Added functionality to allow the use of GPT on a Microsoft Azure instance

scripts/config.py

@@ -34,6 +34,16 @@ class Config(metaclass=Singleton):
         self.smart_token_limit = int(os.getenv("SMART_TOKEN_LIMIT", 8000))
         
         self.openai_api_key = os.getenv("OPENAI_API_KEY")
+        self.use_azure = False
+        self.use_azure = os.getenv("USE_AZURE")
+        if self.use_azure:
+            self.openai_api_base = os.getenv("OPENAI_API_BASE")
+            self.openai_api_version = os.getenv("OPENAI_API_VERSION")
+            self.openai_deployment_id = os.getenv("OPENAI_DEPLOYMENT_ID")
+            openai.api_type = "azure"
+            openai.api_base = self.openai_api_base
+            openai.api_version = self.openai_api_version
+        
         self.elevenlabs_api_key = os.getenv("ELEVENLABS_API_KEY")
         
         self.google_api_key = os.getenv("GOOGLE_API_KEY")

scripts/llm_utils.py

@@ -6,11 +6,20 @@ openai.api_key = cfg.openai_api_key
 
 # Overly simple abstraction until we create something better
 def create_chat_completion(messages, model=None, temperature=None, max_tokens=None)->str:
-    response = openai.ChatCompletion.create(
-        model=model,
-        messages=messages,
-        temperature=temperature,
-        max_tokens=max_tokens
-    )
+    if cfg.use_azure:
+        response = openai.ChatCompletion.create(
+            deployment_id=cfg.openai_deployment_id,
+            model=model,
+            messages=messages,
+            temperature=temperature,
+            max_tokens=max_tokens
+        )
+    else:
+        response = openai.ChatCompletion.create(
+            model=model,
+            messages=messages,
+            temperature=temperature,
+            max_tokens=max_tokens
+        )
 
     return response.choices[0].message["content"]