samterfa / openai Goto Github PK

why my try is not working as your animated GIF shows? nothing comes out. please see my code in the picture:

Thanks
Eric

Dear author,

Thanks a lot for your great tool!

May I have your guidance that how to make the add-in work? After library(openai), and then type # write some R code ..., no code is generated automatically, is it due to the addin content interactive: False?

Many thanks!

HI!

I am trying to use this very cool tool but get the following error when I try to add the addin.

Error in (function (prompt = rstudioapi::getConsoleEditorContext()$contents, :
list(message = "You exceeded your current quota, please check your plan and billing details.", type = "insufficient_quota", param = NULL, code = NULL)

Error in map_chr():
ℹ In index: 1.
ℹ With name: text.
Caused by error in .x$text:
! $ operator is invalid for atomic vectors
Run rlang::last_trace() to see where the error occurred.

create_completion(
model = 'davinci',
max_tokens = 30,
temperature = .5,
top_p = 1,
n = 1,
stream = F,
prompt = 'Once upon a time') %>%
pluck('choices') %>%
map_chr(~ .x$text)

I have NO idea how to fix this.

After following the installation and set-up steps (here), when I click on the XXX, I received this message:
Error in (function(prompt=rstudioapi::getConsoleEditorContext()$contents,:list(message = "You exceeded your current quota, please check your plan billing details", type = "insuficient_quota", param = NULL, code = NULL)...

I was wondering if is mandatory to pay to use the API, is that the main problem?

Thanks!

library(openai)
library(purrr)
library(magrittr)
library(dplyr)

list_models() %>% pluck('data') %>% map_dfr(compact)

Show in New Window
Error in namespaceExport(ns, exports) :
undefined exports: %has_args%, %has_attr%, %has_name%, on_failure<-, are_equal, assert_that, has_args, has_attr, has_extension, has_name, is.count, is.date, is.dir, is.error, is.flag, is.number, is.readable, is.scalar, is.string, is.time, is.writeable, noNA, not_empty, on_failure, see_if, validate_that

Hi, I got this error trying to install the pkg from github. Is there any prob with the export of the function?

Downloading GitHub repo samterfa/openai@HEAD
── R CMD build ─────────────────────────────────────────────────────────────────────
✔  checking for file 'C:\Users\Luca\AppData\Local\Temp\RtmpM9cJU1\remotes205c280d3682\samterfa-openai-73480e9/DESCRIPTION'
─  preparing 'openai':
✔  checking DESCRIPTION meta-information ...
─  checking for LF line-endings in source and make files and shell scripts
─  checking for empty or unneeded directories
─  building 'openai_0.0.1.tar.gz'
   
Installing package into ‘C:/Users/Luca/Documents/2023.efsa_inventory/renv/library/R-4.3/x86_64-w64-mingw32’
(as ‘lib’ is unspecified)
- The project is out-of-sync -- use `renv::status()` for details.
* installing *source* package 'openai' ...
** using staged installation
** R
** inst
** byte-compile and prepare package for lazy loading
** help
*** installing help indices
** building package indices
** testing if installed package can be loaded from temporary location
Error: package or namespace load failed for 'openai' in namespaceExport(ns, exports):
 undefined exports: create_chat_completions
Error: loading failed
Execution halted
ERROR: loading failed
* removing 'C:/Users/Luca/Documents/2023.efsa_inventory/renv/library/R-4.3/x86_64-w64-mingw32/openai'
Warning messages:
1: In untar2(tarfile, files, list, exdir, restore_times) :
  skipping pax global extended headers
2: In untar2(tarfile, files, list, exdir, restore_times) :
  skipping pax global extended headers
3: In i.p(...) :
  installation of package ‘C:/Users/Luca/AppData/Local/Temp/RtmpM9cJU1/file205c5b137984/openai_0.0.1.tar.gz’ had non-zero exit status```

I get the following error, both as a dialog and on the shell.

Error in (function (prompt = rstudioapi::getConsoleEditorContext()$contents, :
list(message = "This model's maximum context length is 4097 tokens. However, you requested 4105 tokens (101 in the messages, 4004 in the completion). Please reduce the length of the messages or completion.", type = "invalid_request_error", param = "messages", code = "context_length_exceeded")

When typing the prompt "Load mtcars data and create boxplot" in the console, I receive the following return:
Here's how to load the mtcars data and create a basic boxplot of the mpg variable using R:
Error: unexpected symbol in "load mtcars"

I am using R 4.2.3 with most recent version of R studio and Windows 11

Can I specify to use GPT 4 engine instead of GPT 3.5?

list_models() %>%
pluck('data') %>%
map_dfr(compact)
Error in dplyr::bind_rows():
! Argument 1 must be a data frame or a named atomic vector.
Run rlang::last_trace() to see where the error occurred.
Warning message:
Outer names are only allowed for unnamed scalar atomic inputs

chatgpt:::run_addin_ask_chatgpt()

Listening on http://127.0.0.1:3999

***** ChatGPT input:**

Please help:
list_models() %>%
pluck('data') %>%
map_dfr(compact)

Error in dplyr::bind_rows():
! Argument 1 must be a data frame or a named atomic vector.
Run rlang::last_trace() to see where the error occurred.
Warning message:
Outer names are only allowed for unnamed scalar atomic inputs
***** ChatGPT output:**

This error is telling us that the object being passed to map_dfr() is not a data frame or a named atomic vector. The issue could be with the compact() function that is being used in map_dfr().

It's also possible that the data being passed to map_dfr() is not in the correct format. It's hard to pinpoint the exact issue without knowing the details of list_models() and compact().

You can try running rlang::last_trace() to get more information about where the error occurred in your code. This may give you some clues as to what the issue might be.
MY SOLUTION:
DELETE " %>%
map_dfr(compact) "
Now it works.

Thank you so much for building and maintaining this!

I'm wondering if CRAN submission is on the roadmap.

And if you intend to make a reference website as well. Often handy for quickly sending around the function documentation.

Also wondering how we should think about this package in contrast with irudnyts's package?

Thank you 🙏