# \#azure **URL:** https://community.openai.com/tag/azure/419.md [Latest](https://community.openai.com/latest.md) · [Categories](https://community.openai.com/categories.md) · [Tags](https://community.openai.com/tags.md) --- ## [APIError with 95% of image requests for 2 days now](https://community.openai.com/t/apierror-with-95-of-image-requests-for-2-days-now/1368832)
**Author:** [@Alexander\_Vaith](https://community.openai.com/u/Alexander_Vaith)\ **Replies:** 6\ **Last updated:** [December 15, 2025, 7:30am UTC](https://community.openai.com/t/apierror-with-95-of-image-requests-for-2-days-now/1368832 "2025-12-15T07:30:19Z")
Summary Starting yesterday (approx. 24 hours ago), we began experiencing a critical regression with Azure OpenAI Vision requests. Approximately 95% of requests containing base64 images are failing with a generic APIErro… --- ## [Azure Realtime Model Compatibility: Azure Deployment name (free text) is not Accepted in API Spec](https://community.openai.com/t/azure-realtime-model-compatibility-azure-deployment-name-free-text-is-not-accepted-in-api-spec/1368587)
**Author:** [@Abbas\_Jafari](https://community.openai.com/u/Abbas_Jafari)\ **Replies:** 0\ **Last updated:** [December 7, 2025, 12:46am UTC](https://community.openai.com/t/azure-realtime-model-compatibility-azure-deployment-name-free-text-is-not-accepted-in-api-spec/1368587 "2025-12-07T00:46:48Z")
Hi all, currently using Agents library seems to be impossible as the Realtime api in Azure expects transcription model parameter to be deployment name of the Azure, but spec only allows: \`whisper-1\`, \`gpt-4o-mini-transcr… --- ## [Connecting OpenAI Agentic flow with Azure Search Vector Store](https://community.openai.com/t/connecting-openai-agentic-flow-with-azure-search-vector-store/1364578)
**Author:** [@adrian.ursu](https://community.openai.com/u/adrian.ursu)\ **Replies:** 0\ **Last updated:** [October 31, 2025, 10:27am UTC](https://community.openai.com/t/connecting-openai-agentic-flow-with-azure-search-vector-store/1364578 "2025-10-31T10:27:26Z")
Hi guys, I am new to this forum and fairly new to the whole overwhelming world of AI, so please bear with me :slight\_smile: My first project is creating a Knowledge Base/RAG application. I have managed to create a vec… --- ## [Who is gpt-4o agent successor in the gpt-5 serie?](https://community.openai.com/t/who-is-gpt-4o-agent-successor-in-the-gpt-5-serie/1361827)
**Author:** [@LambertB](https://community.openai.com/u/LambertB)\ **Replies:** 2\ **Last updated:** [October 10, 2025, 8:55am UTC](https://community.openai.com/t/who-is-gpt-4o-agent-successor-in-the-gpt-5-serie/1361827 "2025-10-10T08:55:12Z")
Hello everyone, For the past year I’ve been building agents using Azure OpenAI gpt-4o 2024-11-20. I wanted to upgrade to one of the model of the gpt-5 serie to gain performance notably in SWE and Instruction following.… --- ## [Getting AI Search citations in Responses API?](https://community.openai.com/t/getting-ai-search-citations-in-responses-api/1247526)
**Author:** [@joshua.brumpton](https://community.openai.com/u/joshua.brumpton)\ **Replies:** 2\ **Last updated:** [October 2, 2025, 12:50am UTC](https://community.openai.com/t/getting-ai-search-citations-in-responses-api/1247526 "2025-10-02T00:50:58Z")
I’m moving from the completions API because it’s not giving enough control over the data source results from my Azure AI Search index. I want to use the responses API. First, I perform query rewrites and retrieve the se… --- ## [SORA API on Azure. Wow! But... need a bit more inputs there](https://community.openai.com/t/sora-api-on-azure-wow-but-need-a-bit-more-inputs-there/1345403)
**Author:** [@itsvnk](https://community.openai.com/u/itsvnk)\ **Replies:** 0\ **Last updated:** [August 13, 2025, 1:34pm UTC](https://community.openai.com/t/sora-api-on-azure-wow-but-need-a-bit-more-inputs-there/1345403 "2025-08-13T13:34:10Z")
Sora API is available on request on Azure & boy, it rocks! But, going back to the video generator on OpenAi, it will be nice to know how to include some of those parameters in Azure API for SORA. Azure just allows some … --- ## [It does not work on my machine (it does on prod). Azure OpenAI API](https://community.openai.com/t/it-does-not-work-on-my-machine-it-does-on-prod-azure-openai-api/1247391)
**Author:** [@r\_crtchn](https://community.openai.com/u/r_crtchn)\ **Replies:** 1\ **Last updated:** [April 30, 2025, 12:22pm UTC](https://community.openai.com/t/it-does-not-work-on-my-machine-it-does-on-prod-azure-openai-api/1247391 "2025-04-30T12:22:59Z")
So there’s an issue with my local setup, we use vpn to access OpenAI APIs. Today, it’s not working locally. It’s been hours. But our prod setup works just fine. --- ## [How can I use structured\_output with Azure OpenAI?](https://community.openai.com/t/how-can-i-use-structured-output-with-azure-openai/898427)
**Author:** [@Franck.Dernoncourt](https://community.openai.com/u/Franck.Dernoncourt)\ **Replies:** 10\ **Last updated:** [March 31, 2025, 1:47am UTC](https://community.openai.com/t/how-can-i-use-structured-output-with-azure-openai/898427 "2025-03-31T01:47:52Z")
I want to use structured output with Azure OpenAI. I tried the following code, based on the code given in https://openai.com/index/introducing-structured-outputs-in-the-api/: from pydantic import BaseModel from openai … --- ## [Azure OpenAI issue with chat response generation using data retrieval](https://community.openai.com/t/azure-openai-issue-with-chat-response-generation-using-data-retrieval/688507)
**Author:** [@nodamen17](https://community.openai.com/u/nodamen17)\ **Replies:** 1\ **Last updated:** [March 17, 2025, 1:52am UTC](https://community.openai.com/t/azure-openai-issue-with-chat-response-generation-using-data-retrieval/688507 "2025-03-17T01:52:08Z")
Our company is planning to use GPT-3.5 Turbo to create our own custom chatbot that is supposed to help the users with their meditation journey. Currently our server is hosted by Microsoft, so we are using their OpenAI St… --- ## [Azure OpenAI Deployed Model Suddenly throw 400 for Assistant API Streaming](https://community.openai.com/t/azure-openai-deployed-model-suddenly-throw-400-for-assistant-api-streaming/1131401)
**Author:** [@noelpointer](https://community.openai.com/u/noelpointer)\ **Replies:** 0\ **Last updated:** [February 27, 2025, 7:29pm UTC](https://community.openai.com/t/azure-openai-deployed-model-suddenly-throw-400-for-assistant-api-streaming/1131401 "2025-02-27T19:29:49Z")
Yesterday morning (around 8:22am ET) an Azure deployed model consistently started returning 400 errors for the Assistant API streaming responses. The error: HTTP 400 (invalid\_request\_error: unsupported\_model) Parameter… --- ## [Do we also have streaming support for azure openai for o1-preview](https://community.openai.com/t/do-we-also-have-streaming-support-for-azure-openai-for-o1-preview/1035400)
**Author:** [@fern2](https://community.openai.com/u/fern2)\ **Replies:** 6\ **Last updated:** [January 31, 2025, 1:50am UTC](https://community.openai.com/t/do-we-also-have-streaming-support-for-azure-openai-for-o1-preview/1035400 "2025-01-31T01:50:31Z")
Do we also have streaming support for azure openai for o1-preview? I’m asking because I now open ai released streaming support for the standard API. --- ## [How to tackle similar section names in RAG?](https://community.openai.com/t/how-to-tackle-similar-section-names-in-rag/1060758)
**Author:** [@saurabh\_harak](https://community.openai.com/u/saurabh_harak)\ **Replies:** 1\ **Last updated:** [December 18, 2024, 2:47pm UTC](https://community.openai.com/t/how-to-tackle-similar-section-names-in-rag/1060758 "2024-12-18T14:47:10Z")
Hello everyone, I am working on a Retrieval-Augmented Generation (RAG) use case involving documents like HR policies. While the application performs well with distinct data in the PDF files, we’re facing two major chall… --- ## [Azure OpenAI GPT-4o mini 2024-07-18 Structured Outputs \`response\_format\` not working](https://community.openai.com/t/azure-openai-gpt-4o-mini-2024-07-18-structured-outputs-response-format-not-working/908217)
**Author:** [@yl95](https://community.openai.com/u/yl95)\ **Replies:** 8\ **Last updated:** [November 18, 2024, 7:47pm UTC](https://community.openai.com/t/azure-openai-gpt-4o-mini-2024-07-18-structured-outputs-response-format-not-working/908217 "2024-11-18T19:47:47Z")
trying to replicate the math tutor example using Azure OpenAI API, but response\_format is flagged as “Invalid parameter”. Full error message: "name": "BadRequestError", "message": "Error code: 400 - {'error': {'messa… --- ## [Issue with Azure OpenAI Integration: Response Returning None and Debugging Steps](https://community.openai.com/t/issue-with-azure-openai-integration-response-returning-none-and-debugging-steps/1019675)
**Author:** [@ssingh](https://community.openai.com/u/ssingh)\ **Replies:** 0\ **Last updated:** [November 15, 2024, 5:50pm UTC](https://community.openai.com/t/issue-with-azure-openai-integration-response-returning-none-and-debugging-steps/1019675 "2024-11-15T17:50:00Z")
Hi everyone, I’m working on an application that integrates with Azure OpenAI using the azure-openai Python SDK. My setup includes functionality for creating assistants, uploading files to a vector store, and requesting … --- ## [Error 500 with structured outputs using Azure](https://community.openai.com/t/error-500-with-structured-outputs-using-azure/956870)
**Author:** [@bachtruoq](https://community.openai.com/u/bachtruoq)\ **Replies:** 7\ **Last updated:** [November 14, 2024, 9:02pm UTC](https://community.openai.com/t/error-500-with-structured-outputs-using-azure/956870 "2024-11-14T21:02:18Z")
My first resquest using structured outputs with gpt-4o version 2024-08-01-preview went succesfully. However, now, whenever I change my schema I get a openai.InternalServerError: Error code: 500 - {‘error’: {‘message’: ‘T… --- ## [Post Processing Failed during Fine Tuning gpt-4o](https://community.openai.com/t/post-processing-failed-during-fine-tuning-gpt-4o/994209)
**Author:** [@anukuttantpm](https://community.openai.com/u/anukuttantpm)\ **Replies:** 1\ **Last updated:** [October 27, 2024, 4:34pm UTC](https://community.openai.com/t/post-processing-failed-during-fine-tuning-gpt-4o/994209 "2024-10-27T16:34:38Z")
Hi, I’ve been trying to find tune gpt 4o with images for object recognition. But, while training the model through Azure, it’s showing like post processing failed. what might be the issue? --- ## [Issue with Error 400 "Repetitive Patterns" Triggered by Message History](https://community.openai.com/t/issue-with-error-400-repetitive-patterns-triggered-by-message-history/965638)
**Author:** [@ginkiro](https://community.openai.com/u/ginkiro)\ **Replies:** 0\ **Last updated:** [October 3, 2024, 8:37am UTC](https://community.openai.com/t/issue-with-error-400-repetitive-patterns-triggered-by-message-history/965638 "2024-10-03T08:37:38Z")
Hello, I’ve encountered an issue related to the 400 “Repetitive Patterns” error. The problem arises when a user sends messages that include previous conversation history. In this scenario, it’s unclear which specific me… --- ## [Help with using Structured Outputs for JSON Patch Generation and Handling the "value" Field in JSON Schema](https://community.openai.com/t/help-with-using-structured-outputs-for-json-patch-generation-and-handling-the-value-field-in-json-schema/963495)
**Author:** [@ginkiro](https://community.openai.com/u/ginkiro)\ **Replies:** 5\ **Last updated:** [October 2, 2024, 4:27pm UTC](https://community.openai.com/t/help-with-using-structured-outputs-for-json-patch-generation-and-handling-the-value-field-in-json-schema/963495 "2024-10-02T16:27:08Z")
Hi everyone, I’m working on generating JSON Patch operations using Structured Outputs, and I’m running into an issue with defining the value field in my JSON Schema. As you know, the value field in a JSON Patch operatio… --- ## [What 'purpose' value to use in files.create with AzureOpenAI?](https://community.openai.com/t/what-purpose-value-to-use-in-files-create-with-azureopenai/883775)
**Author:** [@toromanow](https://community.openai.com/u/toromanow)\ **Replies:** 2\ **Last updated:** [September 7, 2024, 4:14pm UTC](https://community.openai.com/t/what-purpose-value-to-use-in-files-create-with-azureopenai/883775 "2024-09-07T16:14:53Z")
the client.files.create API used to upload files to the assistant takes in the ‘purpose’ value. I’ve been using the ‘assistants’ value just fine. But when switching to AzureOpenAI I’m getting an error: Error code: 400 -… --- ## [Azure .net OpenAI Client: Usage disabled for streamed completion](https://community.openai.com/t/azure-net-openai-client-usage-disabled-for-streamed-completion/861421)
**Author:** [@stramont](https://community.openai.com/u/stramont)\ **Replies:** 1\ **Last updated:** [September 3, 2024, 10:38am UTC](https://community.openai.com/t/azure-net-openai-client-usage-disabled-for-streamed-completion/861421 "2024-09-03T10:38:38Z")
Hello, I’ve been trying to retrieve the Usage information when I stream chat completions using the Azure OpenAI client. I used this post from the OpenAI changelog for guidance: May 6th, 2024 https://platform.openai.com… --- ## [Azure API for gpt4o for video processing](https://community.openai.com/t/azure-api-for-gpt4o-for-video-processing/907104)
**Author:** [@ryonatan6](https://community.openai.com/u/ryonatan6)\ **Replies:** 0\ **Last updated:** [August 14, 2024, 3:17pm UTC](https://community.openai.com/t/azure-api-for-gpt4o-for-video-processing/907104 "2024-08-14T15:17:32Z")
Am trying to process vids with the azure openai interphase inside azure ml/AI studio. the image processing works ok but the videos frames are not working, anyone else delt with this issue? --- ## [Retrieval from Azure Index (as Vector Database)](https://community.openai.com/t/retrieval-from-azure-index-as-vector-database/899617)
**Author:** [@sa\_labrats](https://community.openai.com/u/sa_labrats)\ **Replies:** 0\ **Last updated:** [August 8, 2024, 3:23pm UTC](https://community.openai.com/t/retrieval-from-azure-index-as-vector-database/899617 "2024-08-08T15:23:44Z")
Hi All, I have been working on Azure + OpenAI integration and how we can use Azure Index as an large scale vector database. My Use case: Take pdf documents as input (doc size \>= 25 pages) Divide each document into su… --- ## [How can I write a POST request for Azure OpenAI that uses structured output?](https://community.openai.com/t/how-can-i-write-a-post-request-for-azure-openai-that-uses-structured-output/898569)
**Author:** [@Franck.Dernoncourt](https://community.openai.com/u/Franck.Dernoncourt)\ **Replies:** 0\ **Last updated:** [August 8, 2024, 2:41am UTC](https://community.openai.com/t/how-can-i-write-a-post-request-for-azure-openai-that-uses-structured-output/898569 "2024-08-08T02:41:24Z")
I want to write a POST request for Azure OpenAI that uses structured output. https://azure.microsoft.com/en-us/blog/announcing-a-new-openai-feature-for-developers-on-azure/ says: Here’s an example API call to illustra… --- ## [Any Option to Enable Semantic Cache on AsyncAzureOpenAI?](https://community.openai.com/t/any-option-to-enable-semantic-cache-on-asyncazureopenai/850420)
**Author:** [@mdsa3d](https://community.openai.com/u/mdsa3d)\ **Replies:** 0\ **Last updated:** [July 2, 2024, 9:32am UTC](https://community.openai.com/t/any-option-to-enable-semantic-cache-on-asyncazureopenai/850420 "2024-07-02T09:32:03Z")
I am looking for a way to enable caching on AsyncAzureOpenAI. Currently, I am exploring the redisvl library using the sample app provided by microsoft (github: microsoft/sample-app-aoai-chatGPT) Does anyone have experie… --- ## [New tool\_choice as required is not available on azure](https://community.openai.com/t/new-tool-choice-as-required-is-not-available-on-azure/740735)
**Author:** [@abdurrahman.beyaz](https://community.openai.com/u/abdurrahman.beyaz)\ **Replies:** 2\ **Last updated:** [June 19, 2024, 12:40pm UTC](https://community.openai.com/t/new-tool-choice-as-required-is-not-available-on-azure/740735 "2024-06-19T12:40:32Z")
according to the latest api\_version available on Azure 2024-04-01. tool\_choice is not supporting required option. any idea when it will be available? --- ## [Upload a document to Assistant Vector Store in Azure Open AI](https://community.openai.com/t/upload-a-document-to-assistant-vector-store-in-azure-open-ai/818734)
**Author:** [@srai.bi](https://community.openai.com/u/srai.bi)\ **Replies:** 1\ **Last updated:** [June 14, 2024, 7:04am UTC](https://community.openai.com/t/upload-a-document-to-assistant-vector-store-in-azure-open-ai/818734 "2024-06-14T07:04:49Z")
Hi, I am looking for HTTPs REST API to upload a document to Vector Store which is available in Azure Open AI. So that my Assistant can query on this document. Cannot use AzureOpenAI API as I would need to install DLLs … --- ## [Issues and training when updating the LLM model on a project](https://community.openai.com/t/issues-and-training-when-updating-the-llm-model-on-a-project/816017)
**Author:** [@dgovergun](https://community.openai.com/u/dgovergun)\ **Replies:** 3\ **Last updated:** [June 13, 2024, 4:24pm UTC](https://community.openai.com/t/issues-and-training-when-updating-the-llm-model-on-a-project/816017 "2024-06-13T16:24:52Z")
We are building an AI tool that allows querying data from an SQL database. Langchain is used as the foundation for training models, maintaining chat history, and integrating with different LLM providers/APIs. The main i… --- ## [Chat.completions.create cannot work well when tool choice is set to required](https://community.openai.com/t/chat-completions-create-cannot-work-well-when-tool-choice-is-set-to-required/810996)
**Author:** [@zhwbin65](https://community.openai.com/u/zhwbin65)\ **Replies:** 0\ **Last updated:** [June 11, 2024, 3:34am UTC](https://community.openai.com/t/chat-completions-create-cannot-work-well-when-tool-choice-is-set-to-required/810996 "2024-06-11T03:34:39Z")
Hi, I am trying to build tool function with the following example. It is found that the tool choice paramter cannot be set to required or there will incur error. Can you help explain the right way to set required mode #e… --- ## [Replacement for RateLimitError in AzureOpenAI 1.0.0+](https://community.openai.com/t/replacement-for-ratelimiterror-in-azureopenai-1-0-0/601558)
**Author:** [@malos318](https://community.openai.com/u/malos318)\ **Replies:** 1\ **Last updated:** [June 4, 2024, 12:19pm UTC](https://community.openai.com/t/replacement-for-ratelimiterror-in-azureopenai-1-0-0/601558 "2024-06-04T12:19:56Z")
Hello everyone! I updated my Python code to use the new version of the OpenAI module. The requests themselves work fine, including embeddings. However I previously checked for RateLimitErrors, so I could wait before r… --- ## [Using Azure OpenAI Client with Assistants: Does It Work?](https://community.openai.com/t/using-azure-openai-client-with-assistants-does-it-work/783260)
**Author:** [@efimluboshnikov](https://community.openai.com/u/efimluboshnikov)\ **Replies:** 2\ **Last updated:** [June 1, 2024, 1:23pm UTC](https://community.openai.com/t/using-azure-openai-client-with-assistants-does-it-work/783260 "2024-06-01T13:23:39Z")
I started to work with Assistants. I use my Azure account. I got error even in first tutorial Tutorial Creating Assistants OpenAI python lib version: ‘1.23.6’ Initialize client client = openai.AzureOpenAI( azure\_e… [Next page](https://community.openai.com/tag/azure/419.md?match_all_tags=true&page=1&tags%5B%5D=azure)