agent/agent-framework
2
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Python: [BREAKING] Python: move Azure AI embeddings to Foundry (#5056)

Browse Source 
* renamed AzureAIINferenceEmbeddings and lazy load azure-cosmos and env var rename

* updated coverage

* fix readme
This commit is contained in:
Eduard van Valkenburg
2026-04-02 13:26:35 +02:00
committed by GitHub
Unverified
parent 47d82911c0
commit 95fd5ec658
74 changed files with 403 additions and 978 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/02-agents/devui/.env.example
+1 -1
View File
@@ -8,7 +8,7 @@ FOUNDRY_MODEL=gpt-4o
# Azure OpenAI workflow sample
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
AZURE_OPENAI_RESPONSES_MODEL=gpt-4o
AZURE_OPENAI_CHAT_MODEL=gpt-4o
# Optional fallback env name also supported by workflow_with_agents/workflow.py:
AZURE_OPENAI_MODEL=gpt-4o
# Optional if you need to override the default API version:
python/samples/02-agents/devui/README.md
+2 -2
View File
@@ -94,7 +94,7 @@ workflow_name/
| Sample | What it demonstrates | Required keys / auth |
| ------ | -------------------- | -------------------- |
| [**workflow_declarative/**](workflow_declarative/) | A YAML-defined workflow loaded through `WorkflowFactory`, with nested age-based branching and no model client code. | None |
| [**workflow_with_agents/**](workflow_with_agents/) | A content review workflow that uses agents as executors and routes based on structured review output (`Writer -> Reviewer -> Editor/Publisher -> Summarizer`). | `AZURE_OPENAI_ENDPOINT`, plus `AZURE_OPENAI_RESPONSES_MODEL` or `AZURE_OPENAI_MODEL`; Azure CLI auth via `az login`; `AZURE_OPENAI_API_VERSION` is optional |
| [**workflow_with_agents/**](workflow_with_agents/) | A content review workflow that uses agents as executors and routes based on structured review output (`Writer -> Reviewer -> Editor/Publisher -> Summarizer`). | `AZURE_OPENAI_ENDPOINT`, plus `AZURE_OPENAI_CHAT_MODEL` or `AZURE_OPENAI_MODEL`; Azure CLI auth via `az login`; `AZURE_OPENAI_API_VERSION` is optional |
| [**workflow_spam/**](workflow_spam/) | A multi-step spam detection workflow with human-in-the-loop approval, branching for spam vs. legitimate messages, and a final reporting step. | None |
| [**workflow_fanout/**](workflow_fanout/) | A larger fan-out/fan-in data processing workflow with parallel validation, multiple transformations, QA, aggregation, and demo failure toggles. | None |
@@ -130,7 +130,7 @@ export FOUNDRY_MODEL="gpt-4o"
# Azure OpenAI workflow_with_agents sample
export AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com"
export AZURE_OPENAI_RESPONSES_MODEL="gpt-4o"
export AZURE_OPENAI_CHAT_MODEL="gpt-4o"
export AZURE_OPENAI_MODEL="gpt-4o"
az login
python/samples/02-agents/devui/workflow_with_agents/.env.example
+1 -1
View File
@@ -2,7 +2,7 @@
# This sample uses Azure CLI auth, so run `az login` before starting DevUI.
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
AZURE_OPENAI_RESPONSES_MODEL=gpt-4o
AZURE_OPENAI_CHAT_MODEL=gpt-4o
# Optional fallback env name also supported by the client:
# AZURE_OPENAI_MODEL=gpt-4o
# Optional if you need to override the default API version:
python/samples/02-agents/devui/workflow_with_agents/workflow.py
+1 -1
View File
@@ -65,7 +65,7 @@ def is_approved(message: Any) -> bool:
# Create Azure OpenAI Responses chat client
client = OpenAIChatClient(
model=os.environ.get("AZURE_OPENAI_RESPONSES_MODEL") or os.environ.get("AZURE_OPENAI_MODEL"),
model=os.environ.get("AZURE_OPENAI_CHAT_MODEL") or os.environ.get("AZURE_OPENAI_MODEL"),
azure_endpoint=os.environ.get("AZURE_OPENAI_ENDPOINT"),
api_version=os.environ.get("AZURE_OPENAI_API_VERSION"),
credential=AzureCliCredential(),