I'm currently working with llama index trying to parse a column of my pandas dataframe as a Document object with llama index with the final goal of fitting my data into an LLM (I'm using gpt-4-32k). Does anyone know how to do this without explicitly converting to an unstructured datasource (ie. a doc) which seems counterintuitive?
#First I save my data into an array (of strings)
text_list = concatenated_text_array = uniqueness_data['concatenated_text'].to_numpy().flatten()
#Then I try to cast each element to the Document object
documents = [Document(t) for t in text_list]
#and receive this error:
documents = [Document(t) for t in text_list]
^^^^^^^^^^^
File "pydantic/main.py", line 332, in pydantic.main.BaseModel.__init__
TypeError: __init__() takes exactly 1 positional argument (2 given)
