cleaned up .env to move Azure config to separate azure.yaml file

updated README.md to explain new config
added Azure yaml loader to config class
centralized model retrieval into config class
this commit effectively combines and replaces #700 and #580

scripts/config.py

@@ -1,6 +1,7 @@
 import abc
 import os
 import openai
+import yaml
 from dotenv import load_dotenv
 # Load environment variables from .env file
 load_dotenv()
@@ -46,10 +47,7 @@ class Config(metaclass=Singleton):
         self.use_azure = False
         self.use_azure = os.getenv("USE_AZURE") == 'True'
         if self.use_azure:
-            self.openai_api_base = os.getenv("OPENAI_AZURE_API_BASE")
-            self.openai_api_version = os.getenv("OPENAI_AZURE_API_VERSION")
-            self.openai_deployment_id = os.getenv("OPENAI_AZURE_DEPLOYMENT_ID")
-            self.openai_embedding_deployment_id = os.getenv("OPENAI_AZURE_EMBEDDING_DEPLOYMENT_ID")
+            self.load_azure_config()
             openai.api_type = "azure"
             openai.api_base = self.openai_api_base
             openai.api_version = self.openai_api_version
@@ -82,6 +80,47 @@ class Config(metaclass=Singleton):
         # Initialize the OpenAI API client
         openai.api_key = self.openai_api_key
 
+    def get_azure_deployment_id_for_model(self, model: str) -> str:
+        """
+        Returns the relevant deployment id for the model specified.
+
+        Parameters:
+            model(str): The model to map to the deployment id.
+
+        Returns:
+            The matching deployment id if found, otherwise an empty string.
+        """
+        match model:
+            case self.fast_llm_model:
+                return self.azure_model_to_deployment_id_map["fast_llm_model_deployment_id"]
+            case self.smart_llm_model:
+                return self.azure_model_to_deployment_id_map["smart_llm_model_deployment_id"]
+            case "text-embedding-ada-002":
+                return self.azure_model_to_deployment_id_map["embedding_model_deployment_id"]
+            case default: 
+                return ""            
+
+    AZURE_CONFIG_FILE = os.path.join(os.path.dirname(__file__), '..', 'azure.yaml')
+
+    def load_azure_config(self, config_file: str=AZURE_CONFIG_FILE) -> None:
+        """
+        Loads the configuration parameters for Azure hosting from the specified file path as a yaml file.
+
+        Parameters:
+            config_file(str): The path to the config yaml file. DEFAULT: "../azure.yaml"
+
+        Returns:
+            None
+        """
+        try:
+            with open(config_file) as file:
+                config_params = yaml.load(file, Loader=yaml.FullLoader)
+        except FileNotFoundError:
+            config_params = {}
+        self.openai_api_base = config_params.get("azure_api_base", "")
+        self.openai_api_version = config_params.get("azure_api_version", "")
+        self.azure_model_to_deployment_id_map = config_params.get("azure_model_map", [])
+
     def set_continuous_mode(self, value: bool):
         """Set the continuous mode value."""
         self.continuous_mode = value

scripts/llm_utils.py

@@ -9,7 +9,7 @@ def create_chat_completion(messages, model=None, temperature=None, max_tokens=No
     """Create a chat completion using the OpenAI API"""
     if cfg.use_azure:
         response = openai.ChatCompletion.create(
-            deployment_id=cfg.openai_deployment_id,
+            deployment_id=cfg.get_azure_deployment_id_for_model(model),
             model=model,
             messages=messages,
             temperature=temperature,

scripts/memory/base.py

@@ -9,7 +9,7 @@ cfg = Config()
 def get_ada_embedding(text):
     text = text.replace("\n", " ")
     if cfg.use_azure:
-        return openai.Embedding.create(input=[text], engine=cfg.openai_embedding_deployment_id)["data"][0]["embedding"]
+        return openai.Embedding.create(input=[text], engine=cfg.get_azure_deployment_id_for_model("text-embedding-ada-002"))["data"][0]["embedding"]
     else:
         return openai.Embedding.create(input=[text], model="text-embedding-ada-002")["data"][0]["embedding"]