Update app.py

app.py

@@ -8,11 +8,17 @@ from langchain import OpenAI, LLMChain
 from cachetools import cached, TTLCache
 import openai
 
+
 s3 = boto3.resource('s3')
 bucket_name = "notesinendocrinology"
-bucket = s3.Bucket(bucket_name)
-for obj in bucket.objects.filter(Prefix="comboindex.json"):
-    combo_index_path = obj.key
+prefixes = ["comboindex.json", "osteoporosis.json", "nafld.json"]
+
+for prefix in prefixes:
+    for obj in s3.Bucket(bucket_name).objects.filter(Prefix=prefix):
+        file_path = obj.key
+        s3.Bucket(bucket_name).download_file(file_path, file_path.split("/")[-1])
+        print(f"Downloaded {file_path}")
+
 
 @cached(cache=TTLCache(maxsize=1, ttl=3600))  # cache for 1 hour
 def get_combo_index():
@@ -21,96 +27,69 @@ def get_combo_index():
     index = GPTSimpleVectorIndex.load_from_disk('comboindex.json')
     return index
 
+def keywords(query2):
+	bucket.download_file(combo_index_path, "comboindex.json")
+	index1 = GPTSimpleVectorIndex.load_from_disk('comboindex.json')
+	if "NASH" in query2 or "NAFLD" in query2 or "Non-alcoholic fatty live disease" in query2:
+		bucket.download_file(combo_index_path, "nafld.json")
+		index1 = GPTSimpleVectorIndex.load_from_disk('nafld.json')
+	elif "osteoporosis" in query2 or 'osteopenia' in query2 or 'low bone mass' in query2 or 'DEXA-BMD' in query2 or 'BMD' in query2:
+		bucket.download_file(combo_index_path, "osteoporosis.json")
+		index1 = GPTSimpleVectorIndex.load_from_disk('osteoporosis.json')
+	else:
+		bucket.download_file(combo_index_path, "comboindex.json")
+		index1 = GPTSimpleVectorIndex.load_from_disk('comboindex.json')
+	return index1
+
+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=512,  # 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=0.5,  # 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 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"
+		user_input = f"Generate one follow-up question from the following question: {input}. Give one more question only. The question is 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 = "0. " + 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
+	get_index1 = keywords(query)
+	response = get_index1.query(query, response_mode="default")
 
+	return response
 
 
 tools = [
@@ -147,49 +126,68 @@ def get_answer(query_string):
 	return result
 
 
-def get_answer2(list_thing, answer_type):
+def get_answer2(list_thing):
 	responses = []
-	if answer_type == "Detailed Answer":
-		for question in list_thing:
-			answer = get_answer(question)
-			response = f"{question}\n{answer}"
-			responses.append(response)
-			
-		return "\n\n".join(responses)
-	elif answer_type == "Consolidated answer":
-		for question in list_thing:
-			answer = get_answer(question)
-			response = f"{question}\n{answer}"
-			responses.append(response)
-			
-		return "\n\n".join(responses)
-	
-	else:
-		question = list_thing[0]
+	for question in list_thing:
 		answer = get_answer(question)
 		response = f"{question}\n{answer}"
+		responses.append(response)
+
+	return "\n\n".join(responses)
+
+
+def consolidated_answer(question, oginput):
+	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 qa_app(query1):
+	# 1. function that checks if relevant keyword is found in the query and get the relevant index
+	# 2. generate question variartions
 
-	
+	question_variations_list = generate_variations(query1)
+	whichindex = keywords(query1)
+	if whichindex == 'nafld.json':
+		prefix_answer = "Here is the answer based on Notes in Endocrinology and American Association of Clinical Endocrinology Clinical Practice Guideline for the Diagnosis and Management of Nonalcoholic Fatty Liver Disease in Primary Care and Endocrinology Clinical Settings:"
+		suffix_answer = """Citation: \n
 
+		1. Cusi, Kenneth, Scott Isaacs, Diana Barb, Rita Basu, Sonia Caprio, W. Timothy Garvey, Sangeeta Kashyap et al. "American Association of Clinical Endocrinology clinical practice guideline for the diagnosis and management of nonalcoholic fatty liver disease in primary care and endocrinology clinical settings: co-sponsored by the American Association for the Study of Liver Diseases (AASLD)." Endocrine Practice 28, no. 5 (2022): 528-562.
 
+		"""
+
+	elif whichindex == 'osteoporosis_new.json':
+		prefix_answer = "According to : Pharmacological Management of Osteoporosis in Postmenopausal Women: An Endocrine Society* Clinical Practice Guideline & Notes in Endocrinology"
+		suffix_answer = """Citation: \n
+
+		1. Eastell R, Rosen CJ, Black DM, Cheung AM, Murad MH, Shoback D. Pharmacological management of osteoporosis in postmenopausal women: an Endocrine Society clinical practice guideline. The Journal of Clinical Endocrinology & Metabolism. 2019 May;104(5):1595-622.
+		"""
 
-def qa_app(query, answer_type):
-	question_list = generate_variations(query)
-	big_answer = get_answer2(question_list, answer_type)
-	if answer_type == "Consolidated answer":
-		final_answer = consolidated_answer(big_answer, query)
-		return final_answer
 	else:
-		return big_answer
-	
-	
+		prefix_answer = "According to NIE:"
+		suffix_answer = "Citation: NIE"
+	big_answer = get_answer2(question_variations_list)
+	final_answer = consolidated_answer(big_answer, query1)
+	final_answer_with_citation = prefix_answer + "\n\n" + final_answer + "\n\n" + suffix_answer
+	return final_answer_with_citation
+
+
 inputs = [
 	gr.inputs.Textbox(label="Enter your question:"),
-	gr.inputs.Dropdown(choices=["Quick Answer", "Detailed Answer", "Consolidated answer"], label="Choose answer type:")
+
 ]
 
 output = gr.outputs.Textbox(label="Answer:")
@@ -202,4 +200,3 @@ iface = gr.Interface(
 )
 
 iface.launch()
-