Skip to content

Commit

Permalink
Merge pull request #4 from AbeOmor/main
Browse files Browse the repository at this point in the history
Update docs to sync with Microsoft Docs
  • Loading branch information
AbeOmor committed Sep 13, 2023
2 parents ea7ef74 + 49a91d1 commit 357a340
Show file tree
Hide file tree
Showing 4 changed files with 6 additions and 4 deletions.
2 changes: 1 addition & 1 deletion .github/workflows/run-eval-pf-pipeline.yml
Original file line number Diff line number Diff line change
Expand Up @@ -90,4 +90,4 @@ jobs:
fi
- name: Register promptflow model
if: ${{ steps.jobMetricAssert.outputs.result == 'true' }}
run: az ml model create --file promptflow/deployment/model.yaml -g ${{env.GROUP}} -w ${{env.WORKSPACE}}
run: az ml model create --file promptflow/deployment/model.yaml -g ${{env.GROUP}} -w ${{env.WORKSPACE}}
4 changes: 3 additions & 1 deletion docs/e2e_llmops_with_promptflow.md
Original file line number Diff line number Diff line change
Expand Up @@ -210,7 +210,7 @@ With the Prompt flow model registered in the Machine learning workspace, you are

## Deploy Prompt Flow in AzureML with GitHub Actions

This scenario includes prebuilt workflows for two approaches to deploying a trained model, batch scoring or a deploying a model to an endpoint for real-time scoring. You may run either or both of these workflows to test the performance of the model in your Azure Machine Learning workspace.
This scenario includes prebuilt workflows for deploying a model to an endpoint for real-time scoring. You may run the workflow to test the performance of the model in your Azure Machine Learning workspace.

### Online Endpoint
Expand All @@ -232,6 +232,8 @@ This scenario includes prebuilt workflows for two approaches to deploying a trai

![Screenshot of Machine Learning taxi Online endpoint test.](media/e2e-llmops/azure-ml-online-endpoint-test.png)

> [!NOTE]
> Make sure you have already [granted permissions to the endpoint](https://review.learn.microsoft.com/en-us/azure/machine-learning/prompt-flow/how-to-deploy-for-real-time-inference#grant-permissions-to-the-endpoint) before you test or consume the endpoint.
## Moving to production

Expand Down
2 changes: 1 addition & 1 deletion promptflow/web-classification/run.yml
Original file line number Diff line number Diff line change
Expand Up @@ -11,4 +11,4 @@ connections:
deployment_name: gpt-35-turbo-0301
summarize_text_content:
connection: Default_AzureOpenAI
deployment_name: gpt-35-turbo-0301
deployment_name: gpt-35-turbo-0301
2 changes: 1 addition & 1 deletion promptflow/web-classification/run_evaluation.yml
Original file line number Diff line number Diff line change
Expand Up @@ -15,4 +15,4 @@ connections:
deployment_name: gpt-35-turbo-0301
summarize_text_content:
connection: Default_AzureOpenAI
deployment_name: gpt-35-turbo-0301
deployment_name: gpt-35-turbo-0301

0 comments on commit 357a340

Please sign in to comment.