First model version

.gitattributes

@@ -33,3 +33,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+chat_template.json filter=lfs diff=lfs merge=lfs -text
+generation_config.json filter=lfs diff=lfs merge=lfs -text
+preprocessor_config.json filter=lfs diff=lfs merge=lfs -text
+tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
+adapter_config.json filter=lfs diff=lfs merge=lfs -text
+added_tokens.json filter=lfs diff=lfs merge=lfs -text
+special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+vocab.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+*.DS*

adapter_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c88fb289a155188a09737629830dc32e753bb679d6bddd5f94ddf9daa1921114
+size 727

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc856312174dc99a4c7f88a2c54d9590a3b3f5b5a86e2728d7138c7f4758c6d5
+size 74018232

added_tokens.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fa54985b58718a8fdb4f4d97484c4bd908db114847675e4bf3afe3e1d5d7bd4
+size 392

chat_template.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94174d7176c52a7192f96fc34eb2cf23c7c2059d63cdbfadca1586ba89731fb7
+size 1049

generation_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31bc5c808ee15908986654279dd054f3e6bd65d52f8ca7b18a2a80552e2d35b
+size 215

handler.py

@@ -0,0 +1,58 @@
+import torch
+from typing import Dict, Any
+from PIL import Image
+import base64
+from io import BytesIO
+
+
+class EndpointHandler:
+    def __init__(self, path: str = ""):
+        # Import your model and processor inside the class
+        from colpali_engine.models import ColQwen2, ColQwen2Processor
+
+        # Load the model and processor
+        self.model = ColQwen2.from_pretrained(
+            path,
+            torch_dtype=torch.bfloat16,
+        ).eval()
+        self.processor = ColQwen2Processor.from_pretrained(path)
+
+        # Determine the device
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.model.to(self.device)
+
+    def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]:
+        # Extract images from the input data
+        images_data = data.get("inputs", [])
+
+        if not images_data:
+            return {"error": "No images provided in 'inputs'."}
+
+        # Process images
+        images = []
+        for img_data in images_data:
+            if isinstance(img_data, str):
+                try:
+                    # Assume base64-encoded image
+                    image_bytes = base64.b64decode(img_data)
+                    image = Image.open(BytesIO(image_bytes)).convert("RGB")
+                    images.append(image)
+                except Exception as e:
+                    return {"error": f"Invalid image data: {e}"}
+            else:
+                return {"error": "Images should be base64-encoded strings."}
+
+        # Prepare inputs
+        batch_images = self.processor.process_images(images)
+
+        # Move tensors to the device
+        batch_images = {k: v.to(self.device) for k, v in batch_images.items()}
+
+        # Generate embeddings
+        with torch.no_grad():
+            image_embeddings = self.model(**batch_images)
+
+        # Convert embeddings to a list
+        embeddings_list = image_embeddings.cpu().tolist()
+
+        return {"embeddings": embeddings_list}

preprocessor_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd5968b65af7e090e399f39ae94734e400d9d71a3c82fca2720c5ee514034f3
+size 568

special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
+size 613

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955409fb4dab09a71b957ce69f8a8185bbbd3416b9ab5a47e01221545be39c6f
+size 4298

vocab.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
+size 2776833