Questions tagged [azure-openai]
The azure-openai tag has no usage guidance.
azure-openai
425
questions
13
votes
3
answers
21k
views
Why I'm getting 404 Resource Not Found to my newly Azure OpenAI deployment?
I've gone through this quickstart and I created my Azure OpenAI resource + created a model deployment which is in state succeedded. I also playaround it in https://oai.azure.com/ and it works there.
...
10
votes
6
answers
9k
views
How to do function calling using Azure OpenAI
Here is my code
response = openai.ChatCompletion.create(
engine="XXX", # The deployment name you chose when you deployed the ChatGPT or GPT-4 model.
messages=[
{"role&...
9
votes
8
answers
26k
views
OpenAI API error: "No module named 'openai.embeddings_utils'; 'openai' is not a package"
I want to use openai.embeddings_utils import get_embeddings
So already install openai
Name: openai
Version: 0.26.5
Summary: Python client library for the OpenAI API
Home-page: https://github.com/...
9
votes
2
answers
9k
views
Why do I get the error "Unrecognized request argument supplied: functions" when using `functions` when calling Azure OpenAI GPT?
I'm trying to use functions when calling Azure OpenAI GPT, as documented in https://platform.openai.com/docs/api-reference/chat/create#chat/create-functions
I use:
import openai
openai.api_type = &...
8
votes
2
answers
21k
views
How can I select the proper openai.api_version?
I read on https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/chatgpt?pivots=programming-language-chat-completions:
openai.api_version = "2023-05-15"
and on https://...
8
votes
3
answers
1k
views
Azure OpenAI On Your Data - System message usage [closed]
I'm working with Azure OpenAI On Your Data, trying to understand:
why system message seems to not work as expected
strategy for providing instructions in “on your data” case
For example, calling ...
7
votes
2
answers
10k
views
How to appropriately use the Azure.AI.OpenAI.OpenAIClient.GetChatCompletionsStreamingAsync Method
I am working on a web application that will serve as the help system for one of my companies existing products. One of the features I have implemented is a chatbot that is powered by an Azure Open AI ...
7
votes
3
answers
3k
views
Unclear how Azure OpenAI endpoint /extensions/chat/completions does the retrieval behind the scenes
I am playing around with this example chat application which retrieves most relevant documents from Cognitive Search to help the chatbot answer users' questions. The document retrieval itself is not a ...
5
votes
1
answer
4k
views
Image to text using Azure OpenAI GPT4
I have an Azure open AI Account and GPT4 model deployed. Can I use its API for image-to-text description? If yes, how I will give it the image? I am using this code. But it throws me an error.
import ...
5
votes
1
answer
3k
views
AzureOpenAI and LangChain Weird, multiple answers
I'm using AzureOpenAI to test LangChain's Self Critique using Constitution.
It all works, except I get more than one answer, and the weirdest part, it GENERATES random, unwanted questions, and answer ...
5
votes
1
answer
409
views
Can tiktoken be used instead of text-embedding-ada-002 for generating text embeddings for Azure AI Search?
I'm currently tokenizing documents with a text-embedding-ada-002 on Azure. The document contents and their tokens are uploaded to Azure AI Search. We then use a gpt-35-turbo-16k deployment to search ...
4
votes
4
answers
8k
views
Unsupported data type when making API request to Azure Open AI
I'm getting "unsupported data" error when trying to send post request to Azure OpenAI. What should I do to fix the error?
https://myopenai.openai.azure.com/openai/deployments/code-davinci-...
4
votes
2
answers
4k
views
Azure OpenAI gpt-35-turbo nondeterministic with temperature 0
I have noticed that my deployment of gpt-35-turbo on "Azure AI Studio" is not giving consistent responses to my chat completion prompts even when I set the temperature to 0. The longer the ...
4
votes
1
answer
5k
views
OpenAI Embeddings API: How embeddings work?
There are quite a few tutorials on embeddings in OpenAI. I can't understand how they work.
Referring to https://platform.openai.com/docs/guides/embeddings/what-are-embeddings , an embedding is a ...
4
votes
1
answer
10k
views
How to delete documents in LangChain vectorstore
I am following LangChain's tutorial to create an example selector to automatically select similar examples given an input.
example_selector = SemanticSimilarityExampleSelector.from_examples(
# ...
4
votes
2
answers
8k
views
Azure openai The API deployment for this resource does not exist
I am making sequential calls to Azure OpenAI GPT-4 from a python code. The token size of each call is approx 5000 tokens (inclusing input, prompt and output). The first call goes good. But the API is ...
