`TokenTextSplitter` start indices are sometimes -1

### Checked other resources - [x] I added a very descriptive title to this issue. - [x] I searched the LangChain documentation with the integrated search. - [x] I used the GitHub search to find a similar question and didn't find it. - [x] I am sure that this is a bug in LangChain rather than my code. - [x] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package). ### Example Code To reproduce: ```python from langchain_text_splitters import TokenTextSplitter text = """ "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum." """ chunker = TokenTextSplitter(add_start_index=True, chunk_size=10, chunk_overlap=5) chunker.create_documents([text]) > the result contains examples with -1 as start-index ``` ### Error Message and Stack Trace (if applicable) _No response_ ### Description There is a problem with start indices because of how `TokenTextSplitter` inherits from `TextSplitter`. The `create_documents` method presumes that `self._chunk_overlap` contains a number expressing the number of characters, however with a tokenizer this becomes the number of *tokens* and thus the correct piece of text might not be found: ```python def create_documents( self, texts: List[str], metadatas: Optional[List[dict]] = None ) -> List[Document]: """Create documents from a list of texts.""" _metadatas = metadatas or [{}] * len(texts) documents = [] for i, text in enumerate(texts): index = 0 previous_chunk_len = 0 for chunk in self.split_text(text): m…