Commit History

Fix publishDate parsing to handle errors and localize timezone in vectorize function
7a785e1

gavinzli commited on

Refactor vectorizer module: clean up commented code and improve initialization logging
1a8947e

gavinzli commited on

Handle APIRequestError in collection creation and improve logging
b9d91b4

gavinzli commited on

Refactor vectorizer to create collection in AstraDB and improve logging
4f365e0

gavinzli commited on

Refactor vectorizer.py by removing commented-out code and improve error handling in stats.py during URL requests
65f1467

gavinzli commited on

Update collection name to "article" and adjust separator settings in vectorizer.py
f313f6f

gavinzli commited on

Change logging level to ERROR and increase retry delay to 10 seconds in vectorizer.py
c0eabca

gavinzli commited on

Update collection name to "articles" and enable separator regex in vectorization logic
4f4a669

gavinzli commited on

Remove redundant separator from vectorization logic in vectorizer.py
7dcce70

gavinzli commited on

Remove redundant separator from vectorization logic in vectorizer.py
ea62c80

gavinzli commited on

Refactor vectorization process by removing openai_vectorize calls and updating vectorizer initialization
5fea365

gavinzli commited on

Refactor content update process to ensure reference ID is set to None and re-enable vectorization functions in article processing
b68d569

gavinzli commited on

Add reference ID extraction and implement retry logic for document addition
693e166

gavinzli commited on

Refactor translation error handling and remove debug print statements in vectorization
0750507

gavinzli commited on

Add debug print statements in vectorize function for tracing execution flow
d20886e

gavinzli commited on

Update print statements in vectorize function to display DataFrame columns and chunk content for improved debugging
fdff7f3

gavinzli commited on

Add logging for DataFrame output in vectorize function and log content in _crawl function for better traceability
293d18b

gavinzli commited on

Remove print statements and commented-out DataFrame creation in vectorize function for cleaner code
ead6f2f

gavinzli commited on

Remove commented-out DataFrame column selection in vectorize function for cleaner code
d69af94

gavinzli commited on

Convert single dictionary to list of dictionaries in vectorize function for consistent DataFrame creation
579df96

gavinzli commited on

Refactor logging in multiple files to replace print statements with logging calls for better traceability
1c5f2e5

gavinzli commited on

Refactor error handling and improve logging in utils.py; update vectorization process in vectorizer.py; adjust variable naming in eastmoney.py
c39d841

gavinzli commited on

Update vectorizer.py
108738b
unverified

OxbridgeEconomics commited on

Update vectorizer.py
96825f6
unverified

OxbridgeEconomics commited on

Update vectorizer.py
99b66e9
unverified

OxbridgeEconomics commited on

Update vectorizer.py
ba224f2
unverified

OxbridgeEconomics commited on

Update vectorizer.py
7381b78
unverified

OxbridgeEconomics commited on

Update vectorizer.py
741bcee
unverified

OxbridgeEconomics commited on

Update vectorizer.py
1177da7
unverified

OxbridgeEconomics commited on

Update vectorizer.py
62095f0
unverified

OxbridgeEconomics commited on

Update vectorizer.py
62774df
unverified

OxbridgeEconomics commited on

commit
2dbc5e6

OxbridgeEconomics commited on

commit
948bb9c

OxbridgeEconomics commited on

commit
edb8f2e

OxbridgeEconomics commited on

commit
0f23641

OxbridgeEconomics commited on

commit
4e18ce3

OxbridgeEconomics commited on