2,628 questions
Advice
1
vote
2
replies
41
views
Unable to download package
I have issues with downloading "@stream-io/openai-realtime-api" package in NextJS project.
Error:
enter image description here
I tried to clear cash, change registry, used "--legacy-...
- 1
0
votes
0
answers
22
views
OpenAPI Spec client fail to compile with ambiguous types
I downloaded the OpenAI's OpenAPI Spec file and tried to generate and compile the client and faced a few issues and wonder if anyone knows the fix for it.
This is the specification: https://app....
- 896
Advice
1
vote
1
replies
36
views
RAG with Pinecone + GPT-5 for generating new math problems: incoherent outputs, mixed chunks, and lack of originality
I’m building a tool that generates new mathematics exam problems using an internal database of past problems.
My current setup uses a RAG pipeline, Pinecone as the vector database, and GPT-5 as the ...
0
votes
0
answers
20
views
Azure OpenAI model token rate limit header (x-ratelimit-limit-tokens) is -1
I am trying to get my current rate limit for an OpenAI model hosted on Azure. The response headers contain keys x-ratelimit-limit-tokens and x-ratelimit-remaining-tokens which are supposed to contain ...
- 640
0
votes
1
answer
41
views
Why isn't my VSIX extension for VS 2022 enabling?
I have written a VSIX extension to bring my "version" of ChatGPT into Visual Studio 2022. I haven't even gotten to the wireup with Chat GPT phase yet. All I've done thus far is write it to ...
- 245
3
votes
0
answers
43
views
Weird OpenAI streaming bug: concurrent JS streams randomly mix chunks across responses
I’m hitting a super weird issue with OpenAI’s streaming API.
I’m building a multi-message streaming thing in plain JS (no frameworks) where I need to pipe multiple OpenAI responses one after another. ...
- 59
-1
votes
1
answer
46
views
Open's AI MCP server redirect URI [closed]
I am configuring Open AI to talk to my MCP server using the Oauth service from a third party provider. I add the Client ID and Secret and they are received correctly. However my SSO service complains ...
- 1,029
-3
votes
0
answers
146
views
OpenAI API Key Being Leaked Even Though It’s Stored Securely on Server . Need Help Diagnosing [closed]
I’m facing a serious issue and need help identifying the cause.
My application setup is:
Backend: Python FastAPI
Frontend: Next.js
Auth: JWT (Bearer token)
Hosting: Nginx on a Linux server
OpenAI ...
Advice
0
votes
0
replies
58
views
Does OpenAI API TPM limit count input tokens, output tokens, or both?
I’m a bit confused about how OpenAI’s API rate limits work - specifically the TPM (tokens per minute) limit.
If I have, for example, 2 million TPM, is that limit calculated based on:
only the input ...
- 34
-1
votes
1
answer
57
views
OpenAI deep research API structured output [closed]
Using o3-deep-research, I need strictly structured JSON for a research report with fixed keys and nested values. The keys are set, value structures are set, but ideally the LLM would be able to choose ...
Tooling
0
votes
3
replies
145
views
How to make an AI model come alive?
For fun, I developed an AI model with short-term, medium-term, and long-term memory, inspired by neuro-sama. (I'm a regular backend developer, I don't know much about AI).
How it works:
mic -> vad -...
- 49
-2
votes
1
answer
86
views
Why doesn’t ChatGPT MCP Connector send client_id in /token request even though AS requires client_secret_post?
I'm integrating my own MCP server with OAuth authentication through the ChatGPT Connector.
During the authorization code exchange, the connector doesn’t send the client_id field in the POST request to ...
- 93
Advice
0
votes
1
replies
65
views
Why does my OpenAI API (ChatGPT) return 429 ‘rate limit exceeded’ even for low traffic?
I’m integrating OpenAI’s GPT API using Node.js. My app runs fine for a while, but then randomly throws:
Error: 429 - You exceeded your current quota, please check your plan and billing details.
Even ...
- 1,544
-2
votes
0
answers
54
views
ChatKit DomainVerificationRequestError on mobile (desktop works)
My domain is:
https://norkven.getfeurst.com
Important details:
The agent loads and responds successfully on desktop Chrome and Safari.
On mobile Safari/Chrome, the same page loads, but ChatKit throws ...
0
votes
0
answers
46
views
Inconsistent name normalization when extracting data using OpenAI API (gpt-4.0-mini)
I'm using the OpenAI API (gpt-4.0-mini) to extract and normalize names from social media posts.
However, even with strict prompting, the output sometimes contains slightly different spellings for the ...
