13 questions
0
votes
0
answers
58
views
Chat model returns empty content when I inject a delayed ToolMessage from a scheduled callback
I have a scheduler that triggers a tool function later (outside the original user–model exchange).
When the scheduled time comes, it sends a ToolMessage back into the chat model — but the model ...
- 9
1
vote
0
answers
322
views
Failed to use apply_chat_template when adding tools
I failed to use apply_chat_template when using function calling. Is there something I missed?
Example
I downloaded tokenizer.json and tokenizer_config.json for testing function calling to see its full ...
- 13
-1
votes
1
answer
68
views
What is the correct status code for a semi-ok response? [closed]
I have a client that is asking the server for n elements. The server is asking ChatGPT for n elements, but sometimes ChatGPT returns n-1 or n+1 elements.
Client Code
const count = 3;
var elements = ...
- 7,436
1
vote
0
answers
283
views
Inconsistent JSON parsing when calling LangChain tools from a Structured Chat Agent
I'm using LangChain's Structured Chat Agent and tools to build an analytics assistant. One of the tools I've defined is get_social_insights, which fetches Instagram insights for the account.
However, ...
- 11
0
votes
1
answer
134
views
Question on how to make an openai assistant made with assistants api ui call an external API?
I am developing a chatbot for my company, and I have created middleware in Spring Boot to access my assistant using API calls (make a thread and send messages on it, create a run and then receive a ...
0
votes
1
answer
140
views
How to present the model's response content when using Few-shot prompting with function calling in LangChain and GPT-4 API?
I referred to an example from LangChain about using few-shot prompting along with function calling for my project. The following code snippet is taken from LangChain's documentation:
from ...
- 11
0
votes
1
answer
508
views
How to stop Semantic Kernel function automatically filling in parameters?
I'm using ai to take an input from a user then based on the users input the ai will decide on what function to call. I'm using Microsoft semantic kernel, function calling method to do this. Foreach ...
- 13
0
votes
1
answer
981
views
Call Chat-GPT Assistant using Google Apps Script
I wrote a small Google Apps Script that basically calls a trained Chat-GPT Playground Assistant to answer my query. The code is working perfectly when using it for example with a default model such ...
0
votes
0
answers
917
views
How do I stream the response when function calling is used in OpenAI API?
I'm using function calling in OpenAI to get search results from web to give OpenAi's gpt-3.5-turbo model some context when answering questions. I want to stream the response as soon as it becomes ...
- 72
0
votes
1
answer
2k
views
OpenAI API error: "You tried to access openai.ChatCompletion, but this is no longer supported in openai>=1.0.0
I am currently working on a gpt content creator system, and as I am using Mac it does not let me migrate to newer OpenAI library or downgrade it. Could I replace the ChatCompletion function with ...
- 31
0
votes
1
answer
522
views
OpenAI API error: "TypeError: Cannot read properties of undefined (reading 'create')"
I am creating a chat summarizer app where the input is an Excel file with chat transcripts. Each row of the Excel sheet corresponds to a new chat. The app summarizes the chat in the adjacent column.
...
1
vote
2
answers
6k
views
How To Execute Custom Actions with ChatGPT Assistants API
I am trying to create a GPT chatbot for restaurants that can ask customers for their contact info and time of reservation. After the AI chatbot is sure the customer has provided it with all of these ...
0
votes
1
answer
1k
views
Passing questions to ChatGPT via URL
So officially you cannot pass ChatGPT questions via the browser URL (only via API), unofficially however, I've gotten very close by creating a user script, which essentially reads a parameter I pass ...
- 817