Skip to content

Commit 12c3dd9

Browse files
divyaswarnkardivyaswarnkar
authored
Merge branch 'Azure:main' into main
2 parents 91f8ba5 + d3406b3 commit 12c3dd9

File tree

13 files changed

+92
-84
lines changed

13 files changed

+92
-84
lines changed

‎ingest-doc-blob-document-intelligence-cosmos/default/manifest.json‎

Lines changed: 13 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -1,16 +1,16 @@
11
{
22
"id": "default",
3-
"title": "Document ingestion from Azure Blob Storage using Azure Document Intelligence OCR into Azure Cosmos DB for RAG",
4-
"summary": "To support search and retrieval purposes for the retrieval-augmented generation (RAG) pattern, this workflow reads documents and images, using OCR powered by Azure Document Intelligence, from Azure Blob Storage, chunks the text, creates vector embeddings, formats the resulting data into a JSON document, and inserts that content into Azure Cosmos DB for NoSQL.",
3+
"title": "Document ingestion from Azure Blob Storage using Azure Document Intelligence OCR into Azure Cosmos DB",
4+
"summary": "To support search and retrieval purposes for the retrieval-augmented generation (RAG) pattern, this workflow reads documents and images, using OCR powered by Azure Document Intelligence, from Azure Blob Storage, chunks the text, creates vector embeddings, formats the resulting data into a JSON document, and inserts that content into Azure Cosmos DB for NoSQL. Please send any feedback or quesstions to CDB4AI@Microsoft.com",
55
"description": "",
6-
"prerequisites": "Before you use this template, you need to configure an Azure Open AI instance with an embedding model. For more detailed prerequisites, see the [Azure Logic Apps project sample on GitHub - Create a Chat with Your Data](https://github.com/Azure/logicapps/tree/master/LogicApps-AI-RAG-Demo](https://github.com/Azure/logicapps/tree/master/LogicApps-AI-RAG-Demo). You need to [create an Azure Document Intelligence resource](https://learn.microsoft.com/azure/ai-services/document-intelligence/overview). You also need to [create an Azure Cosmos DB database](https://learn.microsoft.com/azure/cosmos-db/nosql/quickstart-dotnet), and create a connection by using the keys and endpoint. Also, get more familiar with [Vector Search in Azure Cosmos DB](https://learn.microsoft.com/azure/cosmos-db/nosql/vector-search).",
6+
"prerequisites": "Before you use this template, you need to configure an Azure Open AI instance with an embedding model. You need to [create an Azure Document Intelligence resource](https://learn.microsoft.com/azure/ai-services/document-intelligence/overview). You also need to [create an Azure Cosmos DB database](https://learn.microsoft.com/azure/cosmos-db/nosql/quickstart-dotnet), and create a connection by using the keys and endpoint. Also, get more familiar with [Vector Search in Azure Cosmos DB](https://learn.microsoft.com/azure/cosmos-db/nosql/vector-search).",
77
"kinds": [
88
"stateful",
99
"stateless"
1010
],
1111
"workflows": {
1212
"default": {
13-
"name": "ingest-doc-blob-document-intelligence-cosmos"
13+
"name": "cdb-doc-indexer-blob"
1414
}
1515
},
1616
"artifacts": [
@@ -25,8 +25,8 @@
2525
},
2626
"parameters": [
2727
{
28-
"name": "OpenAI_TextEmbedding_Deployment_#workflowname#",
29-
"displayName": "OpenAI text embedding deployment identifier",
28+
"name": "AOAI_Emb_Dep_#workflowname#",
29+
"displayName": "OpenAI embedding deployment",
3030
"type": "String",
3131
"description": "Provide the deployment model for Azure OpenAI.",
3232
"required": true
@@ -40,35 +40,35 @@
4040
},
4141
{
4242
"name": "CosmosDB_Account_#workflowname#",
43-
"displayName": "Cosmos DB Account",
43+
"displayName": "Azure Cosmos DB account",
4444
"type": "String",
4545
"description": "Provide the name for the Azure Cosmos DB Account.",
4646
"required": true
4747
},
4848
{
4949
"name": "CosmosDB_Database_#workflowname#",
50-
"displayName": "Cosmos DB name",
50+
"displayName": "Azure Cosmos DB database",
5151
"type": "String",
5252
"description": "Provide the name for the Azure Cosmos DB database.",
5353
"required": true
5454
},
5555
{
5656
"name": "CosmosDB_Collection_#workflowname#",
57-
"displayName": "Cosmos DB collection name",
57+
"displayName": "Azure Cosmos DB collection",
5858
"type": "String",
5959
"description": "Provide the name for the Azure Cosmos DB collection.",
6060
"required": true
6161
},
6262
{
63-
"name": "CosmosDB_Vector_Path_#workflowname#",
64-
"displayName": "Vector embeddings path or property",
63+
"name": "CDB_Vector_#workflowname#",
64+
"displayName": "Vector embeddings property",
6565
"type": "String",
6666
"description": "Provide the path or property for the vector embeddings in the Cosmos DB data items.",
6767
"required": true
6868
},
6969
{
70-
"name": "CosmosDB_Text_Path_#workflowname#",
71-
"displayName": "Property with the document text in data items",
70+
"name": "CDB_Text_#workflowname#",
71+
"displayName": "Document text property",
7272
"type": "String",
7373
"description": "Provide the property that contains the document text in the Cosmos DB data items.",
7474
"required": true

