Skip to main content
How are we doing? Please help us improve Stack Overflow. Take our short survey
531 questions
Newest Active Bountied Unanswered
Filter by
Sorted by
Tagged with
0 votes
1 answer
46 views

I’m testing Azure Agent Retrieval with Azure AI Search and Azure OpenAI integration. However, instead of getting a natural language LLM-generated answer, the response only returns raw JSON with ...
roczstar's user avatar
  • 73
0 votes
0 answers
45 views

We're setting up an Azure OpenAI instance that needs to connect to an Azure AI Search instance (i.e. "Bring Your Own Data"), we're currently using an API key to connect to the Search ...
Zhaph - Ben Duguid's user avatar
  • 27k
0 votes
1 answer
59 views

Using Azure's AI Search Service to chunk and read textfiles, the target field values are always NULL. I tried using a simplified example, just for the fields metadata_blob_name / title and ...
Jonathan's user avatar
  • 2,107
0 votes
1 answer
107 views

I want to create a structured output from an agent call that contains the full response content, as well as additional metadata. For example, I am making a call to find the differences between two ...
Daniel André's user avatar
  • 1,248
0 votes
1 answer
81 views

I want to update the capacity of a finetuned GPT model on Azure. How can I do so in Python? The following code used to work a few months ago (it used to take a few seconds to update the capacity) but ...
Franck Dernoncourt's user avatar
  • 84.7k
2 votes
1 answer
308 views

I'm trying to implement a custom LiteLlm wrapper to access an LLM endpoint. This is the code I have: import os import litellm import requests from dotenv import load_dotenv from litellm import ...
Al Ant's user avatar
  • 3
0 votes
0 answers
149 views

Using the following Microsoft template as my base: https://devblogs.microsoft.com/dotnet/announcing-dotnet-ai-template-preview1/ I want to be able to add my local stdio MCP server as a tool but can't ...
ChewToy's user avatar
  • 756
1 vote
1 answer
203 views

In streaming mode, there is an event "response.output_text.annotation.added", the data looks like { "type": "response.output_text.annotation.added", "...
Luk Aron's user avatar
  • 1,497
0 votes
0 answers
59 views

I'm using the OpenAi text-embedding-3-small model to create embeddings for each product category in a file. In total it's about 6000 product categories and they look like this: Vehicles & Parts &...
eztam's user avatar
  • 3,873
1 vote
0 answers
169 views

I have APIM with an AOAI backend. APIM authenticates to AOAI using a separate Managed Identity by way of the following API policy plus AOAI IAM roles: <authentication-managed-identity resource=&...
Angrydot's user avatar
  • 21
0 votes
0 answers
22 views

After I Updated the cdn path so that the icons work, the other icons are showing but the ThumbsUp & ThumbsDown buttons are not showing now. What has to be done for that and why this is happening ...
Sweekriti Pant's user avatar
  • 1
-3 votes
1 answer
128 views

I want to fill the vector memory of my project in Azure AI Foundry via a CURL command. I use the way described in the documentation Uploading the file, which apparently has to be done before adding ...
HendrikD2005's user avatar
  • 1
0 votes
1 answer
138 views

When writing a to_ChatCompletionMessageParam() instance method, I have the following implementation: def to_ChatCompletionMessageParam(self) -> ChatCompletionMessageParam: author: Literal["...
feverdreme's user avatar
  • 537
0 votes
2 answers
349 views

I have a C# semantic kernel app that calls various plugin methods. Each method returns a string value. I would like for the app to return this exact string value to the user, but instead semantic ...
jc116's user avatar
  • 63
2 votes
1 answer
70 views

Invoking a request using AzureChatOpenAI returns response as expected: import os from dotenv import load_dotenv from langchain_openai import AzureChatOpenAI load_dotenv() llm = AzureChatOpenAI( ...
Sanchez333's user avatar
  • 460
2 votes
1 answer
1k views

I'm running an Azure Responses call using the Azure Python SDK: from openai import AzureOpenAI . . . self.client = AzureOpenAI( api_key=config.get("api_key"), base_url= config.get(&...
Joseph Pourtaymour's user avatar
  • 21
1 vote
1 answer
313 views

