Update app.py

Made the big change - went for the more detailed answer version

app.py

@@ -20,47 +20,153 @@ def get_combo_index():
     index = GPTSimpleVectorIndex.load_from_disk('comboindex.json')
     return index
 
+def generate_variations(question):
+	def send_message(message_log):
+		# Use OpenAI's ChatCompletion API to get the chatbot's response
+		response = openai.ChatCompletion.create(
+			model="gpt-3.5-turbo",  # The name of the OpenAI chatbot model to use
+			messages=message_log,   # The conversation history up to this point, as a list of dictionaries
+			max_tokens=1000,        # The maximum number of tokens (words or subwords) in the generated response
+			stop=None,              # The stopping sequence for the generated response, if any (not used here)
+			temperature=0.7,        # The "creativity" of the generated response (higher temperature = more creative)
+		)
+		
+		# Find the first response from the chatbot that has text in it (some responses may not have text)
+		for choice in response.choices:
+			if "text" in choice:
+				return choice.text
+			
+		# If no response with text is found, return the first response's content (which may be empty)
+		return response.choices[0].message.content
+	
+	def extract(input):
+		
+		message_log = [{"role": "system", "content": input}]
+		user_input = f"Generate more questions from the following question: {input}. Give two more questions only. The questions are intended for knowledgeable doctors"
+		message_log.append({"role": "user", "content": user_input})
+		response = send_message(message_log)
+		message_log.append({"role": "assistant", "content": response})
+		text = str(response)
+		print(response)
+		return response
+	
+	input2 = question
+	
+	
+	
+	my_string = question
+	output = extract(input2)
+	output_list = output.split("\n")
+	final_list = [my_string] + output_list
+	print(final_list)
+	
+	
+	
+	
+	return final_list
+
+def consolidated_answer(question, oginput):
+	def send_message(message_log):
+		# Use OpenAI's ChatCompletion API to get the chatbot's response
+		response = openai.ChatCompletion.create(
+			model="gpt-3.5-turbo",  # The name of the OpenAI chatbot model to use
+			messages=message_log,   # The conversation history up to this point, as a list of dictionaries
+			max_tokens=1000,        # The maximum number of tokens (words or subwords) in the generated response
+			stop=None,              # The stopping sequence for the generated response, if any (not used here)
+			temperature=0.7,        # The "creativity" of the generated response (higher temperature = more creative)
+		)
+		
+		# Find the first response from the chatbot that has text in it (some responses may not have text)
+		for choice in response.choices:
+			if "text" in choice:
+				return choice.text
+			
+		# If no response with text is found, return the first response's content (which may be empty)
+		return response.choices[0].message.content
+	
+	def extract(input):
+		
+		message_log = [{"role": "system", "content": input}]
+		user_input = f"Give a consolidated answer from this: {input}. It should answer the original question {oginput}. The answer is for knowledgeable doctors so use medical terms."
+		message_log.append({"role": "user", "content": user_input})
+		response = send_message(message_log)
+		message_log.append({"role": "assistant", "content": response})
+		text = str(response)
+		print(response)
+		return response
+	
+	input2 = question
+	
+	
+	output = extract(input2)
+		
+	print(output)
+	return output
+
+	
+	
+
 def querying_db(query: str):
-    index = get_combo_index()
-    response = index.query(query)
-    return response
+	response = index.query(query, response_mode="default")
+	source = response.get_formatted_sources()
+	return response, source
+
 
 tools = [
-    Tool(
-        name="QueryingDB",
-        func=querying_db,
-        description="useful for when you need to answer questions from the database. The answer is given in bullet points.",
-        return_direct=True
-    )
+	Tool(
+		name="QueryingDB",
+		func=querying_db,
+		description="useful for when you need to answer questions from the database. The answer is for knowledgeable doctors",
+		return_direct=True
+	)
 ]
 
-prefix = "Give a detailed answer to the question. Avoid referencing tables or figures"
-suffix = """Give answer in bullet points
+prefix = "Give a detailed answer to the question"
+suffix = """Give answer intended for knowledgeable doctors
 
 Question: {input}
 {agent_scratchpad}"""
 
 prompt = ZeroShotAgent.create_prompt(
-    tools,
-    prefix=prefix,
-    suffix=suffix,
-    input_variables=["input", "agent_scratchpad"]
+	tools,
+	prefix=prefix,
+	suffix=suffix,
+	input_variables=["input", "agent_scratchpad"]
 )
 
-llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)
+llm_chain = LLMChain(llm=OpenAI(temperature=0.5), prompt=prompt)
 tool_names = [tool.name for tool in tools]
 agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)
 
 
 def get_answer(query_string):
-    agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)
-    result = agent_executor.run(query_string)
+	agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)
+	response, source = agent_executor.run(query_string)
+	result = f"{response}"
+	return result
+
+
+def get_answer2(list_thing):
+	answers = []
+	for question in list_thing:
+		answer = get_answer(question)
+		answers.append(answer)
+		
+	response2 = "\n".join(answers)
+	return response2
+
+	
 
-    return result
 
 
 def qa_app(query):
-    return get_answer(query)
+	question_list = generate_variations(query)
+	big_answer = get_answer2(question_list)
+	final_answer = consolidated_answer(big_answer, query)
+	return final_answer
+
+
+
 
 
 inputs = gr.inputs.Textbox(label="Enter your question:")