Bug fixes for #11661 (#553)

* Submited : Create a Large Language Model (LLM) chatbot using Oracle Database 23ai and Generative AI Service.

* Name adjustements

* Folder rename

* Deleted old folder

* Fixed some bugs

Author: bogdanf

ai-chatbot-engine/search+llm/search+llm.md

@@ -88,6 +88,10 @@ with connection.cursor() as cursor:
 The SQL query is executed with the provided vector parameter, fetching relevant information from the database. For each result, the code retrieves the text content, stored in JSON format, and appends it to a list along with the calculated similarity score. This process iterates through all fetched results, accumulating them in the `results` list.
 
 If we print the results, we obtain something like the following. As requested, we have the "score" of each hit, which is essentially the distance in vector space between the question and the text chunk, as well as the metadata JSON embedded in each chunk.
+```python
+import pprint
+pprint.pp(results)
+```
 
 ```
 [(0.342059188035412,
@@ -206,17 +210,19 @@ In a Retrieval-Augmented Generation (RAG) application, the prompt given to a Lar
     </copy>
     ```
 
-    The user's OCID can be retrieved like this:
+    The **user's OCID** can be retrieved like this:
     -	Sign in to the Oracle Cloud Console.
     -	In the top-right corner, click on your user profile icon, then click on “User Settings”.
     -	In the User Settings page, you will find your User OCID.
 
-    The tenancy's OCID:
+    The **key file** is generated using the instructions [from this doc](https://docs.oracle.com/en-us/iaas/Content/API/Concepts/apisigningkey.htm#apisigningkey_topic_How_to_Generate_an_API_Signing_Key_Console).
+
+    The **tenancy's OCID**:
     -	Open the Navigation Menu (the hamburger menu icon).
     -	Under Identity, click on Tenancy.
     -	The Tenancy OCID will be displayed on the Tenancy details page.
 
-    While you have the Console open, fetch also the comaprtment OCID (you will need it in the next step):
+    While you have the Console open, fetch also the **compartment OCID** (you will need it in the next step):
     -	Navigate to Identity: Open the main menu and select Identity & Security -> Compartments.
     -	List of Compartments: You will see a list of compartments. Click on the compartment you need the OCID for.
     -	Compartment Details: The details page of the compartment will display its OCID.

ai-chatbot-engine/setup-23ai/setup-23ai.md

@@ -13,13 +13,15 @@ Estimated Time: 15 minutes
 
 ### Prerequisites
 
-* Basic knowledge of Oracle Cloud Infrastructure (OCI) concepts and consoles
+* Basic knowledge of Oracle Cloud Infrastructure (OCI) concepts and console
 * Basic Linux knowledge
 
 > Note: Any kind of Linux-based system is okay, but you will need to modify the following instructions to suit your specific setup.
 
 ## Task 1: Create a compute instance to run the lab
 
+> Note: If you don't know how to create a virtual machine and connect to it via SSH, please [see this lab first](https://livelabs.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=648&clear=RR,180&session=108750023091545). The following section will only give you a brief overview.
+
 Open your Oracle Cloud Infrastructure Cloud Console and make sure you are in the "US Midwest (Chicago)" region, which is necessary to access the OCI Generative AI services endpoint.
 
    ![console](images/image1.png)
@@ -32,19 +34,21 @@ Open your Oracle Cloud Infrastructure Cloud Console and make sure you are in the
 
 4. Choose the "Oracle Linux 8" image.
 
-5. Choose the instance shape based on your requirements.
+5. Choose a `VM.Standard.E4.Flex` shape.
+
+6. In the Networking section, most of the defaults are perfect for our purposes. However, you will need to scroll down and select the Assign a public IPv4 address option.
 
-6. Configure the networking options and ensure that you have proper security lists that allow SSH (port 22) and Jupyter Lab (port 8888).
+6. Configure the security list to allow SSH (port 22) and Jupyter Lab (port 8888). [See here](https://docs.oracle.com/en-us/iaas/Content/Network/Concepts/securitylists.htm) how to do it.
 
-7. Connect to your remote instance using SSH.
+7. Create your instance by clicking on the `Create` button.
+
+8. Connect to your remote instance using SSH.
    ```
    <copy>
-   ssh opc@[remote IP]
+   ssh -i <private_ssh_key> opc@<public_ip_address>
    </copy>
    ```
 
-   > Note: The exact connection details depend on how you configured remote access when creating the instance.
-
 ## Task 2: Install and configure the database (Oracle Database 23ai Free)
 For simplicity, we will install our database in a container using Podman, a popular container management tool similar to Docker.
 

ai-chatbot-engine/setup-python/setup-python.md

@@ -19,6 +19,8 @@ Estimated Time: 15 minutes
 
 ## Task 1: Install Python
 
+> Note: First, log in to your remote instance via SSH, as described in the previous lab.
+
 ### Step 1: Prerequisites.
 
    ```bash
@@ -54,6 +56,14 @@ Estimated Time: 15 minutes
 
    Close and save with `control-x`, `y`, and `Enter`
 
+   Make sure the new lines in our `bashrc` are run before going further: 
+
+   ```bash
+   <copy>
+   source ~/.bashrc
+   </copy>
+   ```
+
 ### Step 3: Once we have `pyenv` up and running, let's install Python 3.12.
 ```
 <copy>pyenv install 3.12</copy>
@@ -62,6 +72,9 @@ Creating the working folder:
 ```
 <copy>mkdir vectors</copy>
 ```
+```
+<copy>cd vectors</copy>
+```
 
