fixing notes

docs/changelog/118804.yaml

@@ -7,22 +7,9 @@ issues: []
 highlight:
   title: Add new experimental `rank_vectors` mapping for late-interaction second order
     ranking
-  body: "Late-interaction models are powerful rerankers. While their size and\noverall\
-    \ cost doesn't lend itself for HNSW indexing, utilizing them as\nsecond order\
-    \ \"brute-force\" reranking can provide excellent boosts in\nrelevance. At generally\
-    \ lower inference times than large cross-encoders.\n\n\nThis commit exposes a\
-    \ new experimental `rank_vectors` field that allows\nfor maxSim operations. This\
-    \ unlocks the initial, and most common use of\nlate-interaction dense-models.\
-    \ \n\nFor example, this is how you would use it via the API:\n\n```\nPUT index\n\
-    {\n  \"mappings\": {\n    \"properties\": {\n      \"late_interaction_vectors\"\
-    : {\n        \"type\": \"rank_vectors\"\n      }\n    }\n  }\n}\n```\n\nThen to\
-    \ index:\n\n```\nPOST index/_doc\n{\n  \"late_interaction_vectors\": [[0.1, ...],...]\n\
-    }\n```\n\nFor querying, scoring can be exposed with scripting:\n\n```\nPOST index/_search\n\
-    {\n  \"query\": {\n    \"script_score\": {\n      \"query\": {\n        \"match_all\"\
-    : {}\n      },\n      \"script\": {\n        \"source\": \"maxSimDotProduct(params.query_vector,\
-    \ 'my_vector')\",\n        \"params\": {\n          \"query_vector\": [[0.42,\
-    \ ...], ...]\n        }\n      }\n    }\n  }\n}\n```\n\nOf course, the initial\
-    \ ranking should be done before re-scoring or\ncombining via the `rescore` parameter,\
-    \ or simply passing whatever first\nphase retrieval you want as the inner query\
-    \ in `script_score`."
+  body:
+      Late-interaction models are powerful rerankers. While their size and overall
+      cost doesn't lend itself for HNSW indexing, utilizing them as second order reranking
+      can provide excellent boosts in relevance. The new `rank_vectors` mapping allows for rescoring
+      over new and novel multi-vector late-interaction models like ColBERT or ColPali.
   notable: true