Skip to content

Commit 6852468

Browse files
author
Pablo Marin
committed
fixes and improvements
1 parent a604900 commit 6852468

17 files changed

+702
-669
lines changed

01-Load-Data-ACogSearch.ipynb

Lines changed: 15 additions & 38 deletions
Original file line numberDiff line numberDiff line change
@@ -237,23 +237,6 @@
237237
" ]\n",
238238
" },\n",
239239
" {\n",
240-
" \"@odata.type\": \"#Microsoft.Skills.Text.LanguageDetectionSkill\",\n",
241-
" \"context\": \"/document\",\n",
242-
" \"description\": \"If you have multilingual content, adding a language code is useful for filtering\",\n",
243-
" \"inputs\": [\n",
244-
" {\n",
245-
" \"name\": \"text\",\n",
246-
" \"source\": \"/document/content\"\n",
247-
" }\n",
248-
" ],\n",
249-
" \"outputs\": [\n",
250-
" {\n",
251-
" \"name\": \"languageCode\",\n",
252-
" \"targetName\": \"language\"\n",
253-
" }\n",
254-
" ]\n",
255-
" },\n",
256-
" {\n",
257240
" \"@odata.type\": \"#Microsoft.Skills.Text.SplitSkill\",\n",
258241
" \"context\": \"/document\",\n",
259242
" \"textSplitMode\": \"pages\",\n",
@@ -263,10 +246,6 @@
263246
" {\n",
264247
" \"name\": \"text\",\n",
265248
" \"source\": \"/document/merged_text\"\n",
266-
" },\n",
267-
" {\n",
268-
" \"name\": \"languageCode\",\n",
269-
" \"source\": \"/document/language\"\n",
270249
" }\n",
271250
" ],\n",
272251
" \"outputs\": [\n",
@@ -285,10 +264,6 @@
285264
" {\n",
286265
" \"name\": \"text\", \n",
287266
" \"source\": \"/document/pages/*\"\n",
288-
" },\n",
289-
" {\n",
290-
" \"name\": \"languageCode\",\n",
291-
" \"source\": \"/document/language\"\n",
292267
" }\n",
293268
" ],\n",
294269
" \"outputs\": [\n",
@@ -308,10 +283,6 @@
308283
" {\n",
309284
" \"name\": \"text\", \n",
310285
" \"source\":\"/document/pages/*\"\n",
311-
" },\n",
312-
" {\n",
313-
" \"name\": \"languageCode\",\n",
314-
" \"source\": \"/document/language\"\n",
315286
" }\n",
316287
" ],\n",
317288
" \"outputs\": [\n",
@@ -387,7 +358,6 @@
387358
" {\"name\": \"title\", \"type\": \"Edm.String\", \"searchable\": \"true\", \"retrievable\": \"true\", \"facetable\": \"false\", \"filterable\": \"true\", \"sortable\": \"false\"},\n",
388359
" {\"name\": \"content\", \"type\": \"Edm.String\", \"searchable\": \"true\", \"retrievable\": \"true\", \"sortable\": \"false\", \"filterable\": \"false\",\"facetable\": \"false\"},\n",
389360
" {\"name\": \"chunks\",\"type\": \"Collection(Edm.String)\", \"searchable\": \"false\", \"retrievable\": \"true\", \"sortable\": \"false\", \"filterable\": \"false\", \"facetable\": \"false\"},\n",
390-
" {\"name\": \"language\", \"type\": \"Edm.String\", \"searchable\": \"false\", \"retrievable\": \"true\", \"sortable\": \"true\", \"filterable\": \"true\", \"facetable\": \"true\"},\n",
391361
" {\"name\": \"name\", \"type\": \"Edm.String\", \"searchable\": \"true\", \"retrievable\": \"true\", \"sortable\": \"false\", \"filterable\": \"false\", \"facetable\": \"false\"},\n",
392362
" {\"name\": \"location\", \"type\": \"Edm.String\", \"searchable\": \"false\", \"retrievable\": \"true\", \"sortable\": \"false\", \"filterable\": \"false\", \"facetable\": \"false\"},\n",
393363
" {\"name\": \"vectorized\", \"type\": \"Edm.Boolean\", \"searchable\": \"false\", \"retrievable\": \"true\", \"sortable\": \"false\", \"filterable\": \"false\", \"facetable\": \"false\"},\n",
@@ -525,10 +495,6 @@
525495
" \"targetFieldName\" : \"images_text\"\n",
526496
" },\n",
527497
" {\n",
528-
" \"sourceFieldName\": \"/document/language\",\n",
529-
" \"targetFieldName\": \"language\"\n",
530-
" },\n",
531-
" {\n",
532498
" \"sourceFieldName\": \"/document/pages/*/keyPhrases/*\",\n",
533499
" \"targetFieldName\": \"keyPhrases\"\n",
534500
" },\n",
@@ -582,11 +548,22 @@
582548
},
583549
{
584550
"cell_type": "code",
585-
"execution_count": null,
551+
"execution_count": 20,
586552
"metadata": {
587553
"tags": []
588554
},
589-
"outputs": [],
555+
"outputs": [
556+
{
557+
"name": "stdout",
558+
"output_type": "stream",
559+
"text": [
560+
"200\n",
561+
"Status: inProgress\n",
562+
"Items Processed: 3250\n",
563+
"True\n"
564+
]
565+
}
566+
],
590567
"source": [
591568
"# Optionally, get indexer status to confirm that it's running\n",
592569
"r = requests.get(os.environ['AZURE_SEARCH_ENDPOINT'] + \"/indexers/\" + indexer_name +\n",
@@ -632,14 +609,14 @@
632609
},
633610
{
634611
"cell_type": "code",
635-
"execution_count": 28,
612+
"execution_count": 14,
636613
"metadata": {},
637614
"outputs": [
638615
{
639616
"name": "stdout",
640617
"output_type": "stream",
641618
"text": [
642-
"201\n",
619+
"204\n",
643620
"True\n"
644621
]
645622
}

0 commit comments

Comments
 (0)