517 questions
- Bountied 0
- Unanswered
- Frequent
- Score
- Trending
- Week
- Month
- Unanswered (my tags)
0
votes
0
answers
30
views
OpenAI image input token caching
OpenAI GPT-Image API: Image input tokens not caching despite documentation suggesting they should
Problem Summary
I'm using OpenAI's GPT-Image models (gpt-image-1.5, gpt-image-1, gpt-image-1-mini) to ...
Best practices
0
votes
2
replies
57
views
Is it possible to create a custom GPT and connect it to external services like Notion?
Is it possible to create a custom GPT and connect it with available connectors?
I want to create a GPT that can create and read documents in Notion, basically acting like a second memory/brain. The ...
Tooling
0
votes
3
replies
93
views
Why is OpenAI’s ChatGPT SDK preferred at the enterprise level over Google Gemini?
I’ve noticed that many enterprises seem to adopt OpenAI’s ChatGPT SDK more frequently than Google Gemini or other AI platforms. From my understanding, both platforms provide similar foundational AI ...
Best practices
1
vote
3
replies
128
views
Will AI reduce the demand for software developers in the future? and stackoverflow effect due to AI
I'm noticing rapid improvements in AI tools (ChatGPT, GitHub Copilot, etc.), and I'm concerned about how this will impact developer jobs in the next few years.
Will AI replace developers, or will it ...
-2
votes
1
answer
169
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 ...
0
votes
1
answer
172
views
How to stream responses token-by-token from OpenAI ChatGPT API using Python? [closed]
I'm using OpenAI's API in Python, and right now the response is returned only after the full answer is generated.
Example:
response = client.chat.completions.create(
model="gpt-4o-mini",
...
0
votes
0
answers
64
views
How to reduce latency in a context-aware chatbot with chart + dataset inputs
I’m building a chatbot for my research project that helps participants understand a chart. The chatbot runs on a website built with React.
My goal is to make it feel just like using ChatGPT in the ...
-2
votes
1
answer
138
views
How to stop ChatGPT Realtime from speaking JSON when using both text (JSON) and audio (TTS) in the same response? [closed]
I’m trying to use the ChatGPT Realtime API to recognize spoken commands and to have natural language conversation.
What I need:
User speaks a command (e.g. "Turn on the living room lights").
Note the ...
-7
votes
1
answer
299
views
Chat response when using function tools
I’ve set up a tool function to capture important bits of information from user text.
import OpenAI from "openai";
import {Tool} from "openai/resources/responses/responses";
...
0
votes
0
answers
47
views
CodeGPT: MODEL_RESPONSE_ERROR
I am having a CodeGPT Error Code given as below when trying to ask any question within VS Code IDE:
Error Message: Error Code: MODEL_RESPONSE_ERROR
I have the VS Code extension of CodeGPT: Chat & ...
0
votes
2
answers
439
views
"No existing trace found" error thrown in OpenAI Agents SDK
I am trying tutorial for OpenAI Agents SDK.
https://openai.github.io/openai-agents-js/guides/tracing/#default-tracing
github.com/openai/openai-agents-js/examples/nextjs/src/app/api/basic/route.ts
...
2
votes
1
answer
469
views
How to get input_audio_transcription when i use openai realtime api
I'm using OpenAI's Realtime API for voice conversations and have written Node.js code based on the documentation.
https://platform.openai.com/docs/guides/realtime-conversations
I'm able to receive the ...
-1
votes
1
answer
161
views
Using openai python api to upload a file to a chatgpt assistant
I get an error saying file_ids is an unexpected keyword when I try to upload a file in a message using the python openai package. I created a chatgpt-4o thread and I'm trying to upload the file in a ...
0
votes
1
answer
108
views
Openai Eval how do I add my tools, like I do for production?
My production environment loads tools, it contains my functions schema, it's important because that's the response is calling for the tools, so I can't really eval a response when the eval doesn't ...
0
votes
0
answers
30
views
Getting the error [92] NetworkUtility.shouldRetryException: Unexpected response code 400 for https://api.openai.com/v1/images/generations
I'm trying to generate image on my app and it would fail to generate, first time trying to add image generation in an app and not really sure if it's doable, have just been failing to generate the ...