diff --git a/README.md b/README.md index adc7a00107399068b33c5039d6c1d79ec975bae3..cf770bc55aaec79ca631043bc4f04ac68ce3584a 100644 --- a/README.md +++ b/README.md @@ -4,12 +4,10 @@ 1. AWS CLI: Ensure AWS CLI is installed and configured on your laptop(refer to the setup guide provided in Session 1). 2. Ensure python is installed: python 3.8 or higher. - - - ## Part 1: ### Step 1: Object storage Creation + Go to the Part1 folder: `cd Part1` Install required python libraries listed in the 'requirements.txt': `pip3 install -r requirements.txt` @@ -31,11 +29,12 @@ Create a vector database for storing embeddings by running: Where: - **[Name_of_colletion]**: Name of the collection that you want to create. -- **[YourIAM_user]** : the IAM user is `CloudSys-group-XX`, with "XX" representing your group number. +- **[YourIAM_user]** : the IAM user of your account. - **[YourAccount_ID]** : the ACCOUNT ID of your account. +You will find YourIAM_iser and YourAccount_ID when you click on your account ID in the top right-hand corner of the AWS Amazon portal. -This script performs the following actions: +The script performs the following actions: * Sets up encryption, network, and data access policies for the collection. * Creates a vector store with the name collection entered as argument. @@ -50,6 +49,11 @@ Start by requesting access to the following models on the AWS Bedrock service: - Titan Embedding v1 - Claude v2 +To do so: +- Go to the bedrock AWS Amazon service in your AWS portal +- Go to the BedRock configurations option in the left menu at the bottom of the page +- Check that the access is granted for itan Embedding v1 and Claude v2 + Then, run: `python3 vectorise-store.py --bucket_name [YourBucketName] --endpoint [YourVectorDBEndpoint] --index_name [Index_name] --local_path [local_path]`