From 12e4eca0427220d184a6d9456d37fca59454d38e Mon Sep 17 00:00:00 2001 From: Pamela Fox Date: Wed, 26 Nov 2025 10:18:21 -0800 Subject: [PATCH 1/6] Increase embedding TPM capacity and add note in cloud ingestion guide --- docs/data_ingestion.md | 12 +++++++++--- infra/main.bicep | 2 +- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/docs/data_ingestion.md b/docs/data_ingestion.md index 41440bb7fe..898758d072 100644 --- a/docs/data_ingestion.md +++ b/docs/data_ingestion.md @@ -153,15 +153,21 @@ This project includes an optional feature to perform data ingestion in the cloud 3. Open `azure.yaml` and un-comment the document-extractor, figure-processor, and text-processor sections. Those are the Azure Functions apps that will be deployed and serve as Azure AI Search skills. -4. Provision the new Azure Functions resources, deploy the function apps, and update the search indexer with: +4. (Recommended) Increase the capacity for the embedding model to the maximum quota allowed for your region/subscription, so that the Azure Functions can generate embeddings without hitting rate limits: + + ```shell + azd env set AZURE_OPENAI_EMB_DEPLOYMENT_CAPACITY 400 + ``` + +5. Provision the new Azure Functions resources, deploy the function apps, and update the search indexer with: ```shell azd up ``` -5. That will upload the documents in the `data/` folder to the Blob storage container, create the indexer and skillset, and run the indexer to ingest the data. You can monitor the indexer status from the portal. +6. That will upload the documents in the `data/` folder to the Blob storage container, create the indexer and skillset, and run the indexer to ingest the data. You can monitor the indexer status from the portal. -6. When you have new documents to ingest, you can upload documents to the Blob storage container and run the indexer from the Azure Portal to ingest new documents. +7. When you have new documents to ingest, you can upload documents to the Blob storage container and run the indexer from the Azure Portal to ingest new documents. ### Indexer architecture diff --git a/infra/main.bicep b/infra/main.bicep index 3fbbff3144..1fbcd9db49 100644 --- a/infra/main.bicep +++ b/infra/main.bicep @@ -231,7 +231,7 @@ var embedding = { deploymentName: !empty(embeddingDeploymentName) ? embeddingDeploymentName : 'text-embedding-3-large' deploymentVersion: !empty(embeddingDeploymentVersion) ? embeddingDeploymentVersion : (embeddingModelName == 'text-embedding-ada-002' ? '2' : '1') deploymentSkuName: !empty(embeddingDeploymentSkuName) ? embeddingDeploymentSkuName : (embeddingModelName == 'text-embedding-ada-002' ? 'Standard' : 'GlobalStandard') - deploymentCapacity: embeddingDeploymentCapacity != 0 ? embeddingDeploymentCapacity : 30 + deploymentCapacity: embeddingDeploymentCapacity != 0 ? embeddingDeploymentCapacity : 200 dimensions: embeddingDimensions != 0 ? embeddingDimensions : 3072 } From 21cb2a10ed1cabb634dec2dea854f7326a28e343 Mon Sep 17 00:00:00 2001 From: Pamela Fox Date: Wed, 26 Nov 2025 10:25:28 -0800 Subject: [PATCH 2/6] Update markdown lint --- .github/workflows/lint-markdown.yml | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/.github/workflows/lint-markdown.yml b/.github/workflows/lint-markdown.yml index 34077ffbfb..7d38e9d67e 100644 --- a/.github/workflows/lint-markdown.yml +++ b/.github/workflows/lint-markdown.yml @@ -14,9 +14,10 @@ jobs: steps: - name: Checkout repo uses: actions/checkout@v5 - - name: Run markdownlint - uses: articulate/actions-markdownlint@v1 + - name: Run markdownlint-cli2 + uses: DavidAnson/markdownlint-cli2-action@v21 with: config: .github/workflows/markdownlint-config.json - files: '**/*.md' - ignore: data/ + globs: | + **/*.md + !data/** From cce7b76036092250a647a6af42763acd0592d9fd Mon Sep 17 00:00:00 2001 From: Pamela Fox