Update app.py

app.py

@@ -23,8 +23,9 @@ class SentimentAnalyzer:
         # result = pipe(text, label)
         # sentiment_scores= {result['labels'][0]:result['scores'][0],result['labels'][1]:result['scores'][1],result['labels'][2]:result['scores'][2]}
         # sentiment_scores_str = f"Positive: {sentiment_scores['positive']:.2f}, Neutral: {sentiment_scores['neutral']:.2f}, Negative: {sentiment_scores['negative']:.2f}"
-        prompt = f""" Your task is find the top 3 setiments : <positive, negative, neutral> and it's sentiment score for the Mental Healthcare Doctor Chatbot and patient conversation text.\
-        your are analyze the text and provide the output in the following json order: \"\"\"Positive: <sentiment_scores['positive']:.2f>, Neutral: <sentiment_scores['neutral']:.2f>, Negative: <sentiment_scores['negative']:.2f>\"\"\"
+        prompt = f""" Your task is find the top 3 setiments : <labels = positive, negative, neutral> and it's sentiment score for the Mental Healthcare Doctor Chatbot and patient conversation text.\
+        your are analyze the text and provide the output in the following json order: \"\"\"
+        <\{result['labels'][0]: result['scores'][0], result['labels'][1]: result['scores'][1], result['labels'][2]: result['scores'][2] \}>\"\"\" \
         analyze the text : '''{text}'''
         """
         response = openai.Completion.create(
@@ -60,14 +61,32 @@ class SentimentAnalyzer:
         return message
 
     def analyze_sentiment_for_graph(self, text):
-        pipe = pipeline("zero-shot-classification", model=self.model)
-        label=["positive", "negative", "neutral"]
-        result = pipe(text, label)
-        sentiment_scores = {
-            result['labels'][0]: result['scores'][0],
-            result['labels'][1]: result['scores'][1],
-            result['labels'][2]: result['scores'][2]
-        }
+        # pipe = pipeline("zero-shot-classification", model=self.model)
+        # label=["positive", "negative", "neutral"]
+        # result = pipe(text, label)
+        # sentiment_scores = {
+        #     result['labels'][0]: result['scores'][0],
+        #     result['labels'][1]: result['scores'][1],
+        #     result['labels'][2]: result['scores'][2]
+        # }
+        prompt = f""" Your task is find the top 3 setiments : <labels = positive, negative, neutral> and it's sentiment score for the Mental Healthcare Doctor Chatbot and patient conversation text.\
+        your are analyze the text and provide the output in the following json order: \"\"\"
+        <\{result['labels'][0]: result['scores'][0], result['labels'][1]: result['scores'][1], result['labels'][2]: result['scores'][2] \}>\"\"\" \
+        analyze the text : '''{text}'''
+        """
+        response = openai.Completion.create(
+        model="text-davinci-003",
+        prompt=prompt,
+        temperature=1,
+        max_tokens=60,
+        top_p=1,
+        frequency_penalty=0,
+        presence_penalty=0
+        )
+
+        # Extract the generated text
+        sentiment_scores = response.choices[0].text.strip()
+        print(sentiment_scores)
         return sentiment_scores
 
     def emotion_analysis_for_graph(self,text):