add pipeline

README.md

@@ -1,3 +1,6 @@
 ---
-license: other
----
+license: mit
+tags:
+- feature-extraction
+library_name: generic
+---

pipeline.py

@@ -0,0 +1,24 @@
+from typing import Dict, List, Any
+import numpy as np
+from transformers import CLIPTokenizer, CLIPModel
+
+
+class PreTrainedPipeline():
+    def __init__(self, path=""):
+        # Preload all the elements you are going to need at inference.
+        # For instance your model, processors, tokenizer that might be needed.
+        # This function is only called once, so do all the heavy processing I/O here"""
+        self.model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+        self.tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32")
+
+    def __call__(self, inputs: str) -> List[float]:
+        """
+        Args:
+            inputs (:obj:`str`):
+                a string to get the features from.
+        Return:
+            A :obj:`list` of floats: The features computed by the model.
+        """
+        token_inputs = self.tokenizer([inputs],  padding=True, return_tensors="pt")
+        query_embed = self.model.get_text_features(**token_inputs)
+        return query_embed.detach().cpu().numpy()[0].tolist()

requirements.txt

@@ -0,0 +1,5 @@
+numpy==1.23.1
+transformers==4.21.1
+torch==1.12.1
+torchvision==0.13.1
+-f https://download.pytorch.org/whl/cu116