How to use Webwrite to call REST APIs successfully, eg OpenAI API

조회 수: 38 (최근 30일)
CdC
CdC 2023년 3월 6일
댓글: Radoslav Kriz 2024년 1월 6일
Webwrite Produces Error Though Seemingly Identical CURL Request Is Successful at Calling OpenAI API
This matlab code doesn't work. Can anyone figure out why?
prompt = 'Hello, how are you today?';
data = struct('prompt', prompt, 'temperature', 0.7, 'max_tokens', 60);
options = weboptions('RequestMethod','POST','MediaType','application/json','KeyName','Authorization','KeyValue','Bearer xxx');
response = webwrite(url,data,options)
The code generates a server error:
The server returned the status 400 with message "Bad Request" in response to the request to URL
https://api.openai.com/v1/completions.
This code was based on a working CURL example below that successfully calls the openAI API.
In each case, the Authorization xxx is replaced with a functional openAI api key.
Working CURL:
## cURL
curl -X "POST" "https://api.openai.com/v1/chat/completions" \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer xxxxx' \
-d $'{
"model": "gpt-3.5-turbo",
"messages": [
{
"content": "Hello!",
"role": "user"
}
]
}'
This is running on a Mac with up to date OS. This is true using Matlab 2022b or 2023a prerelease.
Thank you for your help

채택된 답변

CdC
CdC 2023년 3월 9일
Thank you for the answer above. Based on it, I created the following function. This is both a working example of how to call rest apis, and a working example of how to call the openAI Chat api. It remains unclear to me why we need to use matlab.net and why webwrite doesn't work, given that this would apepar to be webrite's function.
function [result,tokens] = openAIChat(content)
%openAIChat Call openAI REST API for chat completions
% Detailed explanation goes here
tic
import matlab.net.*
import matlab.net.http.*
% Define the API endpoint Davinci
api_endpoint = "https://api.openai.com/v1/chat/completions";
% Define the API key from https://beta.openai.com/account/api-keys
api_key = "xxxxxxx";
data = jsondecode('{"model":"gpt-3.5-turbo","messages":[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is my birthday?"}]}');
data.messages(2).content = content;
% Define the headers for the API request
headers = matlab.net.http.HeaderField('Content-Type', 'application/json');
headers(2) = matlab.net.http.HeaderField('Authorization', 'Bearer ' + api_key);
% Define the request message
request = matlab.net.http.RequestMessage('post',headers,data);
% Send the request and store the response
response = send(request, URI(api_endpoint));
% Extract the response text
result = response.Body.Data.choices.message.content;
tokens = response.Body.Data.usage;
%disp(result);
end

추가 답변 (2개)

Toshiaki Takeuchi
Toshiaki Takeuchi 2023년 3월 23일
Here is a MATLAB app that provides sample prompts as presets, and you can run chat-generated MATLAB code inside the app. People often struggle with prompt engineering, and the presets gives you a good starting point.
You can either download it from GitHub into your MATLAB path or use "Open in MATLAB Online" to import the repo into MATLAB Online. Once you have the API key, you can set it up in the OS environment variable.
setenv("OPENAI_API_KEY","your key here")
Finally, double click on MatGPT.mlapp to open it in App Designer and run it there.
If you would rather use command line interface, you can use chatGPT class included in the repo.

the cyclist
the cyclist 2023년 3월 7일
I did not carefully look at your code, but there was recently discussion at this question, which reached a successful conclusion (including pointers to a couple File Exchange submission).
I expect it will be helpful toward goal.
  댓글 수: 1
CdC
CdC 2023년 3월 9일
Thanks for your help. Please note posted code based on your answer and link.

댓글을 달려면 로그인하십시오.

카테고리

Help CenterFile Exchange에서 Web Services에 대해 자세히 알아보기

태그

제품


릴리스

R2022b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by