4
votes
1
answer
3k
views
Azure OpenAI model throwing error OperationNotSupported
I tried below code and getting error, I am simply trying API to generate some question based on topic given. How can I do that?
Like if I define a topic of Games, I want to generate two questions for ...
4
votes
1
answer
10k
views
OpenAI Embeddings API error: "AttributeError: module 'openai' has no attribute 'Embedding'"
I was running a python script with the openai library. Whenever I run this function on my local machine it throws the following error
def gpt3_embedding(content, engine='text-embedding-ada-002'):
...
4
votes
1
answer
1k
views
Unable to list text-embedding model for vector search in Azure open AI service
I am encountering an issue while trying to add vector search for Azure open AI service within the context of cognitive search. After selecting the tickmark, I am unable to list any models, even though ...
4
votes
1
answer
3k
views
Can't deploy Azure Open AI models due "No quota is available for this deployment. You can request for more quota."
I wanted to test the gpt-35-turbo-16k model, so I attempted to deploy it. However, I received a message stating that there was no quota available. I initially assumed that it might be due to an ...
4
votes
2
answers
2k
views
Using Embeddings API in Azure OpenAI
When I use embeddings with Azure OpenAI I am getting 404 (resource not found):
EmbeddingsOptions embdOptions = new EmbeddingsOptions(text);
Azure.AI.OpenAI.Embeddings response = Task.Run(() =&...
4
votes
1
answer
1k
views
Get the token usage from semantic kernel C#
I am trying out the semantic kernel in C# for a project. I am using the ChatCompletionService with Azure OpenAI and a few simple plugins that I created. I am not able to figure out how to get the ...
4
votes
0
answers
229
views
GPT-4 returning text-based prompt instead of returning the function call designated to do the same prompt
I'm using Azure OpenAI for implementing a conversational AI using GPT-4 to act as an assistant for resolving user queries. The assistant is supposed to follow a predefined set of instructions, ...
4
votes
1
answer
706
views
Azure Open AI Studio uploading Help Guide for data
We're wanting to take our help guide and use that to build training data to upload into Azure Open AI studio (Azure OpenAI Studio -> File Management).
Is there any examples on taking a help/user ...
4
votes
1
answer
536
views
Azure Machine Learning Vector Index - Why does deployment validation fail?
I'm trying to create a FAISS vector index using Azure Machine Learning's web-based UI. I go through the required steps as per the documentation, and I choose a running compute instance for processing.
...
3
votes
2
answers
573
views
impact of (?) question mark in vector search
we are using azure cognitive search as a vector database, we are generating embeddings using the azure open ai Ada02 model for the query and the document (RAG pattern).
we are observing different ...
3
votes
4
answers
3k
views
Azure Open AI - Add your Data not working
I created a Azure Open AI resource in Azure, and then followed the steps to create a Azure Cognitive search resource and was able to successfully connect Search to My Azure SQL DB. I tested the search ...
3
votes
0
answers
1k
views
Azure OpenAI Bring your own data - Semantic search not working
I'm trying to use Azure OpenAI BYOD feature (https://learn.microsoft.com/en-us/azure/ai-services/openai/use-your-data-quickstart?tabs=command-line&pivots=programming-language-studio).
I have ...
3
votes
4
answers
6k
views
Is there an official OpenAI nuget package to be able to use its API?
I want to use the openAI API in a console app project in Visual Studio but I don't know if they have released an official nuget package.
I understand that this is not true?
If they haven't released ...
3
votes
1
answer
8k
views
"Public access is disabled. Please configure private endpoint." even though private endpoint configured for Azure OpenAI Service
I'm deploying Azure OpenAI Service via Terraform, and I want to set up a private endpoint for it. The docs and this article suggest that, besides a private endpoint, I need a private DNS zone ...
3
votes
1
answer
459
views
Is there a way to update playground openai.api_version?
I have deployed the latest gpt-35-turbo model, with model version '0613', however, when I tried to test it in chat playground, I realized that openai.api_version remains "2023-03-15-preview",...
3
votes
1
answer
2k
views
In Azure OpenAI Assistants when I upload a file and save it where is that file stored?
In Azure OpenAI Studio I am hoping to use Assistants to do data analysis, however, I need to know where those files are stored and how to delete them. When I click on add files I am offered the chance ...
3
votes
3
answers
6k
views
Langchain pandas agent - Azure OpenAI account
I am trying to use Langchain for structured data using these steps from the official document.
I changed it a bit as I am using Azure OpenAI account referring this.
Below is the snippet of my code -
...
3
votes
1
answer
986
views
OpenAI Fine-Tuning error - 'fileName contains an invalid filename: wrong suffix.'
