Update app.py

app.py

@@ -6,12 +6,21 @@ For more information on `huggingface_hub` Inference API support, please check th
 """
 #client = InferenceClient("esha111/recipe-generator")
 
-from llama_cpp import Llama
+#from llama_cpp import Llama
 
-llm = Llama.from_pretrained(
-	repo_id="esha111/recipe-generator",
-	filename="model-q8_0.gguf",
-)
+#llm = Llama.from_pretrained(
+#	repo_id="esha111/recipe-generator",
+#	filename="model-q8_0.gguf",
+#)
+
+import requests
+
+API_URL = "https://api-inference.huggingface.co/models/esha111/recipe-generator"
+
+def query(payload):
+	response = requests.post(API_URL, json=payload)
+	return response.json()
+	
 
 def respond(
     message,
@@ -46,11 +55,15 @@ def respond(
         response += token
         yield response
     """
-    output = llm(
-    	message,
-    	max_tokens=512,
-    	echo=True
-    )
+    #output = llm(
+    #	message,
+    #	max_tokens=512,
+    #	echo=True
+    #)
+
+    output = query({
+	"inputs": message,
+    })
     return output
 
 """