Update apis/chat_api.py

apis/chat_api.py

@@ -175,7 +175,7 @@ class ChatAPIApp:
             data_response = streamer.chat_return_dict(stream_response)
             return data_response
 
-    async def chat_embedding(texts, model_name, api_key):
+    async def chat_embedding(self, texts, model_name, api_key):
         api_url = f"https://api-inference.huggingface.co/pipeline/feature-extraction/{model_name}"
         headers = {"Authorization": f"Bearer {api_key}"}
         response = requests.post(api_url, headers=headers, json={"inputs": texts})
@@ -186,9 +186,8 @@ class ChatAPIApp:
             raise RuntimeError("The model is currently loading, please re-run the query.")
         else:
             raise RuntimeError("Unexpected response format.")  
-            
 
-    async def embedding(request: QueryRequest):
+    async def embedding(self, request: QueryRequest):
             try:
                 for attempt in range(3):  # Retry logic
                     try: