Update app.py

app.py

@@ -19,25 +19,27 @@ load_dotenv()
 
 
 
-# initialize the client
-client = OpenAI(
-  base_url="https://api-inference.huggingface.co/v1",
-  api_key=os.environ.get('HUGGINGFACE_API')#"hf_xxx" # Replace with your token
-) 
+# # initialize the client
+# client = OpenAI(
+#   base_url="https://api-inference.huggingface.co/v1",
+#   api_key=os.environ.get('HUGGINGFACE_API')#"hf_xxx" # Replace with your token
+# ) 
 
 
+base_url="https://api-inference.huggingface.co/v1
 
 
 #Create supported models
 model_links ={
-    "Mistral":"mistralai/Mistral-7B-Instruct-v0.2",
-    "Gemma-7B":"google/gemma-7b-it",
-    "Gemma-2B":"google/gemma-2b-it",
-    "Zephyr-7B-β":"HuggingFaceH4/zephyr-7b-beta",
+    "Mistral":base_url+"mistralai/Mistral-7B-Instruct-v0.2",
+    "Gemma-7B":base_url+"google/gemma-7b-it",
+    "Gemma-2B":base_url+"google/gemma-2b-it",
+    "Zephyr-7B-β":base_url+"HuggingFaceH4/zephyr-7b-beta",
     # "Llama-2":"meta-llama/Llama-2-7b-chat-hf"
-
 }
 
+headers = {"Authorization":F"Bearer"+os.environ.get('HUGGINGFACE_API')}
+
 #Pull info about the model to display
 model_info ={
     "Mistral":
@@ -151,7 +153,7 @@ if prompt := st.chat_input(f"Hi I'm {selected_model}, ask me a question"):
 
     # Display assistant response in chat message container
     with st.chat_message("assistant"):
-        stream = client.chat.completions.create(
+        stream = InferenceClient(
             model=model_links[selected_model],
             messages=[
                 {"role": m["role"], "content": m["content"]}