From 5406312f2e04061d357fe0c2a4e35f558972a848 Mon Sep 17 00:00:00 2001 From: "abir.chebbi" <abir.chebbi@hes-so.ch> Date: Thu, 12 Sep 2024 14:46:09 +0200 Subject: [PATCH] readme --- README.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index b78fae0..ec86e12 100644 --- a/README.md +++ b/README.md @@ -13,7 +13,7 @@ ### Step 1: Object storage Creation Create an S3 bucket and upload a few PDF files by running: -`python create-S3-and-put-docs.py --bucket_name [YourBucketName] --local_path [PathToYourPDFFiles]` +`python3 create-S3-and-put-docs.py --bucket_name [YourBucketName] --local_path [PathToYourPDFFiles]` Where: - **--bucket_name**: The name for the new S3 bucket to be created. @@ -23,11 +23,11 @@ Where: ### Step 2: Vector Store Creation Create a vector database for storing embeddings by running: -`python create-vector-db.py --collection_name [Name_of_colletion] --IAM_user [YourIAM_User]` +`python3 create-vector-db.py --collection_name [Name_of_colletion] --iam_user [YourIAM_user]` Where: - **--collection_name**: Name of the collection that you want to create to store embeddings. -- **--IAM_USER** : For example for group 14 the IAM USER = master-group-14 +- **--iam_user** : For example for group 14 the iam_user is `master-group-14` This script performs the following actions: @@ -41,7 +41,7 @@ After setting up the S3 bucket and Vector Store, we could process PDF files to g Run: -`python main.py --bucket_name [YourBucketName] --endpoint [YourVectorDBEndpoint]` +`python3 main.py --bucket_name [YourBucketName] --endpoint [YourVectorDBEndpoint] --index_name [Index_name]` Where: -- GitLab