Date: Wed, 26 Nov 2025 10:30:15 -0800 Subject: [PATCH 3/6] Better config format --- .github/workflows/lint-markdown.yml | 2 +- .../markdownlint-config.json => .markdownlint-cli2.json | 0 2 files changed, 1 insertion(+), 1 deletion(-) rename .github/workflows/markdownlint-config.json => .markdownlint-cli2.json (100%) diff --git a/.github/workflows/lint-markdown.yml b/.github/workflows/lint-markdown.yml index 7d38e9d67e..80f8146f01 100644 --- a/.github/workflows/lint-markdown.yml +++ b/.github/workflows/lint-markdown.yml @@ -17,7 +17,7 @@ jobs: - name: Run markdownlint-cli2 uses: DavidAnson/markdownlint-cli2-action@v21 with: - config: .github/workflows/markdownlint-config.json + config: .markdownlint-cli2.json globs: | **/*.md !data/** diff --git a/.github/workflows/markdownlint-config.json b/.markdownlint-cli2.json similarity index 100% rename from .github/workflows/markdownlint-config.json rename to .markdownlint-cli2.json From 2f89549a605a0c9c45dd8bbe4bccc540e48b2cb6 Mon Sep 17 00:00:00 2001 From: Pamela Fox Date: Wed, 26 Nov 2025 10:31:15 -0800 Subject: [PATCH 4/6] Better config format --- .github/workflows/lint-markdown.yml | 2 +- .markdownlint-cli2.json => .markdownlint-cli2.jsonc | 0 2 files changed, 1 insertion(+), 1 deletion(-) rename .markdownlint-cli2.json => .markdownlint-cli2.jsonc (100%) diff --git a/.github/workflows/lint-markdown.yml b/.github/workflows/lint-markdown.yml index 80f8146f01..5fa45bb5e8 100644 --- a/.github/workflows/lint-markdown.yml +++ b/.github/workflows/lint-markdown.yml @@ -17,7 +17,7 @@ jobs: - name: Run markdownlint-cli2 uses: DavidAnson/markdownlint-cli2-action@v21 with: - config: .markdownlint-cli2.json + config: .markdownlint-cli2.jsonc globs: | **/*.md !data/** diff --git a/.markdownlint-cli2.json b/.markdownlint-cli2.jsonc similarity index 100% rename from .markdownlint-cli2.json rename to .markdownlint-cli2.jsonc From c0f5e5f8913ead93ccd27f3e8f9dbf32d633d019 Mon Sep 17 00:00:00 2001 From: Pamela Fox Date: Wed, 26 Nov 2025 10:33:40 -0800 Subject: [PATCH 5/6] Fix the config --- .markdownlint-cli2.jsonc | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/.markdownlint-cli2.jsonc b/.markdownlint-cli2.jsonc index 5f4341b93b..91e176647e 100644 --- a/.markdownlint-cli2.jsonc +++ b/.markdownlint-cli2.jsonc @@ -1,5 +1,7 @@ { - "default": true, - "line-length": false, - "MD033": { "allowed_elements": ["br", "details", "summary"] } + "config": { + "default": true, + "line-length": false, + "MD033": { "allowed_elements": ["br", "details", "summary"] } + } } From 887350f00a3babec348c8c15f7ebdddb183dd7f0 Mon Sep 17 00:00:00 2001 From: Pamela Fox Date: Wed, 26 Nov 2025 10:39:35 -0800 Subject: [PATCH 6/6] Ignore table style rule --- .github/workflows/lint-markdown.yml | 1 + .markdownlint-cli2.jsonc | 1 + SECURITY.md | 3 +-- 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/.github/workflows/lint-markdown.yml b/.github/workflows/lint-markdown.yml index 5fa45bb5e8..280bcabca2 100644 --- a/.github/workflows/lint-markdown.yml +++ b/.github/workflows/lint-markdown.yml @@ -21,3 +21,4 @@ jobs: globs: | **/*.md !data/** + !.github/** diff --git a/.markdownlint-cli2.jsonc b/.markdownlint-cli2.jsonc index 91e176647e..e0256fc096 100644 --- a/.markdownlint-cli2.jsonc +++ b/.markdownlint-cli2.jsonc @@ -2,6 +2,7 @@ "config": { "default": true, "line-length": false, + "table-column-style": false, "MD033": { "allowed_elements": ["br", "details", "summary"] } } } diff --git a/SECURITY.md b/SECURITY.md index 388e9ad471..aea2cf2731 100644 --- a/SECURITY.md +++ b/SECURITY.md @@ -1,6 +1,5 @@ - -## Security +# Security Microsoft takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organizations, which include [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin), and [our GitHub organizations](https://opensource.microsoft.com/).