Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [api]

22 questions
4
votes
1 answer

Any advantage of sklearn wrappers for xgboost over python API?

Are there any advantages of using the XGBoost sklearn wrappers XGBRegressor or XGBClassifier over using the Python API with the train method? Is one faster than the other or does one use less memory than the other? I am asking for a generic case…
devdmj
  • 43
  • 3
4
votes
1 answer

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

I am a beginner. I purchased tokens to use GPT-4 and finally figured out how to import the GPT-4 model into my Jupyter Notebook. %env OPENAI_API_KEY= (my key goes here) !pip install --upgrade openai wandb from openai import OpenAI LLM =…
Mas
  • 55
  • 4
3
votes
2 answers

Speed up Keras Model Prediction Load Times

I am trying to create a prediction API using keras which loads the model predicts and closes the model. But initializing time in python is about 3-5 secs so each request takes around 5 secs to return the prediction irrespective of number inputs…
Avinash S Karanth
  • 41
  • 3
2
votes
1 answer

Google Colab vs paid ai api

I am working on creating a dataset for fine tuning and i need ai. my pipeline is ready to use but from your experience what do u think is cheaper for the pipeline? get subscription on COLAB and install ai on it or get any ai API platforms?
Mostafa Hamza
  • 21
  • 1
2
votes
1 answer

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

Regarding the use of OpenAI API, Terms of Use at OpenAI mentions: You can opt out of having Content used for improvement by contacting support@openai.com with your organization ID. Please note that in some cases this may limit the ability of our…
Franck Dernoncourt
  • 5,862
  • 12
  • 44
  • 80
1
vote
1 answer

How to operate dataset from paperswithcode.com?

I'm trying to use IG-3.5B-17k dataset from paperswithcode.com, but I can't figure out how to do that exactly. How to do it? I guess I need to use this site API? Am I even able to use this dataset?
taciturno
  • 137
  • 1
  • 9
1
vote
0 answers

Search for similar wikipedia articles based on a set of keywords

I want to solve two questions: Which wikipedia articles could be interesting to me based on a list of keywords that are generated by the search terms I normally use in google(received by google takeout)? Which wikipedia articles could be…
Pascal Widmann
  • 23
  • 3
1
vote
0 answers

Creating API For Accessing New Website

Is there a way to add a API in Orange Data Mining Tool to access a new website? An example would be can I create and add an API for CNN or MSNBC or FOXNEWS? Currently in Orange in the text mining add-on they only have a couple of websites plus…
James Messineo
  • 11
  • 2
1
vote
0 answers

What informatics tools will allow complex search in order to select full-text articles?

I'd like to search plant science literature (full text) to only return articles in which the word "three" appears four or more times in the full-text Methods section (presumably the best source of this information would be pubmed central). I've…
Abiologist
  • 11
  • 2
1
vote
1 answer

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

I am currently trying to develop a chrome extension for a project. My knowledge of Javascript is quite limited and this is my first using it, so I am trying to reduce as much as possible its use. The extension scope will be basically extracting the…
Manuel
  • 11
  • 2
1
vote
0 answers

ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type int) in Python - from_gerator fails

I know this question has answers, but they are not working. why this fails ? (and why tensorflow has troubles in reading numpy!!) def data_generator(df): for index, row in df.iterrows(): audio = row['audio'] # Replace 'audio' with the…
user305883
  • 175
  • 9
1
vote
0 answers

Is it possible to access "Data Science" on Stack Exchange using an API?

I am a programmer with C and Python knowledge. I am trying to "educate" or train my Chatbot with name "Stella" in "Science and Technology History" and related areas, helped by ChatGPT 3.5. I am already using contents provided by Wikipedia, but some…
user545577
  • 11
  • 1
1
vote
1 answer

Alternatives to twitter for large daily or weekly samples for sentiment analysis

Twitter, with their API, including the free tier, has been a go-to source for collecting large samples of texts expressing sentiment on various topics of interest. I just started a project in December to collect, over the long term, sentiment about…
ViennaMike
  • 121
  • 4
0
votes
1 answer

I keep getting an error message in R while using twitteR

here is what I am doing: tweets=searchTwitter("walmart",n=3000, lang="en",since="2021-01-08",until="2021-01-10") And this is my error message: Warning message: In doRppAPICall("search/tweets", n, params = params, retryOnRateLimit =…
Graciela Colin
  • 1
0
votes
1 answer

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

There are many datasets that are released on the internet. Authors of many of these datasets state that the datasets are strictly for academic usage and not for commercial purposes. Although some datasets are released for both academic and…
Devashish Prasad
  • 864
  • 8
  • 17
1
2