Add size to inner_hits, required in 8.13 (#186)

Author: miguelgrinberg

.github/workflows/tests.yml

@@ -17,6 +17,7 @@ jobs:
         es_stack:
           - 8.11.4
           - 8.12.0
+          - 8.13.0-SNAPSHOT
     runs-on: ubuntu-latest
     services:
       elasticsearch:

notebooks/document-chunking/with-index-pipelines.ipynb

@@ -47,7 +47,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": null,
    "id": "ffc5fa6f",
    "metadata": {
     "id": "ffc5fa6f"
@@ -71,7 +71,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 30,
    "id": "f38e0397",
    "metadata": {
     "colab": {
@@ -80,7 +80,16 @@
     "id": "f38e0397",
     "outputId": "ad6df489-d242-4229-a42a-39c5ca19d124"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Elastic Cloud ID:  ········\n",
+      "Elastic Api Key:  ········\n"
+     ]
+    }
+   ],
    "source": [
     "from elasticsearch import Elasticsearch\n",
     "from getpass import getpass\n",
@@ -122,7 +131,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "id": "25c618eb",
    "metadata": {
     "colab": {
@@ -131,15 +140,7 @@
     "id": "25c618eb",
     "outputId": "30a6ba5b-5109-4457-ddfe-5633a077ca9b"
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'name': 'instance-0000000011', 'cluster_name': 'd1bd36862ce54c7b903e2aacd4cd7f0a', 'cluster_uuid': 'tIkh0X_UQKmMFQKSfUw-VQ', 'version': {'number': '8.11.1', 'build_flavor': 'default', 'build_type': 'docker', 'build_hash': '6f9ff581fbcde658e6f69d6ce03050f060d1fd0c', 'build_date': '2023-11-11T10:05:59.421038163Z', 'build_snapshot': False, 'lucene_version': '9.8.0', 'minimum_wire_compatibility_version': '7.17.0', 'minimum_index_compatibility_version': '7.0.0'}, 'tagline': 'You Know, for Search'}\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "print(client.info())"
    ]
@@ -155,7 +156,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": null,
    "id": "63560817",
    "metadata": {},
    "outputs": [],
@@ -185,7 +186,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 22,
    "id": "6bc95238",
    "metadata": {
     "id": "6bc95238"
@@ -197,7 +198,7 @@
        "ObjectApiResponse({'acknowledged': True})"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -279,7 +280,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 25,
    "id": "_OAahfg-tqrf",
    "metadata": {
     "colab": {
@@ -295,7 +296,7 @@
        "ObjectApiResponse({'acknowledged': True, 'shards_acknowledged': True, 'index': 'chunk_passages_example'})"
       ]
      },
-     "execution_count": 46,
+     "execution_count": 25,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -349,7 +350,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 26,
    "id": "008d723e",
    "metadata": {
     "id": "008d723e"
@@ -395,7 +396,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 27,
    "id": "f12ce2c9",
    "metadata": {
     "id": "f12ce2c9"
@@ -431,12 +432,12 @@
     "\n",
     "To search the data and return what chunk matched the query best you use inner_hits with the knn clause to return just that best matching chunk of the document in the hits output from the query.\n",
     "\n",
-    "Below you will see the response which returns the best document and the relevant portion of the larger document text.\n"
+    "Below you will see the response which returns the best document and the most relevant passage.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 29,
    "id": "Df7hwcIjYwMT",
    "metadata": {
     "colab": {
@@ -479,7 +480,7 @@
       "a.\n",
       "\n",
       "\n",
-      "Score: 0.76643425\n",
+      "Score: 0.7664343\n",
       "\n",
       "---\n",
       "\n",
@@ -502,6 +503,7 @@
     "  index=INDEX_NAME,\n",
     "  knn={\n",
     "    \"inner_hits\": {\n",
+    "      \"size\": 1,\n",
     "      \"_source\": False,\n",
     "      \"fields\": [\n",
     "        \"passages.text\"\n",
@@ -521,6 +523,14 @@
     "\n",
     "pretty_response(response)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c4bbcc4b-ea2d-47a3-b475-c2eb0eebb7e2",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -542,7 +552,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,

notebooks/document-chunking/with-langchain-splitters.ipynb

@@ -377,7 +377,7 @@
    "metadata": {},
    "source": [
     "### Perform a Nested Search\n",
-    "We can now perform a nested search, to find the passages that match our query, which will be returned in `inner_hits`."
+    "We can now perform a nested search, to find the passages that match our query, which will be returned in `inner_hits`. In the example that follows only one passage per parent document is requested."
    ]
   },
   {
@@ -478,6 +478,7 @@
     "  index=INDEX_NAME, \n",
     "  knn={\n",
     "    \"inner_hits\": {\n",
+    "      \"size\": 1,\n",
     "      \"_source\": False,\n",
     "      \"fields\": [\n",
     "        \"passages.text\"\n",
@@ -644,7 +645,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,