Rename ler.py to handler.py

ler.py → handler.py

@@ -186,10 +186,9 @@ device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 if device.type != 'cuda':
     raise ValueError("need to run on GPU")
 
+# multi-model list
 multi_model_list = [
-    {"model_id": "/model_v4"},
-    {"model_id": "/model_v2"},
-    {"model_id": "/model_v3"}
+    {"model_id": "jayparmr/icbinp", "task": "text-classification"},
 ]
 
 class EndpointHandler():
@@ -236,6 +235,26 @@ class EndpointHandler():
         Return:
             A :obj:`dict`:. base64 encoded image
         """
+        # deserialize incomin request
+        inputs = data.pop("inputs", data)
+        # parameters = data.pop("parameters", None)
+        model_id = data.pop("model_id", None)
+
+        # check if model_id is in the list of models
+        if model_id is None or model_id not in self.multi_model:
+            raise ValueError(f"model_id: {model_id} is not valid. Available models are: {list(self.multi_model.keys())}")
+
+        # # pass inputs with all kwargs in data
+        # if parameters is not None:
+        #     prediction = self.multi_model[model_id](inputs, **parameters)
+        # else:
+        #     prediction = self.multi_model[model_id](inputs)
+        # # postprocess the prediction
+        # return prediction
+        
+        
+        
+        
         print("Logs post: self.path",self.path)
         print("Logs post: task is ", data)
         inputs = data.pop("inputs", data)
@@ -255,7 +274,7 @@ class EndpointHandler():
                 if "character sheet" in task.get_prompt().lower():
                     return pose(task, s3_outkey="", poses=pickPoses())
                 else:
-                    return self.multi_text2image_model[ self.path + multi_model_list[0][model_id]](task)
+                    return self.multi_text2image_model[model_id](task)
             elif task_type == TaskType.IMAGE_TO_IMAGE:
                 return img2img(task)
             elif task_type == TaskType.CANNY: