Adding Earning Call transcripts of US based companies #658
Conversation
|
It is complaining about the |
| ```python | ||
| from llama_index import download_loader | ||
|
|
||
| IMDBReviewsloader = download_loader('EarningCallTranscripts') |
There was a problem hiding this comment.
Hi @jerryjliu, thanks for your input
Yes I have done the nit changes and README ones too
| @@ -225,7 +226,7 @@ def main_scraper( | |||
|
|
|||
| print(f"Number of reviews scraped: {len(reviews_date)}") | |||
| if generate_csv: | |||
| os.makedirs("movie_reviews", exist_ok=True) | |||
| os.makedirs(reviews_folder, exist_ok=True) | |||
There was a problem hiding this comment.
do we need to make this change in this PR? if there's imdb changes let's make that in a sep PR
There was a problem hiding this comment.
I contributed imdb_scraper sometime back, but this was just a minor change that does not change much. For making it a separate PR, do I have to undo the changes and commit again, or is there any other way? Sorry if this is a stupid question
| #### Llama Index | ||
| ```python | ||
| from llama_index import download_loader | ||
| from llama_index import GPTVectorStoreIndex, download_loader |
There was a problem hiding this comment.
GPTVectorStoreIndex is outdated, it's now just VectorStoreIndex
There was a problem hiding this comment.
Yes I have done this change, thanks
Description
This loader will help users get the earning call transcripts of different US-based companies. Also, added a reviews folder argument for the IMDB movie reviews loader
Fixes # (issue)
Type of Change
Please delete options that are not relevant.
How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration
Suggested Checklist:
make format; make lintto appease the lint gods