Formerly known as Azure AI Services or Azure Cognitive Services is a unified collection of prebuilt AI capabilities within the Microsoft Foundry platform
Hello @Meenakshi Kathiresan ,
Welcome to Microsoft Q&A .Thank you for reaching out to us.
The observed behavior during migration from the v1 experience (PersistentAgentClient) to the v2 experience (ProjectClient) aligns with how resources are structured within the Foundry project model.
As asked -
- Files and vector stores across v1 and v2 Files and vector stores operate as resources associated with the Foundry project and are not owned by a specific agent definition. A vector store is created independently and then attached to agents or conversations as needed. As a result:
- Files created in v1 remain accessible in v2 when used within the same project
- Vector stores created earlier can continue to be reused across newer agent workflows
- The same vector store can be associated with multiple agents or conversations within that project scope
- Behavior supportability and expectations The reuse of files and vector stores across different experiences is consistent with the current architecture, where these artifacts are managed as project-level data resources rather than agent-specific entities.
Agents are not shared between versions as agent definitions are handled differently from data resources. During migration it is suggested that runtime components such as agents and related configurations are version-scoped and must be recreated when moving between experiences.
This results in:
- Agents created in v1 not appearing in v2
- Recreation of agents being required during migration
- Separation between agent runtime configuration and reusable data resources
To ensure a stable and forward-aligned migration , please
- Reuse existing files and vector stores without duplication
- Recreate agent definitions using the v2 (
ProjectClient) model - Transition workflows fully to v2 instead of maintaining mixed usage across versions
If any inconsistencies are observed, please check if the following help
- If files or vector stores not visible then
- Confirm both workflows are pointing to the same Foundry project endpoint
- Validate subscription, tenant, and project alignment
- Ensure appropriate role-based access permissions are assigned
- For vector store behavior issues
- Please verify that the correct vector store is attached in the v2 agent configuration
- Then confirm ingestion has completed successfully before querying
- Revalidate data indexing if retrieval results appear inconsistent
- For agent availability differences
- Please confirm expected behavior due to version-specific agent models
- Reconfigure tools, bindings, and settings in the v2 agent setup
The following references might be helpful , please check them out
- How to use Azure OpenAI Assistants file search (classic) - Microsoft Foundry (classic) portal | Microsoft Learn
- Vector stores for file search in Microsoft Foundry Agent Service - Microsoft Foundry | Microsoft Learn
- File search tool for Microsoft Foundry agents - Microsoft Foundry | Microsoft Learn
- Set up your environment for Foundry Agent Service - Microsoft Foundry | Microsoft Learn
Thank you