diff --git a/01-Load-Data-ACogSearch.ipynb b/01-Load-Data-ACogSearch.ipynb index 9c15c0b4..bbe3a12a 100644 --- a/01-Load-Data-ACogSearch.ipynb +++ b/01-Load-Data-ACogSearch.ipynb @@ -77,10 +77,10 @@ "outputs": [], "source": [ "# Define the names for the data source, skillset, index and indexer\n", - "datasource_name = \"cogsrch-datasource-files\"\n", - "index_name = \"cogsrch-index-files\"\n", - "skillset_name = \"cogsrch-skillset-files\"\n", - "indexer_name = \"cogsrch-indexer-files\"" + "datasource_name = \"cogsrch-datasource-files-2\"\n", + "index_name = \"cogsrch-index-files-2\"\n", + "skillset_name = \"cogsrch-skillset-files-2\"\n", + "indexer_name = \"cogsrch-indexer-files-2\"" ] }, { @@ -110,7 +110,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "204\n", + "201\n", "True\n" ] } @@ -195,7 +195,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "204\n", + "201\n", "True\n" ] } @@ -339,7 +339,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "204\n", + "201\n", "True\n" ] } @@ -514,7 +514,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "204\n", + "201\n", "True\n" ] } @@ -564,7 +564,18 @@ "cell_type": "code", "execution_count": 11, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "'{\"@odata.context\":\"https://cog-search-zf4fwhz3gdn64.search.windows.net/$metadata#indexers/$entity\",\"@odata.etag\":\"\\\\\"0x8DC7052637CA2AC\\\\\"\",\"name\":\"cogsrch-indexer-files-2\",\"description\":null,\"dataSourceName\":\"cogsrch-datasource-files-2\",\"skillsetName\":\"cogsrch-skillset-files-2\",\"targetIndexName\":\"cogsrch-index-files-2\",\"disabled\":null,\"schedule\":{\"interval\":\"PT30M\",\"startTime\":\"2024-05-09T18:03:38.4035486Z\"},\"parameters\":{\"batchSize\":null,\"maxFailedItems\":-1,\"maxFailedItemsPerBatch\":-1,\"base64EncodeKeys\":null,\"configuration\":{\"dataToExtract\":\"contentAndMetadata\",\"imageAction\":\"generateNormalizedImages\"}},\"fieldMappings\":[{\"sourceFieldName\":\"metadata_title\",\"targetFieldName\":\"title\",\"mappingFunction\":null},{\"sourceFieldName\":\"metadata_storage_name\",\"targetFieldName\":\"name\",\"mappingFunction\":null},{\"sourceFieldName\":\"metadata_storage_path\",\"targetFieldName\":\"location\",\"mappingFunction\":null}],\"outputFieldMappings\":[],\"cache\":null,\"encryptionKey\":null}'" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# Uncomment if you find an error\n", "# r.text" @@ -579,7 +590,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 14, "metadata": { "tags": [] }, @@ -589,8 +600,8 @@ "output_type": "stream", "text": [ "200\n", - "Status: success\n", - "Items Processed: 0\n", + "Status: inProgress\n", + "Items Processed: 40\n", "True\n" ] } diff --git a/02-LoadCSVOneToMany-ACogSearch.ipynb b/02-LoadCSVOneToMany-ACogSearch.ipynb index 2b9088dc..050df55b 100644 --- a/02-LoadCSVOneToMany-ACogSearch.ipynb +++ b/02-LoadCSVOneToMany-ACogSearch.ipynb @@ -17,7 +17,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "c088c844-1e71-4279-a8fe-a77a007c15c4", "metadata": {}, "outputs": [], @@ -34,21 +34,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "id": "c4908539-1d17-46a3-b9e0-dcc46a210c4f", "metadata": {}, "outputs": [], "source": [ "# Define the names for the data source, index and indexer\n", - "datasource_name = \"cogsrch-datasource-csv\"\n", - "skillset_name = \"cogsrch-skillset-csv\"\n", - "index_name = \"cogsrch-index-csv\"\n", - "indexer_name = \"cogsrch-indexer-csv\"" + "datasource_name = \"cogsrch-datasource-csv-2\"\n", + "skillset_name = \"cogsrch-skillset-csv-2\"\n", + "index_name = \"cogsrch-index-csv-2\"\n", + "indexer_name = \"cogsrch-indexer-csv-2\"" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "id": "f2434379-070e-4110-8f5a-7d5bda9a0b7c", "metadata": {}, "outputs": [], @@ -68,7 +68,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "id": "a9fa6c09-a489-4b6d-8c93-5fc26bae63a0", "metadata": {}, "outputs": [ @@ -76,7 +76,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "204\n", + "201\n", "True\n" ] } @@ -120,7 +120,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "id": "2fbbbd0d-3015-4601-9ef1-7008ad168167", "metadata": {}, "outputs": [], @@ -132,7 +132,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "id": "aaac918a-8859-45f5-9519-2cf56bfded88", "metadata": {}, "outputs": [ @@ -148,72 +148,72 @@ "text/html": [ "\n", - "\n", + "
\n", " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", "
