2,763 questions
-2
votes
0
answers
17
views
Recommended AI model language/sites to study and rehearse coding overall [closed]
What are the current AI tools/programs/sites/model languages that are considered the "best" to study and understand coding concepts, not them just straight solving problems for you, ...
1
vote
0
answers
13
views
Stylus Extension having domain specificity issues
/* ==UserStyle==
@name ChatGPT Max Content View (Minimized Navbar & Prompt)
@namespace github.com/your-username
@version 4.0.1
@description Maximizes content area by ...
- 11
-1
votes
0
answers
9
views
How to effectively format "System" prompts and rubric-style instructions in .jsonl files for fine-tuning?
I'm working on preparing a .jsonl file for fine-tuning a language model and had two questions:
Q2. What are some best practices for writing the "System" prompt in the dataset? Are there ...
1
vote
1
answer
28
views
Gemini AI Structured Output with references via OpenAI SDK
I'm using OpenRouter (OpenAI-compatible proxy) as an abstraction layer to call different LLM providers with a consistent interface, including Google's Gemini models. I've set up my code to use ...
- 2,077
0
votes
0
answers
22
views
How to detect and merge updates in nested Pydantic models (partial vs. full updates from LLM feedback)?
I'm building a system where an LLM (through OpenAI Apis) generates a structured response conforming to this Pydantic schema (I am using open Ai structured output generation). After a user provides ...
1
vote
1
answer
29
views
How to reduce response latency in Azure OpenAI GPT-3.5 Turbo & GPT-4 API?
I'm using the Azure OpenAI API with GPT-3.5 Turbo and GPT-4 models. I'm currently experiencing average response times of:
GPT-3.5 Turbo: ~900ms
GPT-4: ~1.3 seconds
I’m already using the following ...
- 11
0
votes
0
answers
37
views
Tool calling with OpenAI not passing response to OpenAI after the tool response
I have this setup since I have to use specific dynamic key and URL for OpenAI. I can get normal responses from GenAI. However with tools, it does not send the tool response back to GenAI and gives ...
- 1
0
votes
0
answers
45
views
OpenAI Azure chat.completions.create stalling without throwing exception
I have a fastapi endpoint which streams a response from Azure OpenAI:
@router.post("/message", dependencies=[Depends(validate_auth)])
def message(sessionID: str = Form(...), messages: str = ...
1
vote
1
answer
65
views
VS Code AI chat consumes too many OpenAI tokens — is this expected?
I'm trying to use the AI-powered agent chat feature in VS Code (the built-in AI assistant). I'm using my own OpenAI API key (gpt-4o, gpt-4.1) and the chat works in general — but I'm seeing extremely ...
- 414
0
votes
1
answer
41
views
How do you get Azure OpenAI to return json in C#?
If I want to return json from Azure OpenAI, such as Gpt-4o, how do I get it to respond in json? I've found examples in Python, but none using the Azure.AI.OpenAI sdk library for C# .NET.
- 2,146
0
votes
0
answers
11
views
Unable to receive verification code for Fotor AI API sign-up — how to get API key [closed]
I want to use the Fotor(https://www.fotor.com/) API key with python to change images to anime style by using API and sign-in as developer and they support a form and in that form
one field , verifying-...
0
votes
1
answer
22
views
How to properly use OpenAI.RealtimeConversation.RealtimeConversationClient to start multiple RealtimeConversationSession(s)?
The Azure OpenAI SDK appears to follow a one-client-per-session model, but I want to be sure. Since it is still in beta, it is not clear if a single instance of the client returned by ...
- 11
0
votes
0
answers
18
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 ...
- 15
2
votes
1
answer
93
views
Suddenly getting 400 Bad Request error calling OpenAI.Chat.ChatClient.CompleteChat()
Late last week, our Azure-based RAG chat service started returning HTTP 400 Bad Request errors. We are running a web API on ASP.NET Core 8. Nothing in the code changed, and I have verified that our ...
- 21
0
votes
0
answers
33
views
OpenAI gpt-40-realtime-preview-2024-12-17 APi with whisper-1 integration with Vector Stores attached to Assistants
I am using gpt-40-realtime-preview-2024-12-17 APi with whisper-1 for voice chat feature for my mobile application. The issue is, I am not able to connect Realtime API to Vector Store, which is ...
- 41