[Bug]: Incorrect Return Type in EarningsCallTranscript.load_data()

[alaia0a]

Bug Description

The load_data() function in the EarningsCallTranscript class currently returns a single Document object directly instead of a List[Document] as per its type hint.

Version

0.11.6

Steps to Reproduce

1. Call the load_data() method.
2. Try to pass the result to VectorStoreIndex.from_documents(): python

   documents = loader.load_data()
   index = VectorStoreIndex.from_documents(documents)

3. The following error occurs: AttributeError: 'Document' object has no attribute 'get_doc_id'

Relevant Logs/Tracbacks

No response

[dosubot[bot]]

Hey there, @alaia0a! I'm here to assist you with any bugs, questions, or contributions. Let's tackle this issue together!

The issue arises because the load_data() function in the EarningsCallTranscript class returns a single Document object instead of a List[Document] as per its type hint. This discrepancy causes an AttributeError when used with VectorStoreIndex.from_documents(), which expects a list of Document objects.

To fix this, modify the load_data() function to return a list containing the Document object:

def load_data(self) -> List[Document]:
    resp_dict, speakers_list = get_earnings_transcript(
        self.quarter, self.ticker, self.year
    )
    return [Document(
        text=resp_dict["content"],
        extra_info={
            "ticker": resp_dict["symbol"],
            "quarter": "Q" + str(resp_dict["quarter"]),
            "date_time": resp_dict["date"],
            "speakers_list": speakers_list,
        },
    )]

This change ensures that the load_data() method returns a list of Document objects, which is compatible with VectorStoreIndex.from_documents() ^[1].

To continue talking to Dosu, mention @dosu.