I am trying to fine-tune a GPT model through the Azure OpenAI API.
I now need to upload the file to openai using the code below:
file_name = "training_data_prepared.jsonl"
upload_response = ...
3
votes
1
answer
2k
views
Creating ChatBot from custom Knowledge Base using ChatGPT
Problem Description:
We have a strong and huge Knowledge Base internally for our organization which contains a lot of documentation, policies and guidelines, tutorials, question answers, employee's ...
3
votes
1
answer
4k
views
OpenAI Embeddings API: How to change the embedding output dimension?
In the official OpenAI node library Create embeddings if for example using the model text-embedding-ada-002 the embeddings returned is an array of around 1536.
import {Configuration, OpenAIApi} from '...
3
votes
2
answers
3k
views
How to Provide Context from a List of Documents in OpenAI's Chat Completions API?
I'm currently using the RAG pattern for answering questions about documents. I'm working with OpenAI's Chat completions API, specifically trying to use a list of documents to provide context to the ...
3
votes
4
answers
2k
views
Data source can't be referred by Azure OpenAI API
I have deployed chat model on Azure OpenAI Studio and given the model my own data source using "Add your data (preview)" feature.
On Chat session in Chat playground page, the chat model can ...
3
votes
3
answers
695
views
Azure OpenAI - models missing
Yesterday I have been deploying Azure Open AI resource using Bicep template and it went OK. I was deploying following models:
gpt-35-turbo-16k version: 0613
gpt-35-turbo version 0613
text-embedding-...
3
votes
0
answers
2k
views
Azure Open AI InvalidRequestError
I'm new to OpenAI and trying some calls. I have created the resources and got my project endpoint and api key. However, I got the following error:
InvalidRequestError: The API deployment for this ...
3
votes
0
answers
1k
views
How to queue API calls to Azure OpenAI service (with a token per minute rate limit) the most efficiently?
How can we implement an efficient queue using Azure serverless technologies (e.g. Azure Servicebus) to call Azure OpenAI service concurrently but guarantee earlier messages are processed first?
The ...
3
votes
0
answers
873
views
Azure OpenAI returns "OperationNotSupported - The embeddings operation does not work with the specified model, text-embedding-ada-002"
Our backend service using Azure OpenAI APIs was unexpectedly getting this kind of responses for around 2 hours for all incoming requests:
error_code=OperationNotSupported
error_message='The embeddings ...
2
votes
2
answers
6k
views
OpenAI API, ChatCompletion and Completion give totally different answers with same parameters. Why?
I'm exploring the usage of different prompts on gpt3.5-turbo.
Investigating over the differences between "ChatCompletion" and "Completion", some references say that they should be ...
2
votes
1
answer
2k
views
TypeError: expected string or buffer - Langchain, OpenAI Embeddings
I am trying to create RAG using the product manuals in pdf which are splitted, indexed and stored in Chroma persisted on a disk. When I try the function that classifies the reviews using the documents ...
2
votes
1
answer
4k
views
Azure OpenAI LangChain - (InvalidField) The vector field 'content_vector' must have the property 'vectorSearchConfiguration' set
I'm trying to create an embedding vector database with some .txt documents in my local folder. In particular I'm following this tutorial from the official page of LangChain: LangChain - Azure ...
2
votes
1
answer
2k
views
Azure OpenAI Embeddings vs OpenAI Embeddings
Is anyone getting different results from Azure OpenAI embeddings deployment using text-embedding-ada-002 than the ones from OpenAI? Same text, same model, and the results are considerably far in the ...
2
votes
1
answer
2k
views
What is the request-per-minute rate limit for Azure openAI models for gpt-3.5-turbo?
I couldn't find the RPM limit for Azure openAI
I found the TPM limit thou which is 240k for East US, South Central US, West Europe, France Central, UK South,
I've tried Microsoft documentation but ...
2
votes
1
answer
5k
views
Is there a way I can handle context and general questions in Langchain QA Retrieval?
I want to make a chatbot, that should answer questions from the context, in my case, a vector database. It is doing that perfectly. But I also want it to answer questions, which are not in the vector ...
2
votes
2
answers
282
views
Model Deployment - Pricing Information
We are creating some models in Azure Open AI Studio and doing deployments of same. I want to check how much charges are applied for model creation, deployments and requests made to deployed model. I ...
2
votes
1
answer
560
views
How to intercept generated prompts of kernel in SemanticKernel?
In SemanticKernel I want to see what are the final rendered prompts that are being sent to OpenAI. I've found the PromptRendered event:
kernel.PromptRendered += (sender, args) => Console.WriteLine(...