init!

backend.py

@@ -4,12 +4,12 @@ import io
 import requests
 import html  # For escaping HTML characters
 from bs4 import BeautifulSoup
-from openai import OpenAI 
+from openai import OpenAI
 
 # Initialize OpenAI API with Nvidia's Mistral model
 client = OpenAI(
-    base_url="https://integrate.api.nvidia.com/v1",
-    api_key="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"
+    base_url="https://api.llama-api.com",
+    api_key="LA-38879bbd57704371a151ce66b6186aa6e95ab69a3b974f5ca4459f2ce89c4de1"
 )
 
 def clean_test_case_output(text):
@@ -86,13 +86,13 @@ def generate_testcases(user_story):
     try:
         # Call the Nvidia Mistral API with the refined prompt
         completion = client.chat.completions.create(
-            model="nv-mistralai/mistral-nemo-12b-instruct",  # Using Mistral model
+            model="llama3.1-70b",  # Using Mistral model
             messages=[
                 {"role": "user", "content": prompt}
             ],
             temperature=0.06,  # Further lowering temperature for precise and deterministic output
             top_p=0.5,  # Prioritize high-probability tokens even more
-            max_tokens=4096,  # Increase max tokens to allow longer content
+            max_token=4096,  # Increase max tokens to allow longer content
             stream=True  # Streaming the response for faster retrieval
         )