From cae644cfe79b237114c34a3e94b7d063e80c1e96 Mon Sep 17 00:00:00 2001
From: Mridula <mridula.s@elastic.co>
Date: Tue, 27 May 2025 14:46:56 +0100
Subject: [PATCH 1/3] Modified the code to include retrievers instead of rank

---
 notebooks/search/02-hybrid-search.ipynb | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/notebooks/search/02-hybrid-search.ipynb b/notebooks/search/02-hybrid-search.ipynb
index 4d7e7a87..6aa6163c 100644
--- a/notebooks/search/02-hybrid-search.ipynb
+++ b/notebooks/search/02-hybrid-search.ipynb
@@ -196,7 +196,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -204,13 +204,13 @@
     "    if len(response[\"hits\"][\"hits\"]) == 0:\n",
     "        print(\"Your search returned no results.\")\n",
     "    else:\n",
-    "        for hit in response[\"hits\"][\"hits\"]:\n",
+    "        for idx, hit in enumerate(response[\"hits\"][\"hits\"], start=1):\n",
     "            id = hit[\"_id\"]\n",
     "            publication_date = hit[\"_source\"][\"publish_date\"]\n",
-    "            rank = hit[\"_rank\"]\n",
+    "            score = hit[\"_score\"]\n",
     "            title = hit[\"_source\"][\"title\"]\n",
     "            summary = hit[\"_source\"][\"summary\"]\n",
-    "            pretty_output = f\"\\nID: {id}\\nPublication date: {publication_date}\\nTitle: {title}\\nSummary: {summary}\\nRank: {rank}\"\n",
+    "            pretty_output = f\"\\nID: {id}\\nPublication date: {publication_date}\\nTitle: {title}\\nSummary: {summary}\\nRank: {idx}\\nScore: {score}\"\n",
     "            print(pretty_output)"
    ]
   },
@@ -231,12 +231,12 @@
     "\n",
     "We then use [Reciprocal Rank Fusion (RRF)](https://www.elastic.co/guide/en/elasticsearch/reference/current/rrf.html) to balance the scores to provide a final list of documents, ranked in order of relevance. RRF is a ranking algorithm for combining results from different information retrieval strategies.\n",
     "\n",
-    "Note that _score is null, and we instead use _rank to show our top-ranked documents."
+    "Note: With the retriever API, _score contains the document’s relevance score, and the rank is simply the position in the results (first result is rank 1, etc.)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -289,7 +289,7 @@
     "        \"k\": 5,\n",
     "        \"num_candidates\": 10,\n",
     "    },\n",
-    "    rank={\"rrf\": {}},\n",
+    "    retriever={\"rrf\": {}},\n",
     ")\n",
     "\n",
     "pretty_response(response)"

From 06f84bb8317d80cab753ff1d36f9142b48f2ad04 Mon Sep 17 00:00:00 2001
From: Mridula <mridula.s@elastic.co>
Date: Tue, 27 May 2025 17:39:21 +0100
Subject: [PATCH 2/3] Corrected the json response

---
 notebooks/search/02-hybrid-search.ipynb | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/notebooks/search/02-hybrid-search.ipynb b/notebooks/search/02-hybrid-search.ipynb
index 6aa6163c..275fa739 100644
--- a/notebooks/search/02-hybrid-search.ipynb
+++ b/notebooks/search/02-hybrid-search.ipynb
@@ -280,18 +280,20 @@
     "response = client.search(\n",
     "    index=\"book_index\",\n",
     "    size=5,\n",
-    "    query={\"match\": {\"summary\": \"python programming\"}},\n",
-    "    knn={\n",
-    "        \"field\": \"title_vector\",\n",
-    "        \"query_vector\": model.encode(\n",
-    "            \"python programming\"\n",
-    "        ).tolist(),  # generate embedding for query so it can be compared to `title_vector`\n",
-    "        \"k\": 5,\n",
-    "        \"num_candidates\": 10,\n",
-    "    },\n",
-    "    retriever={\"rrf\": {}},\n",
+    "    retriever={\n",
+    "        \"rrf\": {\n",
+    "            \"retrievers\": [\n",
+    "                {\"standard\": {\"query\": {\"match\": {\"summary\": \"python programming\"}}}},\n",
+    "                {\"knn\": {\n",
+    "                    \"field\": \"title_vector\",\n",
+    "                    \"query_vector\": model.encode(\"python programming\").tolist(),\n",
+    "                    \"k\": 5,\n",
+    "                    \"num_candidates\": 10\n",
+    "                }}\n",
+    "            ]\n",
+    "        }\n",
+    "    }\n",
     ")\n",
-    "\n",
     "pretty_response(response)"
    ]
   }

From 2327dc710aedf5badfdc6d7ee62fc90817f85a05 Mon Sep 17 00:00:00 2001
From: Mridula <mridula.s@elastic.co>
Date: Tue, 27 May 2025 17:56:23 +0100
Subject: [PATCH 3/3] Format notebook with black-jupyter pre-commit hook

---
 notebooks/search/02-hybrid-search.ipynb | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/notebooks/search/02-hybrid-search.ipynb b/notebooks/search/02-hybrid-search.ipynb
index 275fa739..5516974d 100644
--- a/notebooks/search/02-hybrid-search.ipynb
+++ b/notebooks/search/02-hybrid-search.ipynb
@@ -284,15 +284,17 @@
     "        \"rrf\": {\n",
     "            \"retrievers\": [\n",
     "                {\"standard\": {\"query\": {\"match\": {\"summary\": \"python programming\"}}}},\n",
-    "                {\"knn\": {\n",
-    "                    \"field\": \"title_vector\",\n",
-    "                    \"query_vector\": model.encode(\"python programming\").tolist(),\n",
-    "                    \"k\": 5,\n",
-    "                    \"num_candidates\": 10\n",
-    "                }}\n",
+    "                {\n",
+    "                    \"knn\": {\n",
+    "                        \"field\": \"title_vector\",\n",
+    "                        \"query_vector\": model.encode(\"python programming\").tolist(),\n",
+    "                        \"k\": 5,\n",
+    "                        \"num_candidates\": 10,\n",
+    "                    }\n",
+    "                },\n",
     "            ]\n",
     "        }\n",
-    "    }\n",
+    "    },\n",
     ")\n",
     "pretty_response(response)"
    ]