fix overlap and splitter optimization (#2742)

Co-authored-by: jyong <[email protected]>
langgenius · Mar 7, 2024 · 8ba38e8 · 8ba38e8
1 parent b163545
commit 8ba38e8
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 4 deletions.
diff --git a/api/core/rag/index_processor/index_processor_base.py b/api/core/rag/index_processor/index_processor_base.py
@@ -52,7 +52,7 @@ def _get_splitter(self, processing_rule: dict,
 
             character_splitter = FixedRecursiveCharacterTextSplitter.from_encoder(
                 chunk_size=segmentation["max_tokens"],
-                chunk_overlap=0,
+                chunk_overlap=segmentation.get('chunk_overlap', 0),
                 fixed_separator=separator,
                 separators=["\n\n", "。", ".", " ", ""],
                 embedding_model_instance=embedding_model_instance
@@ -61,7 +61,7 @@ def _get_splitter(self, processing_rule: dict,
             # Automatic segmentation
             character_splitter = EnhanceRecursiveCharacterTextSplitter.from_encoder(
                 chunk_size=DatasetProcessRule.AUTOMATIC_RULES['segmentation']['max_tokens'],
-                chunk_overlap=0,
+                chunk_overlap=DatasetProcessRule.AUTOMATIC_RULES['segmentation']['chunk_overlap'],
                 separators=["\n\n", "。", ".", " ", ""],
                 embedding_model_instance=embedding_model_instance
             )

diff --git a/api/core/splitter/text_splitter.py b/api/core/splitter/text_splitter.py
@@ -30,7 +30,7 @@ def _split_text_with_regex(
     if separator:
         if keep_separator:
             # The parentheses in the pattern keep the delimiters in the result.
-            _splits = re.split(f"({separator})", text)
+            _splits = re.split(f"({re.escape(separator)})", text)
             splits = [_splits[i] + _splits[i + 1] for i in range(1, len(_splits), 2)]
             if len(_splits) % 2 == 0:
                 splits += _splits[-1:]
@@ -94,7 +94,7 @@ def create_documents(
                 documents.append(new_doc)
         return documents
 
-    def split_documents(self, documents: Iterable[Document]) -> list[Document]:
+    def split_documents(self, documents: Iterable[Document] ) -> list[Document]:
         """Split documents."""
         texts, metadatas = [], []
         for doc in documents: