Zach Schillaci
Zach Schillaci
Thanks for the amazing open source work! For certain data-sensitive projects, it may be important to silo the database and its contents (aside from table/column names) from any calls to...
As referenced in other issues (see #814, #1026), the current implementation of `LLMMathChain` allows for prompt injection attacks which can execute arbitrary code using Python's `exec` method. As a quick...
The Python `wikipedia` package gives easy access for searching and fetching pages from Wikipedia, see https://pypi.org/project/wikipedia/. It can serve as an additional search and retrieval tool, like the existing Google...
Surface separate `kwargs` for `Agent` and `AgentExecutor` in a consistent way for the agent toolkits. Following the example in `create_pbi_agent` and `create_pbi_chat_agent`,`agent_kwargs` and `kwargs` are now accessible for all `AgentExecutor`...
See #4770, #4784
Is it possible to continue the initial autoregressive pre-training on a custom dataset, as was done for Code Llama - Python? This would in principle allow for the fine-tuning of...
Add a simple print message when calling `plot_contour` or `plot_surface` if `pos_history` is greater than 2 dimensions warning the user that higher dimensions will be ignored for plotting.
When setting `columns_auto_size_mode=ColumnsAutoSizeMode.FIT_ALL_COLUMNS_TO_VIEW` the columns aren't refit correctly on the first table render. I have to first refresh the page to force the resizing. Am I missing something here?
When using `SetFit` for classification in a more technical domain, I could imagine the generically-trained `SBERT` models may produce poor sentence embeddings if the domain is not represented well enough...