azure_open_ai

config.py

@@ -5,4 +5,5 @@ QDRANT_URL = os.getenv('QDRANT_URL')
 QDRANT_ACCESS_TOKEN = os.getenv('QDRANT_ACCESS_TOKEN')
 OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
 JWKS_URL = os.getenv('JWKS_URL')
-X_API_KEY = os.getenv('X_API_KEY')  # Replace with your actual API key
+X_API_KEY = os.getenv('X_API_KEY')  
+AZURE_OPENAI_KEY = os.getenv('AZURE_OPENAI_KEY')

services/openai_service.py

@@ -1,13 +1,24 @@
+
 import logging
 import os
 from openai import OpenAI
+from openai import AzureOpenAI
 from openai import OpenAIError, RateLimitError
-from config import OPENAI_API_KEY
+from config import OPENAI_API_KEY, AZURE_OPENAI_KEY
 
 # Initialize the OpenAI client with the API key from the environment variable
 #api_key = os.getenv('OPENAI_API_KEY')
+# client = OpenAI(api_key=OPENAI_API_KEY)
+
+AZURE_OPENAI_ENDPOINT = os.getenv('AZURE_OPENAI_ENDPOINT')
+AZURE_API_VERSION = "2024-02-15-preview"  # API version for Azure OpenAI
 
-client = OpenAI(api_key=OPENAI_API_KEY)
+# Initialize the Azure OpenAI client with the endpoint and API key
+client = AzureOpenAI(
+    azure_endpoint=AZURE_OPENAI_ENDPOINT,
+    api_key=AZURE_OPENAI_KEY,
+    api_version=AZURE_API_VERSION
+)
 
 def generate_rag_response(json_output, user_query):
     logging.info("Generating RAG response")
@@ -28,8 +39,9 @@ def generate_rag_response(json_output, user_query):
         # Create a chat completion request
         chat_completion = client.chat.completions.create(
             messages=main_prompt,
-            model="gpt-4o-mini",  # Use the gpt-4o-mini model
-            timeout=10
+            model="gpt-35-turbo",  # Use the gpt-4o-mini model
+            max_tokens=486,  # Limit the maximum number of tokens in the response    
+            temperature=1  
         )
 
         # Log the response from the model
@@ -46,3 +58,8 @@ def generate_rag_response(json_output, user_query):
     except Exception as e:
         logging.error(f"Unexpected error: {e}")
         return None, str(e)
+
+
+
+
+