- Current code reads conversations from a Slack channel from most recent to oldest.
- This adds a parameter that controls it in the `load_data` method.
* Fix Notion Loader: Database the loader is only loading the first 100 page_ids
During testing of the Notion Loader today, I noticed that I only received the first 100 pages when loading all pages from a database. Notion API returns the attribute has_more, and if this is true, we must request more pages. So this is the implementation of the fix.
* Implement suggestions from @emptycrown
* Update base.py
---------
Co-authored-by: Markus Odenthal <markus.odenthal@real-digital.de>
Co-authored-by: Jesse Zhang <jessetanzhang@gmail.com>
* add github repository, test a new way to download loader
* test imports when downloaded from gpt_index
* Refactor(Github Repo): Move github_client and utils to modules
* Moved github_client.py and utils.py from loader_hub/github_repo to modules/github_repo
* Updated import statements in base.py to reflect the new location
* temp
* Refactor(GithubRepositoryReader): Add github_client argument
- Add github_client argument to GithubRepositoryReader constructor
- Set default value for github_client argument
- Update docstring to reflect changes
* Refactor(Github Repo): Update init file
- Remove imports of base, github_client and utils
- Add imports of GithubRepositoryReader and GithubClient
- Update __all__ to include the new imports
* Fix(library): Update library.json
- Updated library.json to include __init__.py file
* Refactor(GithubRepositoryReader): Add filter for directories and files
- Add filter for directories and files in GithubRepositoryReader
- Ignore directories and files that do not pass the filter
- Print out if directory or file is ignored due to filter
* Refactor(BaseReader): Check filter files
- Refactor `_check_filter_files` to `_check_filter_file_extensions` in `BaseReader`
- Ignoring files due to filter
* Docs(FilterType): Add documentation for FilterType enum
- Add documentation for FilterType enum
- Explain what the enum is used for
- Describe the attributes of the enum
* Add(GPT Index): Add GPT Index example
Add GPT Index example to README
- Set OPENAI_API_KEY environment variable
- Download GithubRepositoryReader module
- Create GithubClient and GithubRepositoryReader
- Load data from Github Repository
- Create GPTSimpleVectorIndex
- Query the index
* Add(GPT Index): Add GPT Index example
Add GPT Index example to README
- Set OPENAI_API_KEY environment variable
- Download GithubRepositoryReader module
- Create GithubClient and GithubRepositoryReader
- Load data from Github Repository
- Create GPTSimpleVectorIndex
- Query the index
* Add(GPT Index): Add GPT Index example
Add GPT Index example to README
- Set OPENAI_API_KEY environment variable
- Download GithubRepositoryReader module
- Create GithubClient and GithubRepositoryReader
- Load data from Github Repository
- Create GPTSimpleVectorIndex
- Query the index
* change the import path for extras
* change import path for extra files to absolute
* Add test for GithubClient currently not using mocks which is not ideal
* Update test_github_reader.py
* Update test_github_reader.py
---------
Co-authored-by: Jesse Zhang <jessetanzhang@gmail.com>
