mirror of
https://github.com/danswer-ai/danswer.git
synced 2025-09-27 20:38:32 +02:00
Title Truncation Logic (#1828)
This commit is contained in:
@@ -110,7 +110,7 @@ def chunk_document(
|
|||||||
tokenizer = get_default_tokenizer()
|
tokenizer = get_default_tokenizer()
|
||||||
|
|
||||||
title = document.get_title_for_document_index()
|
title = document.get_title_for_document_index()
|
||||||
title_prefix = f"{title}{RETURN_SEPARATOR}"[:MAX_CHUNK_TITLE_LEN] if title else ""
|
title_prefix = f"{title[:MAX_CHUNK_TITLE_LEN]}{RETURN_SEPARATOR}" if title else ""
|
||||||
title_tokens = len(tokenizer.tokenize(title_prefix))
|
title_tokens = len(tokenizer.tokenize(title_prefix))
|
||||||
|
|
||||||
metadata_suffix = ""
|
metadata_suffix = ""
|
||||||
|
Reference in New Issue
Block a user