible=False
             )
-    
+
     clear = gr.ClearButton([msg, chatbot, text_input, pdf_input])
-    
+
     # Update input visibility based on settings
     enable_citations.change(
         update_document_inputs,
         inputs=[enable_citations, doc_type_radio],
         outputs=[doc_type_radio, text_input, pdf_input]
     )
-    
+
     doc_type_radio.change(
         update_document_inputs,
         inputs=[enable_citations, doc_type_radio],
         outputs=[doc_type_radio, text_input, pdf_input]
     )
-    
+
     # Handle message submission
     msg.submit(
         user_message,