Update app.py

app.py

@@ -34,10 +34,17 @@ from templates import bot_template, css, user_template
 from xml.etree import ElementTree as ET
 
 # 1. Constants and Top Level UI Variables
-API_URL = 'https://qe55p8afio98s0u3.us-east-1.aws.endpoints.huggingface.cloud'  # Dr Llama
+
+# My Inference API Copy
+# API_URL = 'https://qe55p8afio98s0u3.us-east-1.aws.endpoints.huggingface.cloud'  # Dr Llama
+# Original:
+API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-2-7b-chat-hf"
 API_KEY = os.getenv('API_KEY')
+MODEL1="meta-llama/Llama-2-7b-chat-hf"
+MODEL1URL="https://huggingface.co/meta-llama/Llama-2-7b-chat-hf"
+HF_KEY = os.getenv('HF_KEY')
 headers = {
-    "Authorization": f"Bearer {API_KEY}",
+    "Authorization": f"Bearer {HF_KEY}",
     "Content-Type": "application/json"
 }
 key = os.getenv('OPENAI_API_KEY')
@@ -444,10 +451,20 @@ def get_zip_download_link(zip_file):
     return href
 
 # 14. Inference Endpoints for Whisper (best fastest STT) on NVIDIA T4 and Llama (best fastest AGI LLM) on NVIDIA A10
+# My Inference Endpoint
 API_URL_IE = f'https://tonpixzfvq3791u9.us-east-1.aws.endpoints.huggingface.cloud'
+# Original
+API_URL_IE = "https://api-inference.huggingface.co/models/openai/whisper-small.en"
+MODEL2 = "openai/whisper-small.en"
+MODEL2_URL = "https://huggingface.co/openai/whisper-small.en"
+#headers = {
+#	"Authorization": "Bearer XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX",
+#	"Content-Type": "audio/wav"
+#}
+HF_KEY = os.getenv('HF_KEY')
 headers = {
-	"Authorization": "Bearer XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX",
-	"Content-Type": "audio/wav"
+    "Authorization": f"Bearer {HF_KEY}",
+    "Content-Type": "audio/wav"
 }
 
 @st.cache_resource