From 43064b1572e8218d49d85a36cad6af8dfcd193ee Mon Sep 17 00:00:00 2001
From: Christoph Eder <ce1@live.de>
Date: Sat, 13 Dec 2025 18:14:08 +0100
Subject: [PATCH] Changes in embedding.py, phrase.py, word.py     Adopted
 serialisation schema to last commit

---
 anansyTypes/structures/embedding.py | 14 +++++++---
 anansyTypes/structures/phrase.py    | 41 ++++++++++++++---------------
 anansyTypes/structures/word.py      | 24 +++++++----------
 3 files changed, 40 insertions(+), 39 deletions(-)

diff --git a/anansyTypes/structures/embedding.py b/anansyTypes/structures/embedding.py
index 3cbffd0..9553cdb 100644
--- a/anansyTypes/structures/embedding.py
+++ b/anansyTypes/structures/embedding.py
@@ -26,16 +26,22 @@ class Embedding:
     @classmethod
     def from_dict(cls, data: dict) -> "Embedding":
         return cls(data=np.array(data["data"], dtype=np.float32))
-    
+
     @classmethod
     def __get_pydantic_core_schema__(cls, source_type: Any, handler):
         from pydantic_core import core_schema
-        
+
+        def validate_embedding(value):
+            if isinstance(value, cls):
+                return value
+            if isinstance(value, dict):
+                return cls.from_dict(value)
+            raise ValueError(f"Cannot convert {type(value)} to Embedding")
+
         return core_schema.with_info_plain_validator_function(
-            lambda value, _: cls.from_dict(value) if isinstance(value, dict) else value,
+            lambda value, _: validate_embedding(value),
             serialization=core_schema.plain_serializer_function_ser_schema(
                 lambda x: {"data": x.data.tolist()},
                 when_used="json",
             ),
         )
-
diff --git a/anansyTypes/structures/phrase.py b/anansyTypes/structures/phrase.py
index 9252afe..a5dba06 100644
--- a/anansyTypes/structures/phrase.py
+++ b/anansyTypes/structures/phrase.py
@@ -14,39 +14,38 @@ class Phrase(Lexeme):
     @property
     def content(self) -> str:
         return self._content
-    
+
     @property
     def embedding(self) -> Embedding:
         return self._embedding
-    
+
     @classmethod
-    def from_dict(cls, data: dict) -> 'Phrase':
+    def from_dict(cls, data: dict) -> "Phrase":
         return cls(
-            id=data['id'],
-            content=data['content'],
-            embedding=Embedding.from_dict(data['embedding'])
+            id=data["id"],
+            content=data["content"],
+            embedding=Embedding.from_dict(data["embedding"]),
         )
 
     @classmethod
     def __get_pydantic_core_schema__(cls, source_type: Any, handler):
         from pydantic_core import core_schema
-        
-        return core_schema.no_info_after_validator_function(
-            lambda x: x if isinstance(x, cls) else cls(**x),
-            core_schema.typed_dict_schema(
-                {
-                    'id': core_schema.typed_dict_field(handler.generate_schema(int)),
-                    'content': core_schema.typed_dict_field(handler.generate_schema(str)),
-                    'embedding': core_schema.typed_dict_field(handler.generate_schema(Embedding)),
-                }
-            ),
+
+        def validate_phrase(value):
+            if isinstance(value, cls):
+                return value
+            if isinstance(value, dict):
+                return cls.from_dict(value)
+            raise ValueError(f"Cannot convert {type(value)} to Phrase")
+
+        return core_schema.with_info_plain_validator_function(
+            lambda value, _: validate_phrase(value),
             serialization=core_schema.plain_serializer_function_ser_schema(
                 lambda x: {
-                    'id': x.id,
-                    'content': x.content,
-                    'embedding': x.embedding
+                    "id": x.id,
+                    "content": x.content,
+                    "embedding": {"data": x.embedding.data.tolist()},
                 },
-                when_used='json',
+                when_used="json",
             ),
         )
-
diff --git a/anansyTypes/structures/word.py b/anansyTypes/structures/word.py
index abea127..9f1128c 100644
--- a/anansyTypes/structures/word.py
+++ b/anansyTypes/structures/word.py
@@ -36,24 +36,20 @@ class Word(Lexeme):
     def __get_pydantic_core_schema__(cls, source_type: Any, handler):
         from pydantic_core import core_schema
 
-        return core_schema.no_info_after_validator_function(
-            lambda x: x if isinstance(x, cls) else cls(**x),
-            core_schema.typed_dict_schema(
-                {
-                    "id": core_schema.typed_dict_field(handler.generate_schema(int)),
-                    "content": core_schema.typed_dict_field(
-                        handler.generate_schema(str)
-                    ),
-                    "embedding": core_schema.typed_dict_field(
-                        handler.generate_schema(Embedding)
-                    ),
-                }
-            ),
+        def validate_word(value):
+            if isinstance(value, cls):
+                return value
+            if isinstance(value, dict):
+                return cls.from_dict(value)
+            raise ValueError(f"Cannot convert {type(value)} to Word")
+
+        return core_schema.with_info_plain_validator_function(
+            lambda value, _: validate_word(value),
             serialization=core_schema.plain_serializer_function_ser_schema(
                 lambda x: {
                     "id": x.id,
                     "content": x.content,
-                    "embedding": x.embedding,  # Let Pydantic serialize Embedding
+                    "embedding": {"data": x.embedding.data.tolist()},
                 },
                 when_used="json",
             ),