4 votes
Accepted

How do I prompt GPT-4 to look at a PDF in Jupyter Notebook?

OpenAI's API does not support providing PDFs. Therefore, what you intend to do is not possible. You have other options though: Parse the PDF locally and send text to GPT4. The parse may consist of ...
noe's user avatar
  • 26.6k
3 votes
Accepted

Any advantage of sklearn wrappers for xgboost over python API?

One advantage of using scikit-learn wrappers is that they are more likely to work within the scikit-learn ecosystem. For example, it might be easier to put the algorithm into pipelines.
Brian Spiering's user avatar
2 votes
Accepted

Can we identify that an academic dataset was used for commercial purpose

If the model is a discriminative model (e.g. a classification model), it is highly unlikely that you can identify whether it was trained with some specific dataset. If the model is generative, (e.g. a ...
noe's user avatar
  • 26.6k
2 votes
Accepted

How to operate dataset from paperswithcode.com?

This is specified in the dataset description in paperswithcode.com (emphasis mine): IG-3.5B-17k is an internal Facebook AI Research dataset for training image classification models. It consists of ...
noe's user avatar
  • 26.6k
1 vote

Speed up Keras Model Prediction Load Times

I was able to get to work like this without flask or django. Just using default http.server in python ...
Avinash S Karanth's user avatar
1 vote

Storing XML data from thousands of API calls

store the data returned by the API calls ... I was going to propose: option (4.) Save the data from each XML file in a new row in a DB. And then, fortunately, I saw: In a subsequent step the raw ...
J_H's user avatar
  • 1,055
1 vote

What is the most straightforward way to run python code in a chrome extension?

I would recommend looking into Brython. This is an implementation of Python that the underlying library converts into Javascript. It isn't a complete drop-in solution as it still suffers from ...
Robert Rapplean's user avatar
1 vote
Accepted

Does opting out of having my content used for improvement mean there are no other forms of data retention of my content by OpenAI?

Does opting out of having my content used for improvement mean there are no other forms of data retention of my content by OpenAI? Since March 1, by default, "OpenAI will not use data submitted ...
Franck Dernoncourt's user avatar
1 vote

Is there any differences between using text-davinci-003 with the Azure API vs. with the OpenAI API?

I'm also asking myself the same question to figure out whether it's worth migrating for increased availability or is Azure simply wrapping the original API. This is the only info I was able to find on ...
Larry Fishermann's user avatar
1 vote
Accepted

training gradient boosting algorithm in python testing in Golang

There's actually a few libraries that handle the inference part well. https://github.com/dmitryikh/leaves is probably the most common one and seems to fit your need.
Tophat's user avatar
  • 2,420
1 vote

Historical exchange rate data via World Bank API?

I don't think so, since: USD is usually used as a reference. Providing exchange rates for all possible pairs would be to much data. If there are 100 countries, there would be 100! (factorial) ...
Eugen's user avatar
  • 457

Only top scored, non community-wiki answers of a minimum length are eligible