No response from Chat Gpt
Closed this issue · 9 comments
Do you have access to gpt-4
? If not, try to set gpt-3.5-turbo
. To be extra sure, restart VS code afterwards.
Is there a way to see logs?
Exiting VS Code and reopening it didn't help?
You can try this: https://stackoverflow.com/a/65938179
If this doesn't work, you can debug like so:
- Clone the project from this repo
- Open the project in VS Code
- Open
extension.ts
- Press F5
This should open a new VS Code instance in extension debug mode. Errors will be printed to the debug console
So it says too many requests. My api key shows never used on the dashboard.
Error fetching stream: Error: Request failed with status code 429
at createError (c:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\dist\webpack:\chatide\node_modules\axios\lib\core\createError.js:16:1)
at settle (c:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\dist\webpack:\chatide\node_modules\axios\lib\core\settle.js:17:1)
at RedirectableRequest.handleResponse (c:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\dist\webpack:\chatide\node_modules\axios\lib\adapters\http.js:278:1)
at RedirectableRequest.emit (C:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\lib\events.js:526:28)
at RedirectableRequest._processResponse (c:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\dist\webpack:\chatide\node_modules\follow-redirects\index.js:356:1)
at ClientRequest.RedirectableRequest._onNativeResponse (c:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\dist\webpack:\chatide\node_modules\follow-redirects\index.js:62:1)
at Object.onceWrapper (C:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\lib\events.js:646:26)
at ClientRequest.emit (C:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\lib\events.js:538:35)
at HTTPParser.parserOnIncomingClient (C:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\lib\_http_client.js:618:27)
at HTTPParser.parserOnHeadersComplete (C:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\lib\_http_common.js:128:17)
at TLSSocket.socketOnData (C:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\lib\_http_client.js:482:22)
at TLSSocket.emit (C:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\lib\events.js:526:28)
at addChunk (C:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\lib\internal\streams\readable.js:315:12)
at readableAddChunk (C:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\lib\internal\streams\readable.js:289:9)
at TLSSocket.Readable.push (C:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\lib\internal\streams\readable.js:228:10)
at TLSWrap.onStreamRead (C:\Users\acoop\Downloads\ChatIDE-main\ChatIDE-main\lib\internal\stream_base_commons.js:190:23)
at TLSWrap.callbackTrampoline (node:internal/async_hooks:130:17) {config: {…}, request: ClientRequest, response: {…}, isAxiosError: true, toJSON: ƒ, …}
response: {status: 429, statusText: 'Too Many Requests', headers: {…}, config: {…}, request: ClientRequest, …}
This seems to be coming from this catch
clause:
try {
const res = await openai.createChatCompletion({
model: modelString,
messages: messages,
// eslint-disable-next-line @typescript-eslint/naming-convention
max_tokens: maxTokensNumber,
temperature: temperatureNumber,
stream: true,
}, { responseType: 'stream' });
for await (const token of streamToTokens(res)) {
yield token;
}
} catch (error: any) {
console.error('Error fetching stream:', error);
}
Let's try to hit the OpenAI API separately from the extension, for example using curl. Can you try this and see if this works?
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-3.5-turbo",
"messages": [{"role": "user", "content": "Say this is a test!"}],
"temperature": 0.7
}'
Swap out $OPENAI_API_KEY
for your actual api key
(from https://platform.openai.com/docs/api-reference/making-requests)
@Snazzie the newest version here https://marketplace.visualstudio.com/items?itemName=ChatIDE.chatide might solve your issue, but let me know if not
Looks like it was due to having to have a paid account? Bummer
"error": {
"message": "You exceeded your current quota, please check your plan and billing details.",
"type": "insufficient_quota",
"param": null,
"code": null
}