I'm encountering an issue when trying to add attributes (metadata) to files in an Azure OpenAI Vector Store. My setup: Azure OpenAI API (version 2025-04-01-preview) Python SDK for file uploads Goal: ...
Luke's user avatar
  • 385
0 votes
1 answer
534 views

I'm trying to create a MCP (Model Context Protocol) client using C#'s SDK and Azure Open AI. This MCP clients needs to have Sampling capabilities, but I don't know how to extract the IChatClient ...
Infinity's user avatar
  • 3
0 votes
0 answers
99 views

I checked Azure's documentation on this topic here but I do not see anything related to this. My goal is to create a question and answer dataset for my RAG solution based on each chunk for a good ...
Mike B's user avatar
  • 3,629
1 vote
3 answers
662 views

I am trying to connect a non-Azure OpenAI embedding model in AI Foundry using Microsoft Entra ID. I don't have an issue connecting to Azure OpenAI embedding models using Microsoft Entra ID. After ...
trideau's user avatar
  • 31
2 votes
2 answers
409 views

I am using AzureOpenAI Service, and I just encountered an issue openai.NotFoundError: Error code: 404 - {'error': {'code': 'DeploymentNotFound', 'message': 'The API deployment for this resource does ...
mengyuest's user avatar
  • 21
1 vote
2 answers
314 views

Maybe you have the same issue or any idea how to fix this?! I'm using Semantic Kernel (.net) to access an Azure AI Service with GPT-4o model deployed in swedencentral via an APIM. When I start a group ...
Haiko's user avatar
  • 56
0 votes
1 answer
71 views

Im new to autogen ai currently using autogen version 0.7 Automating using Autogen AI to fetch azure migrate assessment report and generating PPT using autogen agents group chat agent but some times ...
User's user avatar
  • 79
1 vote
1 answer
362 views

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 ...
Shaan's user avatar
  • 11
0 votes
0 answers
114 views

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 = ...
Benjamin Gilbert's user avatar
  • 2
0 votes
1 answer
490 views

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.
Robert Corvus's user avatar
  • 2,176
1 vote
1 answer
241 views

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 ...
kalabic's user avatar
  • 21
3 votes
1 answer
708 views

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 ...
WhosOnFirst's user avatar
  • 31
0 votes
1 answer
167 views

I follow Azure's tutorial on fine-tuning GPT. Here is the code for the deployment phase: # Deploy fine-tuned model import json import requests token = '[redacted]' subscription = '[redacted]' ...
Franck Dernoncourt's user avatar
  • 84.7k
0 votes
1 answer
334 views

I have the following code to call Azure OpenAI endpoint using OpenAI Key. import axios from 'axios'; const openaiApiKey = process.env.REACT_APP_OPENAI_API_KEY; const openaiApiEndpoint = process.env....
user989988's user avatar
  • 3,896
0 votes
1 answer
910 views

I have successfully deployed a model (text-embedding-3-large) using the Azure OpenAI portal, and I'm now trying to integrate it using the OpenAI .NET SDK. The Azure portal itself provides the ...
José Augustinho's user avatar
  • 110
0 votes
0 answers
43 views

I am using OpenAI dotnet sdk, I use assistant to post the prompt and to get the response. I would like assistant to remember the previous prompt posted (i.e. retain the context of the conversation)...
Sankaranarayanan Rajkumar's user avatar
  • 51
0 votes
1 answer
172 views

Im triying to do a basic PyRIT project but im not able to use the AzureOpenAI with PyRIT. I have this code woking, but not with PyRIT: from openai import AzureOpenAI client = AzureOpenAI( api_key=&...
user30129718's user avatar
  • 3
0 votes
1 answer
1k views

Why doesn't my Azure OpenAI model show up in Cursor as one of the available models? I added my Azure OpenAI account show up in Cursor in the Settings window: The green toggle switch seems to ...
Franck Dernoncourt's user avatar
  • 84.7k
1 vote
1 answer
1k views

