AttributeError: 'str' object has no attribute 'page_content'

[SnoopyDevelops]

https://python.langchain.com/en/latest/use_cases/question_answering/semantic-search-over-chat.html

https://github.com/hwchase17/langchain/blob/master/docs/use_cases/question_answering/semantic-search-over-chat.ipynb

Apparently, split_documents function's input need to have attributes of page_content and metadata, but getting string list as input here

[PawelFaron]

Please provide working code that can reproduce this issue.

[SnoopyDevelops]

https://github.com/hwchase17/langchain/blob/master/docs/use_cases/question_answering/semantic-search-over-chat.ipynb

3. Ingest chat embeddings

with open("messages.txt") as f:
    state_of_the_union = f.read()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
pages = text_splitter.split_text(state_of_the_union)

text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
texts = text_splitter.split_documents(pages)

[PawelFaron]

As for me it looks like a bug in that example.
Change this:
texts = text_splitter.split_documents(pages)
To this:
texts = text_splitter.create_documents(pages)

[SnoopyDevelops]

It worked. Can I create a pull request to fix this issue?

[PawelFaron]

Sorry I created it already.

[SnoopyDevelops]

No problem, Thanks for your help

[ccwdb]

Thanks for helpping!