Added validation to encoder model in multimodal models

Author: x-tabdeveloping

turftopic/models/cluster.py

@@ -208,6 +208,7 @@ def __init__(
             self.encoder_ = SentenceTransformer(encoder)
         else:
             self.encoder_ = encoder
+        self.validate_encoder()
         if vectorizer is None:
             self.vectorizer = default_vectorizer()
         else:

turftopic/models/ctm.py

@@ -159,6 +159,7 @@ def __init__(
             self.encoder_ = SentenceTransformer(encoder)
         else:
             self.encoder_ = encoder
+        self.validate_encoder()
         if vectorizer is None:
             self.vectorizer = default_vectorizer()
         else:

turftopic/models/decomp.py

@@ -87,6 +87,7 @@ def __init__(
             self.encoder_ = SentenceTransformer(encoder)
         else:
             self.encoder_ = encoder
+        self.validate_encoder()
         if vectorizer is None:
             self.vectorizer = default_vectorizer()
         else:

turftopic/models/gmm.py

@@ -87,6 +87,7 @@ def __init__(
             self.encoder_ = SentenceTransformer(encoder)
         else:
             self.encoder_ = encoder
+        self.validate_encoder()
         if vectorizer is None:
             self.vectorizer = default_vectorizer()
         else:

turftopic/models/keynmf.py

@@ -95,6 +95,7 @@ def __init__(
             self.encoder_ = SentenceTransformer(encoder)
         else:
             self.encoder_ = encoder
+        self.validate_encoder()
         if vectorizer is None:
             self.vectorizer = default_vectorizer()
         else:

turftopic/multimodal.py

@@ -5,6 +5,9 @@
 
 import numpy as np
 from PIL import Image
+from sentence_transformers import SentenceTransformer
+
+from turftopic.encoders.multimodal import MultimodalEncoder
 
 UrlStr = str
 
@@ -74,7 +77,8 @@ def encode_multimodal(
             "document_embeddings": document_embeddings,
         }
 
-    def validate_embeddings(self, embeddings: Optional[MultimodalEmbeddings]):
+    @staticmethod
+    def validate_embeddings(embeddings: Optional[MultimodalEmbeddings]):
         if embeddings is None:
             return
         try:
@@ -89,6 +93,16 @@ def validate_embeddings(self, embeddings: Optional[MultimodalEmbeddings]):
                 f"Shape mismatch between document_embeddings {document_embeddings.shape} and image_embeddings {image_embeddings.shape}"
             )
 
+    def validate_encoder(self):
+        if not hasattr(self.encoder_, "encode"):
+            if not all(
+                hasattr(self.encoder_, "get_text_embeddings"),
+                hasattr(self.encoder_, "get_image_embeddings"),
+            ):
+                raise TypeError(
+                    "An encoder must either have an encode() method or a get_text_embeddings and get_image_embeddings method (optionally get_fused_embeddings)"
+                )
+
     @abstractmethod
     def fit_transform_multimodal(
         self,