 ### Step 4: Assign the Python version we just downloaded to our working directory:
 ```
@@ -72,8 +85,17 @@ Now check if it succeeded :
 ```
 <copy>python --version</copy>
 ```
+## Task 2: Install the required frameworks
+
+```bash
+<copy>
+pip install oracledb
+pip install sentence-transformers
+pip install oci
+</copy>
+```
 
-## Task 2: Install and configure Jupyter Lab
+## Task 3: Install and configure Jupyter Lab
 
 ### Step 1: Install the Jupyter server
 ```
@@ -87,7 +109,7 @@ If you see an output like this one, it worked.
 
 ![Jupyter ourput](images/image4.png)
 
-Leave it running.
+Leave it running, but write down the `token` listed in the command output.  
 
 ### Step 2: Open an SSH tunnel to allow access to the Jupyter Lab server.
 
@@ -98,24 +120,14 @@ Instead of exposing Jupyter Lab directly to the internet, you can use SSH tunnel
 In your local terminal, not within the SSH session with your remote instance, run this:
 
 ```bash
-<copy>ssh -L 8888:localhost:8888 opc@<remote IP></copy>
+<copy>ssh -L 8888:localhost:8888 -i <private_ssh_key> opc@<public_ip_address></copy>
 ```
 > Note: The exact connection details depend on how you configured remote access when creating the instance.
 
-Now, open the Jupyter URL (http://127.0.0.1:8888/lab) in a browser on your local machine.
+Now, open the Jupyter URL http://127.0.0.1:8888/lab?token=[`the token listed by your jupyter command output`] in a browser on your local machine.
 
 ![jupyter lab](images/image7.png)
 
-## Task 3: Install the required frameworks
-
-```bash
-<copy>
-pip install oracledb
-pip install sentence-transformers
-pip install oci
-</copy>
-```
-
 You may now **proceed to the next lab**
 
 ## Learn More

ai-chatbot-engine/vectorization/vectorization.md

@@ -40,7 +40,6 @@ Let's work with our source files, which contain the knowledge we want to use as
 ### Source files format
 FAQs are loaded from a file, encoded, and stored. For this example, we will use a properly formatted plain text FAQ, following the pattern:
 ```
-<copy>
 What is Oracle Cloud Free Tier?
 
 Oracle Cloud Free Tier allows you to sign up for an Oracle Cloud account which provides a number of Always Free services and a Free Trial with US$300 of free credit to use on all eligible Oracle Cloud Infrastructure services for up to 30 days. The Always Free services are available for an unlimited period of time. The Free Trial services may be used until your US$300 of free credits are consumed or the 30 days has expired, whichever comes first.
@@ -58,7 +57,6 @@ Why do I need to provide credit or debit card information when I sign up for Ora
 To provide free Oracle Cloud accounts to our valued customers, we need to ensure that you are who you say you are. We use your contact information and credit/debit card information for account setup and identity verification. Oracle may periodically check the validity of your card, resulting in a temporary “authorization” hold. These holds are removed by your bank, typically within three to five days, and do not result in actual charges to your account.
 
 =====
-</copy>
 ```
 
 So, we have the question, an empty line, the answer, and then a separator denoted by `=====`. For this simple example, we load the whole thing into memory. For a small FAQ file, there is no need for a proper vector database; however, if your knowledge base grows, you will want one.
@@ -71,7 +69,7 @@ Now, drag and drop the downloaded file into the Jupyter window to upload it to y
 ![Jupyter drag&drop](images/image8.png)
 
 ### Step 2: Create a new notebook to host our code.
-Right-click into the left navigation pane in the Jupyter window and select "New file".
+Right-click into the left navigation pane in the Jupyter window and select "New notebook".
 
 ![new file](images/image9.png)
 
@@ -99,7 +97,7 @@ Finally, let's start to code.
             file_path = os.path.join(directory_path, filename)
 
             with open(file_path) as f:
-            raw_faq = f.read()
+               raw_faq = f.read()
 
             filename_without_ext = os.path.splitext(filename)[0]  # remove .txt extension
             faqs[filename_without_ext] = [text.strip() for text in raw_faq.split('=====')]
@@ -130,7 +128,7 @@ Finally, let's start to code.
       ![load txt files](images/image12.png)
 
 
-3. The final step in preparing the source data is to arrange the above dictionary in a way that is easy to ingest in the vector database.
+3. The final step in preparing the source data is to arrange the above dictionary in a way that is easy to ingest in the vector database. Enter this code into a new cell.
 
    ```python
    <copy>

ai-chatbot-engine/workshops/freetier/manifest.json

@@ -1,6 +1,6 @@
 {
-    "workshoptitle": "AI Chatbot engine with Oracle Database 23c and OCI Generative AI Services",
-    "help": "bogdan.farca@oracle.com",
+    "workshoptitle": "AI Chatbot engine with Oracle Database 23ai and OCI Generative AI Services",
+    "help": "livelabs-help-db_us@oracle.com",
     "tutorials": [
         {
             "title": "Introduction",