Skip to content

Increase embedding TPM capacity and add note in cloud ingestion guide #2846

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pamelafox merged 7 commits into from
Dec 1, 2025
Merged

Increase embedding TPM capacity and add note in cloud ingestion guide #2846

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
12e4eca
Increase embedding TPM capacity and add note in cloud ingestion guide
pamelafox Nov 26, 2025
21cb2a1
Update markdown lint
pamelafox Nov 26, 2025
cce7b76
Better config format
pamelafox Nov 26, 2025
2f89549
Better config format
pamelafox Nov 26, 2025
c0f5e5f
Fix the config
pamelafox Nov 26, 2025
887350f
Ignore table style rule
pamelafox Nov 26, 2025
a0ad452
Merge branch 'main' into embeddingtpm
pamelafox Dec 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 9 additions & 3 deletions docs/data_ingestion.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,8 @@
| ------ | ------------------------------------ | ------------------------ |
| PDF | Yes (DI or local with PyPDF) | Yes |
| HTML | Yes (DI or local with BeautifulSoup) | Yes |
| DOCX, PPTX, XLSX | Yes (DI) | Yes |

Check failure on line 32 in docs/data_ingestion.md

View workflow job for this annotation

GitHub Actions / Check for Markdown linting errors 

Table column style [Table pipe does not align with heading for style "aligned"]

Check failure on line 32 in docs/data_ingestion.md

View workflow job for this annotation

GitHub Actions / Check for Markdown linting errors 

Table column style [Table pipe does not align with heading for style "aligned"]

Check failure on line 32 in docs/data_ingestion.md

View workflow job for this annotation

GitHub Actions / Check for Markdown linting errors 

Table column style [Table pipe does not align with heading for style "aligned"]
| Images (JPG, PNG, BPM, TIFF, HEIFF)| Yes (DI) | Yes |

Check failure on line 33 in docs/data_ingestion.md

View workflow job for this annotation

GitHub Actions / Check for Markdown linting errors 

Table column style [Table pipe does not align with heading for style "aligned"]
| TXT | Yes (Local) | Yes |
| JSON | Yes (Local) | Yes |
| CSV | Yes (Local) | Yes |
Expand Down Expand Up @@ -153,15 +153,21 @@

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

Expand Down
2 changes: 1 addition & 1 deletion infra/main.bicep
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
}

Expand Down
Loading