AI Vector Search - Using Vector Embedding Models with Nodejs (#131)

* created lab

* Updates

* Updated Spelling

* Deleted bad folder speling

* Moved to workshops

* added livelabs folder

* Fixed formatting

* Fixed Indentations

* Spelling Changes

* Fixed Image format problem

* Fixed Broken Images

* Spelling

* changes to lab

* Fixed Image scaling

* Deleted Spelling issue folder

* Minor Fixes

ai-vector-embedding-nodejs/introduction/introduction.md

@@ -131,8 +131,6 @@ One way to compare embedding models is quality vs performance vs popularity
 Figure 9. Comparison of Quality vs Performance vs Polularity of Embedding Models
 
 
-**Need an updated version of this picture with the relevant embedding models !!!** 
-
 ## Getting Started with this Workshop 
 
 **Create vector table and load sample data**
@@ -162,15 +160,21 @@ There are many different embedding models. At the time of this lab creation:
 * The *data* and *query vectors* should use the same embedding model (otherwise you will get garbage results)
 
 In this workshop you will have an opportunity to use the following vector embedding models from:
+* Cohere
+* Sentence Transformers from Hugging Face
+
+This Lab utilizes tabs to switch between learning about the embedding models:
+
+![Introduction Part 4  Image 3](images/tabs.png =60%x*)
+
+To switch between learning about Cohere and Hugging Face embedding models click on the appropiate tab. 
 
-* Lab 1. Cohere
-* Lab 2. Sentence Transformers from Hugging Face
 
 
 
 ## Learn More
 
-* [Oracle Database 23c Release Notes](../docs/release_notes.pdf)
+* [Oracle Database 23ai Release Notes](../docs/release_notes.pdf)
 * [Oracle AI Vector Search Users Guide](../docs/oracle-ai-vector-search-users-guide_latest.pdf)
 * [Oracle Documentation](http://docs.oracle.com)
 * [Google Transformers Whitepaper - Attention Is All You Need](https://arxiv.org/pdf/1706.03762.pdf)
@@ -182,4 +186,4 @@ In this workshop you will have an opportunity to use the following vector embedd
 ## Acknowledgements
 * **Author** - Doug Hood, Product Manager
 * **Contributors** -  Sean Stacey, Outbound Product Manager, Zackary Rice, Software Developer
-* **Last Updated By/Date** - Sean Stacey, April 2024
+* **Last Updated By/Date** - Zackary Rice, May 2024

ai-vector-embedding-nodejs/labs/labs.md

@@ -208,7 +208,7 @@ In this lab, you will see the following Vector operations using nodejs:
 
     You should see:
 
-    ![Lab 1 Task 2 Step 4](images/nodejscohere04.png =60%x*)
+    ![Lab 1 Task 2 Step 4](images/nodejstfr03.png =60%x*)
 
 
     3.c. We can also query the vector column: V in the MY\_DATA table to see what the vectors and dimensions look like.
@@ -1310,6 +1310,13 @@ In this lab, you will perform the following tasks:
 
 3. We're now ready to try out our new model. As a baseline let's start with the term "cars".  But this time, we'll also perform the similarity search in Spanish "coche", French "voiture" and even a Spanish dialect "carros". What is interesting, is that while the phrases returned are all accurately related to the search phrase "cars", they are not identical phrases returned per language, nor are they in the same sequence.
 
+    ```
+      <copy>
+      node similaritySearchHFTransformers.js
+      </copy>
+    ```
+
+
     Enter Phrase: **cars**
 
     Enter Phrase: **coche**
@@ -1363,4 +1370,4 @@ In these labs you have seen how easy it is to use Oracle Vectors and Similarity
 ## Acknowledgements
 * **Author** - Doug Hood, Product Manager, Zackary Rice, Software Developer
 * **Contributors** - Sean Stacey, Outbound Product Manager
-* **Last Updated By/Date** - Zackary Rice, April 2024
+* **Last Updated By/Date** - Zackary Rice, May 2024