You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+6-15Lines changed: 6 additions & 15 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
# Retrieval Augmented Generation (RAG) stack
2
2
3
-
To run the full stack. These steps will be updated as development progresses on the stack and underlaying DAs.
3
+
To run the full stack, follow these steps. These steps will be updated as development progresses on the stack and underlying DAs.
4
4
5
5
## 1. Deploy the stack in a new project from catalog
6
6
@@ -10,7 +10,9 @@ Click the "Add to project" button, and select create in new project.
10
10
11
11
## 2. Prereqs in target account
12
12
13
-
- Create an API key in the target account. Keep note of it. Give it admin privilege for now. Exact permissions will be narrowed down in future version.
13
+
Before deploying the stack, ensure you have:
14
+
- Created an API key in the target account with sufficient permissions. Note the API key, as it will be used later.
15
+
- For now, grant it admin privileges. The exact permissions required will be refined in future versions.
14
16
15
17
16
18
## 3. Set the input configuration for the stack
@@ -29,7 +31,7 @@ Click the "Add to project" button, and select create in new project.
29
31
"prefix": "<prefix for resources name - ensure unique>",
30
32
"ibmcloud_api_key": "<API Key of the target account with sufficient permissions>",
31
33
"resource_group_name": "<target resource group - name of a new resource group that the stack will creates>",
32
-
"region": "<region where resources are deployed>",
34
+
"region": "<region where all resources are deployed>",
Tips: If deployment fail in one of the DA, you may need to remove the configuration name of the deployment that already passes from the pattern before re-running the script.
77
-
78
-
Tips: to accelerate iteration you may deploy only a subset of the configurations: the bare minimum are key management, security manager, watson saas, alm and rag configuration da. Base account, observability and SCC are not on the critical path to get the app running.
79
-
80
-
81
-
# 5. Deploy the sample app
82
-
83
-
A few manual steps are required in the alpha version to trigger the deployment of the app:
84
-
1. In the secret manager instance, in the default group, create an arbitrary secret named "ibmcloud-api-key". Put the used api key as secret.
85
-
2. Follow the steps at https://cloud.ibm.com/docs/devsecops?topic=devsecops-devsecops-image-signing to generate a gpg key
86
-
3. In the secret manager instance, in the default group, create an arbitrary secret named "signing_key". Put the signing key. See https://cloud.ibm.com/docs/devsecops?topic=devsecops-devsecops-image-signing#cd-devsecops-gpg-store-secretsmgr
87
-
4. Navigate to the "Generative AI Sample App-CI-Toolchain" CD instance, click "ci-pipeline" and execute the "Manual Trigger".
78
+
Tips: If deployment fail in one of the DA, you may re-run the script as is. It will skip existing installed configuration.
Copy file name to clipboardExpand all lines: ibm_catalog.json
+11-4Lines changed: 11 additions & 4 deletions
Original file line number
Diff line number
Diff line change
@@ -14,7 +14,7 @@
14
14
"watson",
15
15
"ai"
16
16
],
17
-
"short_description": "A sample application that illustrates how to implement the RAG Pattern with watsonx.ai and IBM Cloud services.",
17
+
"short_description": "An automated solution that deploys a sample application illustrating how to implement the RAG Pattern with watsonx.ai and IBM Cloud services.",
0 commit comments