Precription feature done

app.py

@@ -28,12 +28,25 @@ Also, the final service rates and offers will be available at the time of bookin
 and may vary from the information provided here.
 **Can I help you with anything?**
 """
-    openai_opening_message = """"You are a helpful assistant of a diagnostic 
+    openai_opening_system_message = """"You are a helpful assistant of a diagnostic 
 services business.
 The system uses RAG to retrieve relevant information from a knowledge base.
 You can also answer questions based on the information provided by the user.
+Do not provide any medical advice or diagnosis. 
+"""
+    prescription_upload_message = """The user has uploaded an image.
+Check if the image contains a prescription, if not, ask the user to upload a valid prescription
+image or provide details about the tests they are interested in. Do not provide 
+information about any other image if the image is not a prescription. Just reply that "I am 
+only trained to assist with prescription images and the uploaded image does not seem 
+to be a prescription." Do not answer any question if the uploaded
+image is not a prescription.
+If the image contains a prescription, extract the tests advised by the doctor 
+and provide details about those tests like rates and offers. For the tests 
+which are not in your knowledge base, say, "Not in our lab". 
+At last, also ask the user if You missed any test.
+Do not provide any medical advice or diagnosis. 
 """
-
     chatbot = gr.Chatbot(type="messages")
     chat_input = gr.MultimodalTextbox(
         interactive=True,
@@ -87,7 +100,7 @@ You can also answer questions based on the information provided by the user.
         # print("history", history)
         if len(history) == 2:
             # print("Inside")
-            history.insert(0,{"role": "system", "content": openai_opening_message})
+            history.insert(0,{"role": "system", "content": openai_opening_system_message})
             # print("history after insert", history)
         messages = copy.deepcopy(history)
         for i, msg in enumerate(messages):
@@ -108,6 +121,16 @@ You can also answer questions based on the information provided by the user.
                             "image_url": {"url": f"data:image/jpeg;base64,{encoded_content}"}}]
         clean_messages = [] # OpenAI doesnot accept metadata or options in messages
         for msg in messages:
+            try:
+                if msg["content"][0]["type"] == "image_url":
+                    clean_messages.append({
+                    "role": "user",
+                    "content": [{
+                        "type": "text",
+                        "text": prescription_upload_message
+                    }]})
+            except:
+                pass
             clean_msg = {
                 "role": msg["role"],
                 "content": msg["content"]
@@ -117,11 +140,11 @@ You can also answer questions based on the information provided by the user.
 
         ########################### AGENTIC WORKFLOW ##########################
         # Call Agent1- the RAG Decision Agent
-        rag_decision = agent1_rag_decision(messages[-1]["content"])
+        rag_decision = agent1_rag_decision(clean_messages[-1]["content"])
 
         if rag_decision == True:
             #Call Agent2 - the RAG Retrieval Agent
-            top_k_results = agent2_use_rag(messages[-1]["content"][0]["text"], k=3)
+            top_k_results = agent2_use_rag(clean_messages[-1]["content"][0]["text"], k=3)
             # Append the top k results to the messages
             for i, result in enumerate(top_k_results):
                 clean_messages.append({
@@ -132,7 +155,7 @@ You can also answer questions based on the information provided by the user.
             response = agent3_llm_agent(clean_messages)
         else:
             # Call Agent3 - the LLM Agent to get query response
-            response = agent3_llm_agent(messages)
+            response = agent3_llm_agent(clean_messages)
         #######################################################################
 
         # print("response:", response)