I am using DSPy framework (v2.6.4) which uses liteLLM (v1.63.7) to connect to LLMs. While connecting Azure OpenAI via liteLLM (v1.63.7) using the below method (Azure AD Token Refresh - ...
4run4's user avatar
  • 35
0 votes
0 answers
66 views

I'm using pandasai with AzureOpenAI to analyze a DataFrame. My code works fine in Google Colab but throws an error in VS Code. Code: import pandasai as pai from pandasai_openai import AzureOpenAI ...
Sh'Jil's user avatar
  • 82
0 votes
1 answer
309 views

I am using the Python SDK to connect to Weaviate. Additionally, I am create collection that is able to send requests to Azure OpenAI, using text2vec-azure-openai module. To use that, I am sending X-...
user30039021's user avatar
  • 1
1 vote
1 answer
431 views

I recently switched from using GPT-4o to Phi-4-multimodel-instruct in my Next.js application using Azure AI services, but I'm encountering the following error: BadRequestError: 400 {"object":...
Junaid Nazir's user avatar
  • 121
0 votes
2 answers
271 views

I follow Azure's tutorial on fine-tuning GPT. I'm stuck at the deployment phase. Code: # Deploy fine-tuned model import json import requests token = '[redacted]' subscription = '[redacted]' ...
Franck Dernoncourt's user avatar
  • 84.7k
0 votes
1 answer
403 views

I am creating a POC for a Chat bot using Azure OpenAI and .Net Core. I have created Open AI resource and Deployment Model in Azure. But I am getting error when calling Completechat() function. Error : ...
Ak C's user avatar
  • 53
3 votes
1 answer
540 views

I created an index on Azure AI Search and connected it to Azure OpenAI using the extra_body. It works perfectly. However, I created a default scoring profile for my index, which boosts documents ...
R_Student's user avatar
  • 809
1 vote
1 answer
315 views

I have tried uploading a batch job with unique custom_id for each row in my input file. The job gets validated but completes very quickly and once I check the job only 276/4096 (as shown in the ...
Nandan Thakur's user avatar
  • 46
2 votes
1 answer
309 views

I’m working on a report generation using some rubric’s and a conversation string containing questions and answers for the questions from the user which is captured through openai real-time api. But ...
EPIC PIXELS's user avatar
  • 21
0 votes
1 answer
381 views

I am using an Azure OpenAI GPT-4o Mini fine-tuned model to generate structured responses (e.g., JSON format). However, the response time is higher than expected, and I am looking for ways to optimize ...
BitByBitBuilder's user avatar
  • 1
-1 votes
1 answer
85 views

I used AzureOpenAI Vectorizer to create embeddings in my search index but it is not created in search index why while uploadind documents i only uploaded id,content,title and titleVector and ...
A V Saravanan's user avatar
  • 1
0 votes
1 answer
331 views

We are using terraform's az_api resource to create Azure openai content filter(rai_policy). While updating the contentFilters property for multiple resources , we are seeing below error **RESPONSE 409:...
G_S's user avatar
  • 115
0 votes
2 answers
592 views

I’m trying to use Azure AI OpenAI to generate responses from a trained model based on a set of data I’ll provide as part of the prompt. My goal is to pass a set of data (e.g., metrics, statistics, or ...
imj's user avatar
  • 470
0 votes
0 answers
136 views

I am trying to create 3 step framework where 1. data quality issue gets reported , 2. user reviewes the data quality and 3. approves to execute agents for DQ corrections in database. I have three ...
Carpe Diem's user avatar
  • 73
0 votes
1 answer
279 views

We are using Azure Devops Server 2022 on-premise and we have a private Azure OpenAI instance enabled with a private endpoint. In VSTS marketplace, we were able to find many extensions: https://...
Vowneee's user avatar
  • 1,551
3 votes
1 answer
2k views

Should I subtract the number of cached input tokens from the number of input tokens when I receive the 'Usage' object back in the OpenAI response? I'm trying to calculate the total cost of the ...
dmm-l-mediehus's user avatar
  • 21

1
2 3 4 5
…
11