feat: return a single tensor when a single image is given

modeling_jina_embeddings_v4.py

@@ -417,7 +417,7 @@ class JinaEmbeddingsV4Model(Qwen2_5_VLForConditionalGeneration):
         return_numpy: bool = False,
         truncate_dim: Optional[int] = None,
         prompt_name: Optional[str] = None,
-    ) -> List[torch.Tensor]:
+    ) -> Union[List[torch.Tensor], torch.Tensor]:
         """
         Encodes a list of texts into embeddings.
 
@@ -431,7 +431,7 @@ class JinaEmbeddingsV4Model(Qwen2_5_VLForConditionalGeneration):
             prompt_name: Type of text being encoded ('query' or 'passage')
 
         Returns:
-            List of text embeddings as tensors or numpy arrays
+            List of text embeddings as tensors or numpy arrays when encoding multiple texts, or single text embedding as tensor when encoding a single text
         """
         prompt_name = prompt_name or "query"
         encode_kwargs = self._validate_encoding_params(
@@ -459,7 +459,7 @@ class JinaEmbeddingsV4Model(Qwen2_5_VLForConditionalGeneration):
             **encode_kwargs,
         )
 
-        return embeddings
+        return embeddings if len(texts) > 1 else embeddings[0]
 
     def _load_images_if_needed(
         self, images: List[Union[str, Image.Image]]
@@ -484,9 +484,9 @@ class JinaEmbeddingsV4Model(Qwen2_5_VLForConditionalGeneration):
         return_numpy: bool = False,
         truncate_dim: Optional[int] = None,
         max_pixels: Optional[int] = None,
-    ) -> List[torch.Tensor]:
+    ) -> Union[List[torch.Tensor], torch.Tensor]:
         """
-        Encodes a list of images into embeddings.
+        Encodes a list of images or a single image into embedding(s).
 
         Args:
             images: image(s) to encode, can be PIL Image(s), URL(s), or local file path(s)
@@ -497,7 +497,7 @@ class JinaEmbeddingsV4Model(Qwen2_5_VLForConditionalGeneration):
             max_pixels: Maximum number of pixels to process per image
 
         Returns:
-            List of image embeddings as tensors or numpy arrays
+            List of image embeddings as tensors or numpy arrays when encoding multiple images, or single image embedding as tensor when encoding a single image
         """
         if max_pixels:
             default_max_pixels = self.processor.image_processor.max_pixels
@@ -525,7 +525,7 @@ class JinaEmbeddingsV4Model(Qwen2_5_VLForConditionalGeneration):
         if max_pixels:
             self.processor.image_processor.max_pixels = default_max_pixels
 
-        return embeddings
+        return embeddings if len(images) > 1 else embeddings[0]
 
     @classmethod
     def from_pretrained(