Merge pull request #35 from DS4SD/dkl/qa-rag

Add QA feature and collection level RAG support

src/index.njk

@@ -67,6 +67,11 @@ title: IBM Deep Search
                     <td></td>
                     <td><img src="/icons/checkmark.svg"/></td>
                 </tr>
+                <tr>
+                    <td>Configure the document conversion process</td>
+                    <td></td>
+                    <td><img src="/icons/checkmark.svg"/></td>
+                </tr>
                 <tr>
                     <td>Search millions of
                         <a href="#collect">pre-loaded documents</a>
@@ -75,7 +80,11 @@ title: IBM Deep Search
                     <td><img src="/icons/checkmark.svg"/></td>
                 </tr>
                 <tr>
-                    <td>Configure the document conversion process</td>
+                    <td>Use <a href="#doc-qa">question-answering</a> on your own documents</td>
+                    <td></td>
+                    <td><img src="/icons/checkmark.svg"/></td>
+                </tr>
+                    <td>Integrate with gen AI systems like <a href="https://www.ibm.com/products/watsonx-ai" target="_blank">IBM watsonx.ai</a></td>
                     <td></td>
                     <td><img src="/icons/checkmark.svg"/></td>
                 </tr>
@@ -229,15 +238,17 @@ title: IBM Deep Search
         <video src="/movies/pat-cid.mp4" controls loop autoplay muted></video>
     </div>
 
-    <h3 id="doc-qa">DocQA: A question-answering conversational assistant on your documents</h3>
+    <h3 id="doc-qa">DocQA: Conversational question-answering on your documents</h3>
     <p>
         DocQA enables information extraction from documents via a question-answering conversational assistant. The system integrates
         several technologies from different AI disciplines consisting of document
         conversion to machine-readable format (via computer vision), finding relevant data (via natural language processing),
         and formulating an eloquent response (via large language models). A research paper describing this application is published
-        at the AAAI 2024 conference. Read more about it <a href="https://research.ibm.com/blog/ai-deep-search-docqa">here</a> and
-        <a href="mailto:deepsearch-core@zurich.ibm.com">contact us</a>
-        for early access.
+        at the AAAI 2024 conference. Read more about it <a href="https://research.ibm.com/blog/ai-deep-search-docqa">here</a>.
+    </p>
+    <p>
+        Question-answering across entire document collections is supported as well by means of Retrieval-Augmented Generation.
+        <a href="mailto:deepsearch-core@zurich.ibm.com">Contact us</a> for early access.
     </p>
     <div>
         <video src="/movies/doc-qa.mp4" controls loop autoplay muted></video>