Merge pull request Significant-Gravitas#258 from sweetlilmre/add-azur…

…e-compat

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

.env.template

@@ -3,4 +3,8 @@ ELEVENLABS_API_KEY=your-elevenlabs-api-key
 SMART_LLM_MODEL="gpt-4"
 FAST_LLM_MODEL="gpt-3.5-turbo"
 GOOGLE_API_KEY=
-CUSTOM_SEARCH_ENGINE_ID=
+CUSTOM_SEARCH_ENGINE_ID=
+USE_AZURE=False
+OPENAI_API_BASE=your-base-url-for-azure
+OPENAI_API_VERSION=api-version-for-azure
+OPENAI_DEPLOYMENT_ID=deployment-id-for-azure

README.md

@@ -92,6 +92,7 @@ pip install -r requirements.txt
 4. Rename `.env.template` to `.env` and fill in your `OPENAI_API_KEY`. If you plan to use Speech Mode, fill in your `ELEVEN_LABS_API_KEY` as well.
   - Obtain your OpenAI API key from: https://platform.openai.com/account/api-keys.
   - Obtain your ElevenLabs API key from: https://elevenlabs.io. You can view your xi-api-key using the "Profile" tab on the website.
+  - If you want to use GPT on an Azure instance, set `USE_AZURE` to `True` and provide the `OPENAI_API_BASE`, `OPENAI_API_VERSION` and `OPENAI_DEPLOYMENT_ID` values as explained here: https://pypi.org/project/openai/ in the `Microsoft Azure Endpoints` section
 
 ## 🔧 Usage
 

scripts/config.py

@@ -34,6 +34,16 @@ def __init__(self):
         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") == 'True'
+        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 @@
 
 # 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"]