Update apis/chat_api.py

apis/chat_api.py

@@ -116,17 +116,6 @@ class ChatAPIApp:
         model_name: str = Field(..., example="bert-base-uncased")
         api_key: str = Field(..., example="your_hf_api_key_here")
 
-    async def chat_embedding(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})
-        result = response.json()
-        if isinstance(result, list) and len(result) > 0 and isinstance(result[0], list):
-            return result
-        elif "error" in result:
-            raise RuntimeError("The model is currently loading, please re-run the query.")
-        else:
-            raise RuntimeError("Unexpected response format.")
 
     class ChatCompletionsPostItem(BaseModel):
         model: str = Field(
@@ -186,7 +175,18 @@ class ChatAPIApp:
             data_response = streamer.chat_return_dict(stream_response)
             return data_response
 
-        
+    async def chat_embedding(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})
+        result = response.json()
+        if isinstance(result, list) and len(result) > 0 and isinstance(result[0], list):
+            return result
+        elif "error" in result:
+            raise RuntimeError("The model is currently loading, please re-run the query.")
+        else:
+            raise RuntimeError("Unexpected response format.")  
+            
 
     async def embedding(request: QueryRequest):
         try: