extend langchain splitter with character splitter

cognee/infrastructure/data/chunking/LangchainChunkingEngine.py

@@ -29,6 +29,9 @@ class LangchainChunkEngine():
 
         if chunk_strategy == ChunkStrategy.CODE:
             chunked_data = LangchainChunkEngine.chunk_data_by_code(source_data,chunk_size, chunk_overlap)
+
+        elif chunk_strategy == ChunkStrategy.LANGCHAIN_CHARACTER:
+            chunked_data = LangchainChunkEngine.chunk_data_by_character(source_data,chunk_size, chunk_overlap)
         else:
             chunked_data = DefaultChunkEngine.chunk_data_by_paragraph(source_data,chunk_size, chunk_overlap)
         return chunked_data
@@ -50,3 +53,12 @@ class LangchainChunkEngine():
 
         return only_content
 
+    def chunk_data_by_character(self, data_chunks, chunk_size, chunk_overlap):
+        from langchain_text_splitters import RecursiveCharacterTextSplitter
+        splitter = RecursiveCharacterTextSplitter(chunk_size, chunk_overlap)
+        data = splitter.split(data_chunks)
+
+        only_content = [chunk.page_content for chunk in data]
+
+        return only_content
+

cognee/shared/data_models.py

@@ -35,6 +35,7 @@ class ChunkStrategy(Enum):
     PARAGRAPH = "paragraph"
     SENTENCE = "sentence"
     CODE    = "code"
+    LANGCHAIN_CHARACTER = "langchain_character"
 
 class MemorySummary(BaseModel):
     """ Memory summary. """