Update app.py

app.py

@@ -30,6 +30,8 @@ import yfinance as yf
 import pandas as pd
 import nltk
 from nltk.tokenize import sent_tokenize
+from openai import OpenAI
+
 
 class KeyValueExtractor:
 
@@ -42,6 +44,7 @@ class KeyValueExtractor:
             pdf_file_path (str): The path to the input PDF file.
         """
         self.model = "facebook/bart-large-mnli"
+        self.client = OpenAI()
         
         
     def get_url(self,keyword):
@@ -113,19 +116,34 @@ class KeyValueExtractor:
       return result["output_text"]
 
     def one_day_summary(self,content) -> None:
-
-      # Use OpenAI's Completion API to analyze the text and extract key-value pairs
-      response = openai.Completion.create(
-          engine="text-davinci-003",  # You can choose a different engine as well
-          temperature = 0,
-          prompt=f"i want detailed Summary from given finance details. i want information like what happen today comparing last day good or bad Bullish or Bearish like these details i want summary. content in backticks.```{content}```.",
-          max_tokens=1000 # You can adjust the length of the response
-      )
-
-      # Extract and return the chatbot's reply
-      result = response['choices'][0]['text'].strip()
-      print(result)
-      return result
+        conversation = [
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": f"i want detailed Summary from given finance details. i want information like what happen today comparing last day good or bad Bullish or Bearish like these details i want summary. content in backticks.```{content}```."}
+        ]
+        
+        # Call OpenAI GPT-3.5-turbo
+        chat_completion = self.client.chat.completions.create(
+            model = "gpt-3.5-turbo",
+            messages = conversation,
+            max_tokens=1000,
+            temperature=0
+        )
+        
+        response = chat_completion.choices[0].message.content
+        return response   
+
+        # # Use OpenAI's Completion API to analyze the text and extract key-value pairs
+        # response = openai.Completion.create(
+        #   engine="text-davinci-003",  # You can choose a different engine as well
+        #   temperature = 0,
+        #   prompt=f"i want detailed Summary from given finance details. i want information like what happen today comparing last day good or bad Bullish or Bearish like these details i want summary. content in backticks.```{content}```.",
+        #   max_tokens=1000 # You can adjust the length of the response
+        # )
+        
+        # # Extract and return the chatbot's reply
+        # result = response['choices'][0]['text'].strip()
+        # print(result)
+        # return result
 
     def extract_key_value_pair(self,content) -> None:
 
@@ -136,18 +154,31 @@ class KeyValueExtractor:
         """
 
         try:
-
-          # Use OpenAI's Completion API to analyze the text and extract key-value pairs
-          response = openai.Completion.create(
-              engine="text-davinci-003",  # You can choose a different engine as well
-              temperature = 0,
-              prompt=f"Get maximum count meaningfull key value pairs. content in backticks.```{content}```.",
-              max_tokens=1000 # You can adjust the length of the response
-          )
-
-          # Extract and return the chatbot's reply
-          result = response['choices'][0]['text'].strip()
-          return result
+            conversation = [
+                {"role": "system", "content": "You are a helpful assistant."},
+                {"role": "user", "content": f"Get maximum count meaningfull key value pairs. content in backticks.```{content}```."}
+            ]
+            
+            # Call OpenAI GPT-3.5-turbo
+            chat_completion = self.client.chat.completions.create(
+                model = "gpt-3.5-turbo",
+                messages = conversation,
+                max_tokens=1000,
+                temperature=0
+            )
+            response = chat_completion.choices[0].message.content
+            return response            
+          # # Use OpenAI's Completion API to analyze the text and extract key-value pairs
+          # response = openai.Completion.create(
+          #     engine="text-davinci-003",  # You can choose a different engine as well
+          #     temperature = 0,
+          #     prompt=f"Get maximum count meaningfull key value pairs. content in backticks.```{content}```.",
+          #     max_tokens=1000 # You can adjust the length of the response
+          # )
+
+          # # Extract and return the chatbot's reply
+          # result = response['choices'][0]['text'].strip()
+          # return result
         except Exception as e:
             # If an error occurs during the key-value extraction process, log the error
             logging.error(f"Error while extracting key-value pairs: {e}")