fix sample app and add link (#1398)

colbert-long/README.md

@@ -15,14 +15,16 @@ with extended context windows for long-document retrieval.
 The app demonstrates the [colbert-embedder](https://docs.vespa.ai/en/embedding.html#colbert-embedder) and
 the tensor expressions for performing two types of extended ColBERT late-interaction for long-context retrieval. 
 
-<p data-test="run-macro init-deploy long-colbert">
+See [Announcing Vespa Long-Context ColBERT](https://blog.vespa.ai/announcing-long-context-colbert-in-vespa/) for details on this application.
+
+<p data-test="run-macro init-deploy colbert-long">
 Requires at least Vespa 8.311.28
 </p>
 
 ## To try this application
 
 Follow [Vespa getting started](https://cloud.vespa.ai/en/getting-started)
-through the <code>vespa deploy</code> step, cloning `long-colbert` instead of `album-recommendation`.
+through the <code>vespa deploy</code> step, cloning `colbert-long` instead of `album-recommendation`.
 
 Feed documents (this includes embed inference in Vespa):
 <pre data-test="exec">

colbert-long/services.xml

@@ -10,7 +10,6 @@
             <transformer-model url="https://huggingface.co/colbert-ir/colbertv2.0/resolve/main/model.onnx"/>
             <tokenizer-model url="https://huggingface.co/colbert-ir/colbertv2.0/raw/main/tokenizer.json"/>
         </component>
-
         <document-api/>
         <search/>
         <nodes count="1">
@@ -23,7 +22,7 @@
 
     <!-- See https://docs.vespa.ai/en/reference/services-content.html -->
     <content id="text" version="1.0">
-        <redundancy>2</redundancy>
+        <min-redundancy>2</min-redundancy>
         <documents>
             <document type="doc" mode="index" />
         </documents>
@@ -33,7 +32,7 @@
                 <tuning>
                     <searchnode>
                         <requestthreads>
-                            <persearch>16</persearch> <!-- Change the number of threads per search here -->
+                            <persearch>4</persearch> <!-- Change the number of threads per search here -->
                         </requestthreads>
                     </searchnode>
                 </tuning>

colbert/README.md

@@ -17,7 +17,7 @@ It also features reciprocal rank fusion to fuse different rankings.
 
 
 <p data-test="run-macro init-deploy colbert">
-Requires at least Vespa 8.283.46
+Requires at least Vespa 8.311.28
 </p>
 
 ## To try this application
@@ -36,21 +36,21 @@ Example queries:
 <pre data-test="exec" data-test-assert-contains="id:doc:doc::1">
 vespa query 'yql=select * from doc where userQuery() or ({targetHits: 100}nearestNeighbor(embedding, q))'\
  'input.query(q)=embed(e5, "query: space contains many suns")' \
- 'input.query(qt)=embed(colbert, "space contains many suns")' \
+ 'input.query(qt)=embed(colbert, @query)' \
  'query=space contains many suns'
 </pre>
 
 <pre data-test="exec" data-test-assert-contains="id:doc:doc::1">
 vespa query 'yql=select * from doc where userQuery() or ({targetHits: 100}nearestNeighbor(embedding, q))'\
  'input.query(q)=embed(e5, "query: shipping stuff over the sea")' \
- 'input.query(qt)=embed(colbert, "shipping stuff over the sea")' \
+ 'input.query(qt)=embed(colbert, @query)' \
  'query=shipping stuff over the sea'
  </pre>
 
  <pre data-test="exec" data-test-assert-contains="id:doc:doc::1">
 vespa query 'yql=select * from doc where userQuery() or ({targetHits: 100}nearestNeighbor(embedding, q))'\
  'input.query(q)=embed(e5, "query: exchanging information by sound")' \
- 'input.query(qt)=embed(colbert, "exchanging information by sound")' \
+ 'input.query(qt)=embed(colbert, @query)' \
  'query=exchanging information by sound'
  </pre>
 

colbert/services.xml

@@ -29,7 +29,7 @@
 
     <!-- See https://docs.vespa.ai/en/reference/services-content.html -->
     <content id="text" version="1.0">
-        <redundancy>2</redundancy>
+        <min-redundancy>2</min-redundancy>
         <documents>
             <document type="doc" mode="index" />
         </documents>