update README

README.md

@@ -8,52 +8,13 @@ More Details can be found in [Builder Space](https://builderspace.proto.sa.aws.d
 
 ## Deployment Guide
 
-**AWS Service Deployment :** 
+**AWS Service and Guidance Deployment :** 
 
-* Change directory to ./deployment folder
-```
-cd ./deployment
-```
 
-* Follow the instruction of README.md in the deployment folder
 
+* Follow below workshop instruction , the workshop will guide you to deploy the solution guidance step by step with detail information
 
-**Model Deployment :** 
-
-* Open Amazon Sagemaker Notebook，find the notebook with the name of SmartSearchNotebook.
-
-* Embedding Model Deployment
-1. shibing624_text2vec-base-chinese: Open Embedding Model/ EmbbedingModel_shibing624_text2vec-base-chinese.ipynb
-2. Run the first two cell to deploy
-3. Run the third cell to validate
-
-* LLM Model Deployment
-1. Chatglm: Open LLM_Model/chatglm/chatglm_sagemaker_byos.ipynb
-2. Run the first two cell to deploy
-3. Run the following cell to validate
-
-Tips 1: The LLM model endpoint still needs some time to download the model artifacts after the endpoint is in service status. You could check the downloading status in CloudWatch logs of the endpoint.  
-Tips 2: The Embedding and LLM models's deployment could be doing, simultaneously.
-
-**Data Preprocessing and Data ingestion :** 
-
-1.	You must make sure the embedding model was deployed successfully.
-2.	Upload your testing data files (docx formation) to Sagemaker Notebook
-3.	Open Script-Doc.ipynb, and run the first two cell
-4.	In hyperparameter part, input the following parameter and run the cell:  
-    a.	index_name: The name of your index (database) in OpenSearch  
-    b.	folder_path: The original data file folder path  
-        folder_path  
-            ---file1.docx  
-            ---file2.docx  
-5.	Run the following cell
-
-**Validation :** 
-1.	Go to Amazon ApiGateway, find the api with the name of opensearch-api
-2.	Chose the /search_knn_doc/GET
-3.	Click TEST
-4.	Input: q="123"&ind="docs"&knn="1", where q is the input question, ind is the index_name which you set in "Data Preprocessing and Data ingestion", knn="1" means using embbeding model while knn="0" means not.
-5.	Status 200 means you deploy successfully.
+[**Guidance's Workshop Link**](https://catalog.us-east-1.prod.workshops.aws/workshops/486e5ddd-b414-4e7f-9bfd-3884a89353e3/en-US)
 
 ## Security