From 7e86c04d01c585326ab6e443941ed15cf9ffca8f Mon Sep 17 00:00:00 2001
From: Miguel Grinberg <miguel.grinberg@gmail.com>
Date: Thu, 7 Dec 2023 17:34:59 +0000
Subject: [PATCH] hybrid bm25/ELSER search

---
 .../search-tutorial/v3/search-tutorial/app.py | 64 +++++++++++++++----
 .../v3/search-tutorial/search.py              | 15 ++++-
 2 files changed, 63 insertions(+), 16 deletions(-)

diff --git a/example-apps/search-tutorial/v3/search-tutorial/app.py b/example-apps/search-tutorial/v3/search-tutorial/app.py
index 2d9737e6..f70d0194 100644
--- a/example-apps/search-tutorial/v3/search-tutorial/app.py
+++ b/example-apps/search-tutorial/v3/search-tutorial/app.py
@@ -17,22 +17,58 @@ def handle_search():
     filters, parsed_query = extract_filters(query)
     from_ = request.form.get('from_', type=int, default=0)
 
-    results = es.search(
-        query={
-            'bool': {
-                'must': [
-                    {
-                        'text_expansion': {
-                            'elser_embedding': {
-                                'model_id': '.elser_model_2',
-                                'model_text': parsed_query,
-                            }
-                        },
+    if parsed_query:
+        search_query = {
+            'sub_searches': [
+                {
+                    'query': {
+                        'bool': {
+                            'must': {
+                                'multi_match': {
+                                    'query': parsed_query,
+                                    'fields': ['name', 'summary', 'content'],
+                                }
+                            },
+                            **filters
+                        }
                     }
-                ],
-                **filters,
+                },
+                {
+                    'query': {
+                        'bool': {
+                            'must': [
+                                {
+                                    'text_expansion': {
+                                        'elser_embedding': {
+                                            'model_id': '.elser_model_2',
+                                            'model_text': parsed_query,
+                                        }
+                                    },
+                                }
+                            ],
+                            **filters,
+                        }
+                    },
+                },
+            ],
+            'rank': {
+                'rrf': {}
+            },
+        }
+    else:
+        search_query = {
+            'query': {
+                'bool': {
+                    'must': {
+                        'match_all': {}
+                    },
+                    **filters
+                }
             }
-        },
+        }
+
+    results = es.search(
+        **search_query,
         size=5,
         from_=from_,
     )
diff --git a/example-apps/search-tutorial/v3/search-tutorial/search.py b/example-apps/search-tutorial/v3/search-tutorial/search.py
index 072ce50b..ac883580 100644
--- a/example-apps/search-tutorial/v3/search-tutorial/search.py
+++ b/example-apps/search-tutorial/v3/search-tutorial/search.py
@@ -66,7 +66,18 @@ def reindex(self):
         return self.insert_documents(documents)
 
     def search(self, **query_args):
-        return self.es.search(index='my_documents', **query_args)
+        # sub_searches is not currently supported in the client, so we send
+        # search requests as raw requests
+        if 'from_' in query_args:
+            query_args['from'] = query_args['from_']
+            del query_args['from_']
+        return self.es.perform_request(
+            'GET',
+            f'/my_documents/_search',
+            body=json.dumps(query_args),
+            headers={'Content-Type': 'application/json',
+                     'Accept': 'application/json'},
+        )
 
     def retrieve_document(self, id):
         return self.es.get(index='my_documents', id=id)
@@ -75,7 +86,7 @@ def deploy_elser(self):
         # download ELSER v2
         self.es.ml.put_trained_model(model_id='.elser_model_2',
                                      input={'field_names': ['text_field']})
-        
+
         # wait until ready
         while True:
             status = self.es.ml.get_trained_models(model_id='.elser_model_2',