Skip to content

Commit

Permalink
Updated docs (#1925)
Browse files Browse the repository at this point in the history
  • Loading branch information
pamelafox committed Aug 20, 2024
1 parent 01a4111 commit d313c6a
Show file tree
Hide file tree
Showing 3 changed files with 31 additions and 11 deletions.
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -63,12 +63,12 @@ The repo includes sample data so it's ready to try end to end. In this sample ap
### Cost estimation

Pricing varies per region and usage, so it isn't possible to predict exact costs for your usage.
However, you can try the [Azure pricing calculator](https://azure.com/e/d18187516e9e421e925b3b311eec8aae) for the resources below.
However, you can try the [Azure pricing calculator](https://azure.com/e/a87a169b256e43c089015fda8182ca87) for the resources below.

- Azure App Service: Basic Tier with 1 CPU core, 1.75 GB RAM. Pricing per hour. [Pricing](https://azure.microsoft.com/pricing/details/app-service/linux/)
- Azure OpenAI: Standard tier, GPT and Ada models. Pricing per 1K tokens used, and at least 1K tokens are used per question. [Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/)
- Azure AI Document Intelligence: SO (Standard) tier using pre-built layout. Pricing per document page, sample documents have 261 pages total. [Pricing](https://azure.microsoft.com/pricing/details/form-recognizer/)
- Azure AI Search: Standard tier, 1 replica, free level of semantic search. Pricing per hour. [Pricing](https://azure.microsoft.com/pricing/details/search/)
- Azure AI Search: Basic tier, 1 replica, free level of semantic search. Pricing per hour. [Pricing](https://azure.microsoft.com/pricing/details/search/)
- Azure Blob Storage: Standard tier with ZRS (Zone-redundant storage). Pricing per storage and read operations. [Pricing](https://azure.microsoft.com/pricing/details/storage/blobs/)
- Azure Monitor: Pay-as-you-go tier. Costs based on data ingested. [Pricing](https://azure.microsoft.com/pricing/details/monitor/)

Expand Down
36 changes: 28 additions & 8 deletions docs/productionizing.md
Original file line number Diff line number Diff line change
Expand Up @@ -37,17 +37,37 @@ which you can specify using the `sku` property under the `storage` module in `in

### Azure AI Search

The default search service uses the `Standard` SKU
with the free semantic search option, which gives you 1000 free queries a month.
Assuming your app will experience more than 1000 questions, you should either change `semanticSearch`
to "standard" or disable semantic search entirely in the `/app/backend/approaches` files.
If you see errors about search service capacity being exceeded, you may find it helpful to increase
The default search service uses the "Basic" SKU
with the free semantic ranker option, which gives you 1000 free queries a month.
After 1000 queries, you will get an error message about exceeding the semantic ranker free capacity.

* Assuming your app will experience more than 1000 questions per month,
you should upgrade the semantic ranker SKU from "free" to "standard" SKU:

```shell
azd env set AZURE_SEARCH_SEMANTIC_RANKER standard
```

Or disable semantic search entirely:

```shell
azd env set AZURE_SEARCH_SEMANTIC_RANKER disabled
```

* The search service can handle fairly large indexes, but it does have per-SKU limits on storage sizes, maximum vector dimensions, etc. You may want to upgrade the SKU to either a Standard or Storage Optimized SKU, depending on your expected load.
However, you [cannot change the SKU](https://learn.microsoft.com/azure/search/search-sku-tier#tier-upgrade-or-downgrade) of an existing search service, so you will need to re-index the data or manually copy it over.
You can change the SKU by setting the `AZURE_SEARCH_SERVICE_SKU` azd environment variable to [an allowed SKU](https://learn.microsoft.com/azure/templates/microsoft.search/searchservices?pivots=deployment-language-bicep#sku).

```shell
azd env set AZURE_SEARCH_SERVICE_SKU standard
```

See the [Azure AI Search service limits documentation](https://learn.microsoft.com/azure/search/search-limits-quotas-capacity) for more details.

* If you see errors about search service capacity being exceeded, you may find it helpful to increase
the number of replicas by changing `replicaCount` in `infra/core/search/search-services.bicep`
or manually scaling it from the Azure Portal.

The search service can handle fairly large indexes, but it does have per-SKU limits on storage sizes, maximum vector dimensions, etc.
See the [service limits document](https://learn.microsoft.com/azure/search/search-limits-quotas-capacity) for more details.

### Azure App Service

The default app service plan uses the `Basic` SKU with 1 CPU core and 1.75 GB RAM.
Expand Down
2 changes: 1 addition & 1 deletion infra/main.parameters.json
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@
"value": "${AZURE_SEARCH_SERVICE_LOCATION}"
},
"searchServiceSkuName": {
"value": "${AZURE_SEARCH_SERVICE_SKU=standard}"
"value": "${AZURE_SEARCH_SERVICE_SKU=basic}"
},
"searchQueryLanguage": {
"value": "${AZURE_SEARCH_QUERY_LANGUAGE=en-us}"
Expand Down

0 comments on commit d313c6a

Please sign in to comment.