Fix/langchain document schema (#2539)

Co-authored-by: jyong <jyong@dify.ai>

api/core/rag/models/document.py

@@ -1,4 +1,6 @@
-from typing import Optional
+from abc import ABC, abstractmethod
+from collections.abc import Sequence
+from typing import Any, Optional
 
 from pydantic import BaseModel, Field
 
@@ -14,3 +16,64 @@ class Document(BaseModel):
     metadata: Optional[dict] = Field(default_factory=dict)
 
 
+class BaseDocumentTransformer(ABC):
+    """Abstract base class for document transformation systems.
+
+    A document transformation system takes a sequence of Documents and returns a
+    sequence of transformed Documents.
+
+    Example:
+        .. code-block:: python
+
+            class EmbeddingsRedundantFilter(BaseDocumentTransformer, BaseModel):
+                embeddings: Embeddings
+                similarity_fn: Callable = cosine_similarity
+                similarity_threshold: float = 0.95
+
+                class Config:
+                    arbitrary_types_allowed = True
+
+                def transform_documents(
+                    self, documents: Sequence[Document], **kwargs: Any
+                ) -> Sequence[Document]:
+                    stateful_documents = get_stateful_documents(documents)
+                    embedded_documents = _get_embeddings_from_stateful_docs(
+                        self.embeddings, stateful_documents
+                    )
+                    included_idxs = _filter_similar_embeddings(
+                        embedded_documents, self.similarity_fn, self.similarity_threshold
+                    )
+                    return [stateful_documents[i] for i in sorted(included_idxs)]
+
+                async def atransform_documents(
+                    self, documents: Sequence[Document], **kwargs: Any
+                ) -> Sequence[Document]:
+                    raise NotImplementedError
+
+    """  # noqa: E501
+
+    @abstractmethod
+    def transform_documents(
+        self, documents: Sequence[Document], **kwargs: Any
+    ) -> Sequence[Document]:
+        """Transform a list of documents.
+
+        Args:
+            documents: A sequence of Documents to be transformed.
+
+        Returns:
+            A list of transformed Documents.
+        """
+
+    @abstractmethod
+    async def atransform_documents(
+        self, documents: Sequence[Document], **kwargs: Any
+    ) -> Sequence[Document]:
+        """Asynchronously transform a list of documents.
+
+        Args:
+            documents: A sequence of Documents to be transformed.
+
+        Returns:
+            A list of transformed Documents.
+        """