JBGruber / askgpt

A chat interface build on top of OpenAI's API endpoints
GNU General Public License v3.0
54 stars 5 forks source link

No output generated with `askgpt()` #9

Closed Lornebradia closed 1 year ago

Lornebradia commented 1 year ago

Running askgpt() with the default arguments does not output anything to the screen:

> askgpt("Tell me about the askgpt R package")
✔ GPT is thinking ⠧ [17.5s]
>

However the answer is available using response_history():

> response_history()[1] |> cat()
Askgpt is an R package that provides an easy-to-use interface for OpenAI's GPT-3 API. GPT-3 (Generative Pre-trained Transformer 3) is a powerful language generation model developed by OpenAI, which can be used to generate human-like text in a wide variety of formats.

The askgpt R package allows users to easily generate text using GPT-3 from within the R environment, making it easy to incorporate natural language generation into R-based projects. The package provides an R wrapper around the GPT-3 API, which allows users to access the full range of GPT-3 functions, including text completion, text classification, and text translation.

To use askgpt, users must first sign up for an OpenAI API key and create an account with OpenAI. Once they have an account, they can install the askgpt package in R using the R console or Rstudio, and they can begin generating text using the GPT-3 API by providing an API key and a text prompt. The package also provides functions for fine-tuning the GPT-3 model, controlling the output length and format, and filtering the output to remove unwanted content.

The askgpt R package is a powerful tool for natural language generation and can be used in a wide variety of applications, including data analysis, machine learning, and text mining. It provides an intuitive and user-friendly interface for accessing the GPT-3 API, making it easy for anyone to start generating high-quality human-like text in R.

If there's any missing step in the configuration, I don't know what it is.

> sessionInfo()
R version 4.3.0 (2023-04-21)
Platform: x86_64-apple-darwin20 (64-bit)
Running under: macOS Ventura 13.2.1

Matrix products: default
BLAS:   /System/Library/Frameworks/Accelerate.framework/Versions/A/Frameworks/vecLib.framework/Versions/A/libBLAS.dylib 
LAPACK: /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/lib/libRlapack.dylib;  LAPACK version 3.11.0

locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8

time zone: Europe/Warsaw
tzcode source: internal

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] askgpt_0.1.1

loaded via a namespace (and not attached):
 [1] jsonlite_1.8.4    dplyr_1.1.2       compiler_4.3.0    tidyselect_1.2.0 
 [5] reprex_2.0.2      clipr_0.8.0       assertthat_0.2.1  callr_3.7.3      
 [9] yaml_2.3.7        fastmap_1.1.1     R6_2.5.1          generics_0.1.3   
[13] curl_5.0.0        knitr_1.43        httr2_0.2.3       tibble_3.2.1     
[17] openssl_2.0.6     R.cache_0.16.0    pillar_1.9.0      R.utils_2.12.2   
[21] rlang_1.1.1       utf8_1.2.3        xfun_0.39         fs_1.6.2         
[25] cli_3.6.1         withr_2.5.0       magrittr_2.0.3    ps_1.7.5         
[29] digest_0.6.31     processx_3.8.1    rstudioapi_0.14   keyring_1.3.1    
[33] rappdirs_0.3.3    askpass_1.1       lifecycle_1.0.3   R.methodsS3_1.8.2
[37] R.oo_1.25.0       vctrs_0.6.2       evaluate_0.21     glue_1.6.2       
[41] styler_1.10.0     sessioninfo_1.2.2 fansi_1.0.4       rmarkdown_2.22   
[45] purrr_1.0.1       htmltools_0.5.5   tools_4.3.0       pkgconfig_2.0.3  
JBGruber commented 1 year ago

I manage to accidentally delete the line that actually prints the answer before submitting this to CRAN :man_facepalming:

Thank you so much for letting me know! Should work now (reinstall with remotes::install_github("JBGruber/askgpt")).