Spaces:
Running
Running
Rename Operational_Instructions/AWS_and_Pinecone_Accounts_for_LiveRAG.md to Operational_Instructions/AWS_Accounts_for_LiveRAG.md
Browse files
Operational_Instructions/{AWS_and_Pinecone_Accounts_for_LiveRAG.md β AWS_Accounts_for_LiveRAG.md}
RENAMED
@@ -1,20 +1,18 @@
|
|
1 |
-
# AWS
|
2 |
-
|
3 |
-
## Using AWS Accounts
|
4 |
|
5 |
During the LiveRAG Challenge, participants may use two AWS accounts:
|
6 |
-
- **
|
7 |
-
- **
|
8 |
|
9 |
Using these accounts is optional but highly recommended to optimize both cost and effort.
|
10 |
|
11 |
-
## Using Your
|
12 |
|
13 |
Each participating group receives AWS credits for the duration of the competition.
|
14 |
The credits are limited, and any usage beyond the allocated amount will be charged to your personal payment method.
|
15 |
To ensure your credits are properly applied, follow the official AWS instructions [here](https://docs.aws.amazon.com/awsaccountbilling/latest/aboutv2/useconsolidatedbilling-credits.html).
|
16 |
|
17 |
-
###
|
18 |
|
19 |
1. **Create an AWS Account** β Sign up for an AWS account and add a payment method (typically a credit card). If you have an existing AWS account you may reuse it.
|
20 |
2. **Apply AWS Credits** β Follow the instructions in the provided AWS documentation to redeem and apply your credits.
|
@@ -22,26 +20,12 @@ To ensure your credits are properly applied, follow the official AWS instruction
|
|
22 |
- Use AWS Cost Management tools to monitor spending.
|
23 |
- Set up billing alarms using AWS CloudWatch to receive notifications when costs exceed predefined thresholds.
|
24 |
|
25 |
-
### Cost Optimization Recommendations
|
26 |
-
|
27 |
-
TII and AWS have estimated the cost of a typical teamβs infrastructure, including GPU usage, and AWS has provided credits accordingly.
|
28 |
-
However, individual teams may have varying requirements, so cost management is essential:
|
29 |
-
- **Shut down unused resources** β Always shut down GPUs and other compute instances when not in use.
|
30 |
-
- **Experiment on smaller datasets first** β This approach speeds up iteration cycles and reduces expenses before scaling up to larger datasets.
|
31 |
-
|
32 |
-
## Using the TII-Provided AWS Account
|
33 |
-
|
34 |
-
The TII-provided AWS account is strictly limited to specific use cases, primarily for accessing pre-built indices. These include:
|
35 |
-
|
36 |
-
- A **Sparse OpenSearch Index** hosted by AWS.
|
37 |
-
- A **Dense Pinecone Index** hosted by Pinecone, with access credentials stored on AWS.
|
38 |
-
|
39 |
|
40 |
### Access and Setup Instructions
|
41 |
|
42 |
-
To gain access and configure the
|
43 |
|
44 |
-
1. **Receive Sign-In Details** β You
|
45 |
2. **Sign In & Change Password** β Log in to the AWS console and update your password.
|
46 |
3. **Create AWS Command Line Interface (CLI) Credentials** β Generate an access key and secret for CLI usage.
|
47 |
4. **Configure AWS CLI Profile** β Run the following command to set up the CLI for this account and follow the instructions:
|
@@ -73,7 +57,12 @@ You're welcome to build your own Pinecone/OpenSearch, or other indices. We encou
|
|
73 |
|
74 |
For instructions pertaining to building your own Pinecone index see [here](Pinecone_for_LiveRAG.md).
|
75 |
|
76 |
-
|
|
|
|
|
|
|
|
|
|
|
77 |
|
78 |
| **Action** | **Recommendation** |
|
79 |
|:-----------------------|:-------------------------------------------------------------|
|
|
|
1 |
+
# AWS Accounts for LiveRAG
|
|
|
|
|
2 |
|
3 |
During the LiveRAG Challenge, participants may use two AWS accounts:
|
4 |
+
- **AWS Team Account** β This is your private AWS account for your team, where you can apply AWS credits provided for the competition.
|
5 |
+
- **AWS LiveRAG Account** β This account is managed by TII and grants access to the dense (Pinecone) and sparse (OpenSearch) pre-built indices.
|
6 |
|
7 |
Using these accounts is optional but highly recommended to optimize both cost and effort.
|
8 |
|
9 |
+
## Using Your AWS Team Account with AWS Credits
|
10 |
|
11 |
Each participating group receives AWS credits for the duration of the competition.
|
12 |
The credits are limited, and any usage beyond the allocated amount will be charged to your personal payment method.
|
13 |
To ensure your credits are properly applied, follow the official AWS instructions [here](https://docs.aws.amazon.com/awsaccountbilling/latest/aboutv2/useconsolidatedbilling-credits.html).
|
14 |
|
15 |
+
### AWS Team Account Setup and Credit Application Steps
|
16 |
|
17 |
1. **Create an AWS Account** β Sign up for an AWS account and add a payment method (typically a credit card). If you have an existing AWS account you may reuse it.
|
18 |
2. **Apply AWS Credits** β Follow the instructions in the provided AWS documentation to redeem and apply your credits.
|
|
|
20 |
- Use AWS Cost Management tools to monitor spending.
|
21 |
- Set up billing alarms using AWS CloudWatch to receive notifications when costs exceed predefined thresholds.
|
22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
### Access and Setup Instructions
|
25 |
|
26 |
+
To gain access and configure the AWS LiveRAG account, follow these steps:
|
27 |
|
28 |
+
1. **Receive Sign-In Details** β You should have received an email with login credentials from the organizers.
|
29 |
2. **Sign In & Change Password** β Log in to the AWS console and update your password.
|
30 |
3. **Create AWS Command Line Interface (CLI) Credentials** β Generate an access key and secret for CLI usage.
|
31 |
4. **Configure AWS CLI Profile** β Run the following command to set up the CLI for this account and follow the instructions:
|
|
|
57 |
|
58 |
For instructions pertaining to building your own Pinecone index see [here](Pinecone_for_LiveRAG.md).
|
59 |
|
60 |
+
### Cost Optimization Recommendations
|
61 |
+
|
62 |
+
We have estimated the cost of a typical teamβs infrastructure, including GPU usage, and AWS has provided credits accordingly.
|
63 |
+
However, individual teams may have varying requirements, so cost management is essential:
|
64 |
+
- **Shut down unused resources** β Always shut down GPUs and other compute instances when not in use.
|
65 |
+
- **Experiment on smaller datasets first** β This approach speeds up iteration cycles and reduces expenses before scaling up to larger datasets.
|
66 |
|
67 |
| **Action** | **Recommendation** |
|
68 |
|:-----------------------|:-------------------------------------------------------------|
|