Chatbot ready and deployment checked

app.py

@@ -167,7 +167,7 @@ with gr.Blocks() as demo:
     ##########################################################################
     gr.Markdown(
         """
-        <h1 style='text-align: center; font-size: 2em; color: #2c3e50; margin-bottom: 0.2em;'>
+        <h1 style='text-align: center; font-size: 1.5em; color: #2c3e50; margin-bottom: 0.2em;'>
             MedScan Diagnostic Services Chatbot (Agentic AI framework powered by OpenAI)
         </h1>
         """

last_stable_app_on_hf.py

@@ -4,6 +4,7 @@ import os
 import base64
 import time
 import copy
+import re
 
 from dotenv import load_dotenv
 # Load environment variables from .env file
@@ -40,7 +41,7 @@ with gr.Blocks() as demo:
     
     def agent4_get_prescription_text(messages):
         """
-        Function to inference openai to get prescription text.
+        Openai agent to get prescription text.
         """
         prescription_text = get_prescription_text(messages)
         return prescription_text
@@ -50,13 +51,17 @@ with gr.Blocks() as demo:
             return base64.b64encode(f.read()).decode("utf-8")
     
     def load_welcome():
-        return [
-            {"role": "assistant", "content": bot_welcome_message}
-        ]
+        history = []
+        history.append({"role": "system", "content": openai_opening_system_message})
+        history.append({"role": "assistant", "content": bot_welcome_message})
+        return history
     
     def clear_and_load():
         # Return the welcome message
-        return [{"role": "assistant", "content": bot_welcome_message}], None
+        history = []
+        history.append({"role": "system", "content": openai_opening_system_message})
+        history.append({"role": "assistant", "content": bot_welcome_message})
+        return history, None
         
     def add_message(history, message):
         # Send the image to the agent4_get_prescription_text
@@ -73,9 +78,13 @@ with gr.Blocks() as demo:
                 "image_url": {"url": f"data:image/jpeg;base64,{encoded_content}"}
             })
             history.append({"role": "user", "content": {"path": x}})
-        # call agent4_get_prescription_text to get prescription text
-        prescription_text = "Extracted lab tests from prescription: \n" + agent4_get_prescription_text(messages)
-        history.append({"role": "system", "content": prescription_text})
+        
+        # call agent4_get_prescription_text if there is an image_url in the message
+        has_image_url = any("image_url" in item for item in messages[0]["content"])
+        if has_image_url:
+            prescription_text = agent4_get_prescription_text(messages)
+            print(f"Prescription Text: {prescription_text}")
+            history.append({"role": "system", "content": prescription_text})
         
         if message["text"] is not None:
             history.append({"role": "user", "content": message["text"]})
@@ -83,6 +92,7 @@ with gr.Blocks() as demo:
         return history, gr.MultimodalTextbox(value=None, interactive=False, file_count="multiple", placeholder="Enter message or upload file...")
     
     def respond(history):
+
         if len(history) == 2:
             history.insert(0,{"role": "system", "content": openai_opening_system_message})
         messages = copy.deepcopy(history)
@@ -107,27 +117,27 @@ with gr.Blocks() as demo:
                 "content": msg["content"]
             }
             clean_messages.append(clean_msg)
-
         ########################### AGENTIC WORKFLOW ##########################
         # Call Agent1- the RAG Decision Agent
+        rag_query = ""
         if clean_messages[-1]["role"] == "system" and "No prescription found" in clean_messages[-1]["content"]:
             # If the last message is a system message with "No prescription found", skip RAG decision
             rag_decision = False
         elif clean_messages[-2]["role"] == "system" and "No prescription found" in clean_messages[-2]["content"]:
             rag_decision = False
         else:
-            rag_query = ""
             # Get the last 10 messages in the format "role: <message>"
             last_10 = clean_messages[-10:] if len(clean_messages) > 10 else clean_messages
             rag_query = "\n".join(
                 f"{msg['role']}: {msg['content'][0]['text'] if isinstance(msg['content'], list) and msg['content'] and 'text' in msg['content'][0] else ''}"
                 for msg in last_10
             )
+            
             rag_decision = agent1_rag_decision(rag_query)
 
         if rag_decision == True:
             #Call Agent2 - the RAG Retrieval Agent
-            top_k_results = agent2_use_rag(clean_messages[-1]["content"][0]["text"], k=3)
+            top_k_results = agent2_use_rag(clean_messages[-1]["content"][0]["text"], k=5)
             # Append the top k results to the messages
             for i, result in enumerate(top_k_results):
                 clean_messages.append({
@@ -141,18 +151,30 @@ with gr.Blocks() as demo:
             response = agent3_llm_agent(clean_messages)
         #######################################################################
 
-        history.append({"role": "assistant", "content": response})
-        return history
+        # history.append({"role": "assistant", "content": response})
+        # return history
     
-        # history.append({"role": "assistant", "content": ""})
-        # for line in response.split("\n"):
-        #     history[-1]["content"] += line + "\n"
-        #     time.sleep(0.3)  # Adjust delay for pacing
-        #     yield history
+        history.append({"role": "assistant", "content": ""})
+        # Split by sentence boundaries (naive but works for most cases)
+        chunks = re.split(r'(?<=[.!?]) +', response)
+
+        for chunk in chunks:
+            history[-1]["content"] += chunk + " "
+            time.sleep(0.3)
+            yield history
     
 
     ##########################################################################
-    chatbot = gr.Chatbot(type="messages", render_markdown=True, height=550)
+    gr.Markdown(
+        """
+        <h1 style='text-align: center; font-size: 1.5em; color: #2c3e50; margin-bottom: 0.2em;'>
+            MedScan Diagnostic Services Chatbot (Agentic AI framework powered by OpenAI)
+        </h1>
+        """
+    )
+    chatbot = gr.Chatbot(type="messages", 
+                        render_markdown=True, 
+                        height=380)
     chat_input = gr.MultimodalTextbox(
         interactive=True,
         file_count="multiple",