From cacd16b4a58b90729b090e1a70a9da5e3ae3b948 Mon Sep 17 00:00:00 2001
From: Ines Bouissou <106828511+lineUCB@users.noreply.github.com>
Date: Sun, 17 Nov 2024 22:46:09 -0800
Subject: [PATCH] Update README.md

---
 rag/README.md | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/rag/README.md b/rag/README.md
index 7c0811e..0482098 100644
--- a/rag/README.md
+++ b/rag/README.md
@@ -18,19 +18,19 @@ Run this to install the required packages
 
 ### Pipeline from website or local to knowledge base
 Run [pipline_kb.py](Scraper_master/pipeline_kb.py) as the pipeline to scrape, chunk and embed websites into a knowledge base. The pipeline takes a task, which is a collection of content that will be saved into a single knowledge base, and will save all information at the root_folder designated in the task.  The pipeline first scrapes, and then converts the content into markdown. Finally, it embeds and saves the everything as a knowledge base. This is all saved according to the path defined by root_folder. The knowledge base is automatically saved in the scraped data folder in a sub-folder labeled "pickle". 
-    A .yaml file is used to specify the tasks to be performed. It should be should be structured as follows:
-    ```
-    root_folder : "path/to/root/folder"
-    tasks :
-      - name : "Website Name"
-        local : False // True if is a Local file, False if it is a site that needs to be scraped
-        url : "https://website/site.url"
-        root : "https://website.url"
-      - name : "Folder Name"
-        local : True // Scraping Locally 
-        url : "path/to/folder"
-        root : "path/to/folder
-    ```
+A .yaml file is used to specify the tasks to be performed. It should be should be structured as follows:
+```
+root_folder : "path/to/root/folder"
+tasks :
+  - name : "Website Name"
+    local : False // True if is a Local file, False if it is a site that needs to be scraped
+    url : "https://website/site.url"
+    root : "https://website.url"
+  - name : "Folder Name"
+    local : True // Scraping Locally 
+    url : "path/to/folder"
+    root : "path/to/folder
+```
 
 
 ### Pre-requisites