yujunjun/graphrag-accelerator
1
0
Fork 0
mirror of https://github.com/Azure-Samples/graphrag-accelerator.git synced 2025-06-27 04:39:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

update docs re: subscription consistency (#57)

Browse Source 
Co-authored-by: Josh Bradley <joshbradley@microsoft.com>
This commit is contained in:
Chris Sanchez 2024-07-10 02:04:15 -06:00 committed by GitHub
parent 0abbfb2a5f
commit a86f20c60e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 20 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docs/DEPLOYMENT-GUIDE.md
View File

@ -43,7 +43,8 @@ az provider show --namespace Microsoft.AlertsManagement -o table
## Installation
### 1. Deploy Azure OpenAI Service
You will need access to a deployed Azure OpenAI resource. Documentation on how to deploy an Azure OpenAI service resource can be found [here](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/create-resource?pivots=web-portal). Ensure deployments for the `gpt-4-turbo` model and `text-embedding-ada-002` embedding model are setup. Take note of the model deployment name and model name.
You will need access to a deployed Azure OpenAI (AOAI) resource. Otherwise documentation on how to deploy an AOAI service can be found [here](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/create-resource?pivots=web-portal). Ensure deployments for the `gpt-4 turbo` model and `text-embedding-ada-002` embedding model are setup. Take note of the model deployment name and model name.
Note that the AOAI instance **must** be in the same subscription that you plan to deploy this solution accelerator in.
As a starting point, we recommend the following quota thresholds be setup for this solution accelerator to run.
| Model Name | TPM Threshold |
@ -53,8 +54,9 @@ text-embedding-ada-002 | 300K
### 2. Login to Azure
Login with Azure CLI and set the appropriate Azure subscription.
```shell
# login to Azure - may need to use use the "--use-device-code" flag if using a remote host/virtual machine
# login to Azure - may need to use the "--use-device-code" flag if using a remote host/virtual machine
az login
# check what subscription you are logged into
az account show
@ -79,7 +81,7 @@ In the `deploy.parameters.json` file, provide values for the following required
`LOCATION` | <my_location> | Yes | The azure cloud region to deploy GraphRAG resources in.
`CONTAINER_REGISTRY_SERVER` | <my_container_registry>.azurecr.io | No | Name of an existing Azure Container Registry where the `graphrag` backend docker image is hosted. Will get created automatically if not provided.
`GRAPHRAG_IMAGE` | graphrag:backend | No | The name and tag of the graphrag docker image in the container registry. Will default to `graphrag:backend`.
`GRAPHRAG_API_BASE` | | Yes | Azure OpenAI service endpoint.
`GRAPHRAG_API_BASE` | https://<my_openai_name>.openai.azure.com | Yes | Azure OpenAI service endpoint.
`GRAPHRAG_API_VERSION` | 2023-03-15-preview | Yes | Azure OpenAI API version.
`GRAPHRAG_LLM_MODEL` | gpt-4 | Yes | Name of the gpt-4 turbo model.
`GRAPHRAG_LLM_DEPLOYMENT_NAME` | | Yes | Deployment name of the gpt-4 turbo model.