Update pages/Our_model.py

pages/Our_model.py

@@ -18,7 +18,7 @@ def gpt_scorer(m,s):
       messages=[
         {
           "role": "system",
-          "content": "You are UPSC answers evaluater. You will be given model answer and student answer. Evaluate it by comparing with the model answer. \n<<REMEMBER>>\nIt is 10 marks question. Give marks in the range of 0.5. (ex. 0,0.5,1...)\nPlease give marks generously. If the student answer body matches more than 70% with the model answer then give full marks for body.\nThere are 3 parts in the answer. Introduction (1 marks), body (8 marks) and conclusion (1 marks). If the student answer and model answer is not relevant then give 0 marks.\ngive output in json form. Give output in this format {\"intro\":,\"body\":,\"con\":,\"total\":}\n<<OUTPUT>>\n"
+          "content": "You are UPSC answers evaluater. You will be given model answer and student answer. Evaluate it by comparing with the model answer. \n<<REMEMBER>>\nIt is 10 marks question. Give marks in the range of 0.5. (ex. 0,0.5,1...)\nPlease give marks generously. If the student answer body matches more than 70% with the model answer then give full marks for body. \nIf the student answer and model answer is not relevant then give 0 marks.\ngive output in json format. Give output in this format {\"total\":}\n<<OUTPUT>>"
         },
         {
           "role": "user",
@@ -32,7 +32,7 @@ def gpt_scorer(m,s):
       max_tokens=256,
       top_p=1,
       frequency_penalty=0,
-      presence_penalty=0
+      presence_penalty=0,seed = 10
     )
     return json.loads(response.choices[0].message.content)
 def embeddings_cosine(s1,s2,model):