Merge pull request #70 from Sanketika-Obsrv/label_help_fixes

#OBS-I331 - Fix the storage page help text and functionality

web-console-v2/src/assets/help/processing.tsx

@@ -7,24 +7,21 @@ const ProcessingHelpText = () =>{
             <section className="section" id="section1">
                 <h1 className="contentsHeader">Data Validation</h1>
                 <p className="contentBody">
-                    <ul className="customList">
                     <p><strong>Data Validation:</strong> All data is automatically validated to ensure accuracy and compliance with the schema. This includes:</p>
-                        <ul>
+                    <ul>
                         <li>Data type checks</li>
                         <li>Enum validations</li>
                         <li>Range validations</li>
                         <li>Minimum and maximum value checks</li>
                         <li>Required field enforcement</li>
-                        </ul>
-                        <p>Any mismatches or missing required fields will cause the data to fail validation.</p>
-                        <p><strong>Additional Fields:</strong> Select how to handle fields not defined in the schema:</p>
-                        <ul>
+                    </ul>
+                    <p>Any mismatches or missing required fields will cause the data to fail validation.</p>
+                    <p><strong>Additional Fields:</strong> Select how to handle fields not defined in the schema:</p>
+                    <ul>
                         <li><strong>Fail for New Fields (No):</strong> Processing will fail if any fields outside the schema are detected.</li>
                         <li><strong>Ignore New Fields (Yes):</strong> Additional fields will be ignored, and processing will continue.</li>
-                        </ul>
-                        <p>Choose the option that best fits your data requirements.</p>
-
                     </ul>
+                    <p>Choose the option that best fits your data requirements.</p>
                 </p>
             </section>
 

web-console-v2/src/assets/help/storage.tsx

@@ -4,41 +4,28 @@ const StorageHelpText = () =>{
     return (
         <div className="displayContent">
             <h1 className="contentsHeader">Setup Guide for Dataset Storage</h1>
-            <section className="section" id="section1">
-                <div className="displayContent">
-                    <h1 className="contentsHeader">Dataset Storage</h1>
-                    <h3 className="contentsHeader">Dataset Type</h3>
-                    <p className="contentBody">
-                        At present, there are three types of datasets that can be created: a regular dataset and a master dataset. While there is no significant difference in the majority of workflows, there are some key differences as outlined below which would impact the UI flows:
-                    </p>
-                    <ul className="customList">
-                        <li className="contentBody"><strong>Master Dataset:</strong> Used for capturing master data (e.g., user, location, catalog)</li>
-                        <li className="contentBody"><strong>Events</strong></li>
-                        <li className="contentBody"><strong>Transactional</strong></li>
+            <section className="section highlighted" id="section1">
+                <h1 className="contentsHeader">Select Storage Type</h1>
+                <div className="contentBody">
+                    <p>Choose from multiple storage options that best meet your dataset needs:</p>
+                    <ul>
+                        <li><strong>Data Lakehouse (Hudi):</strong> Stores datasets cost-effectively, ideal for data science and analytical workloads, especially for transactional data. Offers scalable storage but may have slower query responses (not ideal for real-time APIs).</li>
+                        <li><strong>Real-time Store (Druid):</strong> Designed for telemetry or append-only data, this real-time OLAP store supports sub-second response times for real-time queries and aggregate analysis.</li>
+                        <li><strong>Cache Store (Redis):</strong> Enabled only for &quot;Master&quot; datasets, this option is optimal for data denormalization in real-time due to its speed.</li>
                     </ul>
                 </div>
-            </section>
-
-            <section className="section" id="section2">
-                <div className="displayContent">
-                    <h3 className="contentsHeader">Dataset Store</h3>
-                    <ul className="customList">
-                        <li className="contentBody"><strong>Lakehouse</strong></li>
-                        <li className="contentBody"><strong>Real-time Store</strong></li>
+                <h1 className="contentsHeader">Configure Storage Keys:</h1>
+                <div className="contentBody">
+                    <p>Choose appropriate keys to enable indexing, data storage, and updates.</p>
+                    <ul>
+                        <li><strong>Primary Key:</strong> Required for Lakehouse and Cache Store. Select a unique identifier field to support record updates. Ensure this key uniquely identifies each record in the dataset.</li>
+                        <li><strong>Timestamp Key:</strong> Required for OLAP Store (Druid). Select a timestamp for time-based indexing, either by choosing &quot;Event Arrival Time&quot; for the event&apos;s arrival time into the system, or any valid date-time field from the dataset.</li>
+                        <li><strong>Partition Key:</strong> Required for Lakehouse, optional for OLAP Store, and not necessary for Cache Store. Use a field that logically segments data for efficient storage and query performance.</li>
                     </ul>
                 </div>
+
             </section>
 
-            <section className="section" id="section3">
-                <div className="displayContent">
-                    <h3 className="contentsHeader">Indexing Config</h3>
-                    <ul className="customList">
-                        <li className="contentBody"><strong>A timestamp key for time-series analysis:</strong> The storage data type of this field should be date, date-time, epoch, or any other date/time type; and this field must be marked as required. User options would be to consider data arrival time as a timestamp key or select a date from one of the date fields. This is not applicable for a master dataset.</li>
-                        <li className="contentBody"><strong>A primary key for dedup/updates to the data:</strong> Can be any text/number field. Required only for File/Application/Stream connector types. A primary key can be a combination of more than one field.</li>
-                        <li className="contentBody"><strong>A partition key for tenanting, efficient querying of data:</strong> Can be any text/number field. Partition key can be a combination of more than one field.</li>
-                    </ul>
-                </div>
-            </section>
         </div>
     );
 }