 cord_uidsource_xtitleabstractauthorsurlcord_uidsource_xtitleabstractauthorsurl
0ug7v899jPMCClinical features of culture-p...OBJECTIVE: This retrospective ...Madani, Tariq A; Al-Ghamdi, Ai...https://www.ncbi.nlm.nih.gov/pmc/articles/PMC35282/0ug7v899jPMCClinical features of culture-p...OBJECTIVE: This retrospective ...Madani, Tariq A; Al-Ghamdi, Ai...https://www.ncbi.nlm.nih.gov/pmc/articles/PMC35282/
102tnwd4mPMCNitric oxide: a pro-inflammato...Inflammatory diseases of the r...Vliet, Albert van der; Eiseric...https://www.ncbi.nlm.nih.gov/pmc/articles/PMC59543/102tnwd4mPMCNitric oxide: a pro-inflammato...Inflammatory diseases of the r...Vliet, Albert van der; Eiseric...https://www.ncbi.nlm.nih.gov/pmc/articles/PMC59543/
2ejv2xln0PMCSurfactant protein-D and pulmo...Surfactant protein-D (SP-D) pa...Crouch, Erika C...https://www.ncbi.nlm.nih.gov/pmc/articles/PMC59549/2ejv2xln0PMCSurfactant protein-D and pulmo...Surfactant protein-D (SP-D) pa...Crouch, Erika C...https://www.ncbi.nlm.nih.gov/pmc/articles/PMC59549/
32b73a28nPMCRole of endothelin-1 in lung d...Endothelin-1 (ET-1) is a 21 am...Fagan, Karen A; McMurtry, Ivan...https://www.ncbi.nlm.nih.gov/pmc/articles/PMC59574/32b73a28nPMCRole of endothelin-1 in lung d...Endothelin-1 (ET-1) is a 21 am...Fagan, Karen A; McMurtry, Ivan...https://www.ncbi.nlm.nih.gov/pmc/articles/PMC59574/
49785vg6dPMCGene expression in epithelial ...Respiratory syncytial virus (R...Domachowske, Joseph B; Bonvill...https://www.ncbi.nlm.nih.gov/pmc/articles/PMC59580/49785vg6dPMCGene expression in epithelial ...Respiratory syncytial virus (R...Domachowske, Joseph B; Bonvill...https://www.ncbi.nlm.nih.gov/pmc/articles/PMC59580/
\n" ], "text/plain": [ - "" + "" ] }, - "execution_count": 11, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -472,7 +472,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 10, "id": "b87b8ebd-8091-43b6-9124-cc17021cfb78", "metadata": {}, "outputs": [ diff --git a/04-Complex-Docs.ipynb b/04-Complex-Docs.ipynb index 55511b73..fcec12ba 100644 --- a/04-Complex-Docs.ipynb +++ b/04-Complex-Docs.ipynb @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "id": "15f6044e-463f-4988-bc46-a3c3d641c15c", "metadata": {}, "outputs": [], @@ -75,7 +75,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "id": "331692ba-b68e-4b99-9bae-5057da9a389d", "metadata": {}, "outputs": [], @@ -86,7 +86,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "id": "594ff0d4-56e3-4bed-843d-28c7a092069b", "metadata": {}, "outputs": [], @@ -114,7 +114,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "id": "0999e24b-6a75-4fa1-9a5f-426cf0f0bdba", "metadata": {}, "outputs": [], @@ -136,7 +136,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 6, "id": "3554f0b7-fee8-4446-a155-5d22dc0f0888", "metadata": {}, "outputs": [ @@ -144,7 +144,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "100%|██████████| 5/5 [00:27<00:00, 5.44s/it]\n" + "100%|██████████| 5/5 [00:26<00:00, 5.40s/it]\n" ] } ], diff --git a/credentials.env b/credentials.env index a95dc6d5..f311e6ee 100644 --- a/credentials.env +++ b/credentials.env @@ -5,8 +5,8 @@ BING_SEARCH_URL="https://api.bing.microsoft.com/v7.0/search" BOT_DIRECT_CHANNEL_ENDPOINT="https://directline.botframework.com/v3/directline" # Demo Data (edit with your own if you want to use your own data) -BLOB_CONNECTION_STRING="BlobEndpoint=https://datasetsgptsmartsearch.blob.core.windows.net/;SharedAccessSignature=sv=2022-11-02&ss=b&srt=sco&sp=rl&se=2026-01-03T02:11:44Z&st=2024-01-02T18:11:44Z&spr=https&sig=ngrEqvqBVaxyuSYqgPVeF%2B9c0fXLs94v3ASgwg7LDBs%3D" -BLOB_SAS_TOKEN="?sv=2022-11-02&ss=b&srt=sco&sp=rl&se=2025-05-07T22:20:04Z&st=2024-05-07T14:20:04Z&spr=https&sig=iy2PycZwWefYLWwqHjIzwkA6TjEBJTKr65Cd9yuv4HA%3D" +BLOB_CONNECTION_STRING="BlobEndpoint=https://datasetsgptsmartsearch.blob.core.windows.net/;QueueEndpoint=https://datasetsgptsmartsearch.queue.core.windows.net/;FileEndpoint=https://datasetsgptsmartsearch.file.core.windows.net/;TableEndpoint=https://datasetsgptsmartsearch.table.core.windows.net/;SharedAccessSignature=sv=2022-11-02&ss=bf&srt=sco&sp=rltf&se=2025-05-10T02:01:38Z&st=2024-05-09T18:01:38Z&spr=https&sig=vqU3TzulBIjvhHhUmYxE9zKXnhREuCGDHPpmdPDvv%2FQ%3D" +BLOB_SAS_TOKEN="?sv=2022-11-02&ss=bf&srt=sco&sp=rltf&se=2025-05-10T02:01:38Z&st=2024-05-09T18:01:38Z&spr=https&sig=vqU3TzulBIjvhHhUmYxE9zKXnhREuCGDHPpmdPDvv%2FQ%3D" # Edit with your own azure services values