Update app.py

app.py

@@ -5,19 +5,7 @@ from huggingface_hub import InferenceClient
 For more information on huggingface_hub Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 # client = InferenceClient("unsloth/Llama-3.2-1B-Instruct")
-#client = InferenceClient(model="https://aq0teqpujnx3bv68.us-east-1.aws.endpoints.huggingface.cloud/")
-import requests
-
-API_URL = "https://aq0teqpujnx3bv68.us-east-1.aws.endpoints.huggingface.cloud"
-headers = {
-	"Accept" : "application/json",
-	"Content-Type": "application/json" 
-}
-
-def query(payload):
-	response = requests.post(API_URL, headers=headers, json=payload)
-	return response.json()
-
+client = InferenceClient(model="llama-3-1-8b-medical-f16-qip")
 
 def respond(
     message,
@@ -36,21 +24,32 @@ def respond(
     max_tokens = 512
     temperature = 0.7
     top_p = 0.95
-  
     
-    for message in query({
-    	"inputs":system_message + "\n\n" + message,
-    	"parameters": {
-    		"max_new_tokens": 150
-    	}
-    }):
-        print(message)
-        token = message
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+
         response += token
         yield response
 
 
-
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """