Title: Synthetic Dataset Format from AI Foundry Not Compatible with Evaluation Schema
Current Situation The synthetic dataset created from AI Foundry Data Synthetic Data is generated in the following messages format { "messages": [ { "role": "system", "content": "You are a helpful assistant" }, { "role": "user", "content": "What is the primary purpose?" }, { "role": "assistant", "content": "The primary purpose is..." } ] } Challenge When attempting evaluation, especially RAG evaluation, the documentation indicates that the dataset must contain structured fields such as question - The query being asked ground_truth - The expected answer Recommended additional fields reference_context metadata Example required format { "question": "", "ground_truth": "", "reference_context": "", "metadata": { "document": "" } } Because the synthetic dataset is in messages format, I am unable to directly map it to the required evaluation schema. Question Is there a recommended or supported way to convert the synthetic dataset generated in AI Foundry messages format into the structured format required for evaluation? Can the user role be mapped to question? Can the assistant role be mapped to ground_truth? Is there any built in transformation option within AI Foundry?
Is there a way to connect 2 Ai foundry to the same cosmos containers?
I defined Azure AI Foundry Connection for Azure Cosmos DB and BYO Thread Storage in Azure AI Agent Service by using these instructions: Integration with Azure AI Agent Service - Azure Cosmos DB for NoSQL | Microsoft Learn I see that it created 3 containers under the cosmos I provided: <guid>-agent-entity-store v-system-thread-message-store <guid>-thread-message-store Now I created another AI foundry and added a connection for the same AI foundry, and it created 3 different containers under the same DB. Is there a way that they'll use the same exact containers? I want to use multiple AI foundries, and they will use the same Cosmos containers to manage the data.
Less models in ai foundry that supports agentic use
Hi, I have seen that nearly 11,000 models are available in Azure ai foundry, but when I try to deploy models that support Agents, only 18 models are available for selection. Is there any reason behind this ? Are we planning to support many models from external providers or rely on gpt models as first priority
AI Foundry - Open API spec tool issue
Hello, I'm trying to invoke my application's API as a tool within the AI Foundry OpenAPI specification tool. However, I keep encountering a 401 Unauthorized error. I'm using a Bearer token for authentication, and it works perfectly when tested via Postman. I'm unsure whether the issue lies in the input/output schema or the connection configuration. Unfortunately, the AI Foundry Traces aren't providing enough detail to pinpoint the exact problem. Additionally, my API and AI Foundry accounts are hosted in different Azure subscriptions and networks. Could this network separation be affecting the connection? I would appreciate any guidance or help to resolve this issue. -Tamizh
Is AI Foundry in new exam for DP-100
A 25-30% of the DP-100 exam is now dedicated to Optimizing Language Models for AI Applications - is this requiring Azure AI Foundry? It doesn't say specifically in the study guide: https://learn.microsoft.com/en-us/credentials/certifications/resources/study-guides/dp-100 Also, the videos could benefit from being updated to cover the changes as of 16 January 2025.