‎ingest-doc-blob-document-intelligence-cosmos/default/workflow.json‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@
66
"type": "ServiceProvider",
77
"inputs": {
88
"parameters": {
9-
"deploymentId": "@parameters('OpenAI_TextEmbedding_Deployment_#workflowname#')",
9+
"deploymentId": "@parameters('AOAI_Emb_Dep_#workflowname#')",
1010
"input": "@take(body('Chunk_text')?['value'], length(body('Chunk_text')['value']))"
1111
},
1212
"serviceProviderConfiguration": {
@@ -31,9 +31,9 @@
3131
"inputs": {
3232
"from": "@range(0, length(body('Chunk_text')['value']))\r\n",
3333
"select": {
34-
"@{parameters('CosmosDB_Text_Path_#workflowname#')}": "@{body('Chunk_text')['value'][item()]}",
34+
"@{parameters('CDB_Text_#workflowname#')}": "@{body('Chunk_text')['value'][item()]}",
3535
"documentName": "@{triggerBody()?['name']}",
36-
"@{parameters('CosmosDB_Vector_Path_#workflowname#')}": "@body('Get_multiple_embeddings')['embeddings'][item()]",
36+
"@{parameters('CDB_Vector_#workflowname#')}": "@body('Get_multiple_embeddings')['embeddings'][item()]",
3737
"fileType": "@{triggerBody()?['properties']?['blobFullPathWithContainer']}",
3838
"id": "@{guid()}",
3939
"chunkNumber": "@{add(item(),1)}",

‎ingest-doc-blob-document-intelligence-cosmos/manifest.json‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,13 +1,13 @@
11
{
22
"id": "ingest-doc-blob-document-intelligence-cosmos",
3-
"title": "Document ingestion from Azure Blob Storage using Azure Document Intelligence OCR into Azure Cosmos DB for RAG",
4-
"summary": "To support search and retrieval purposes for the retrieval-augmented generation (RAG) pattern, this workflow reads documents and images, using OCR powered by Azure Document Intelligence, from Azure Blob Storage, chunks the text, creates vector embeddings, formats the resulting data into a JSON document, and inserts that content into Azure Cosmos DB for NoSQL.",
3+
"title": "Document ingestion from Azure Blob Storage using Azure Document Intelligence OCR into Azure Cosmos DB",
4+
"summary": "To support search and retrieval purposes for the retrieval-augmented generation (RAG) pattern, this workflow reads documents and images, using OCR powered by Azure Document Intelligence, from Azure Blob Storage, chunks the text, creates vector embeddings, formats the resulting data into a JSON document, and inserts that content into Azure Cosmos DB for NoSQL. Please send any feedback or quesstions to CDB4AI@Microsoft.com",
55
"skus": [
66
"standard"
77
],
88
"workflows": {
99
"default": {
10-
"name": "ingest-doc-blob-document-intelligence-cosmos"
10+
"name": "cdb-doc-indexer-blob"
1111
}
1212
},
1313
"featuredConnectors": [

‎ingest-doc-sharepoint-document-intelligence-cosmos/default/manifest.json‎

Lines changed: 15 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -1,16 +1,16 @@
11
{
22
"id": "default",
3-
"title": "Document ingestion from SharePoint using Azure Document Intelligence OCR into Azure Cosmos DB for RAG",
4-
"summary": "To support search and retrieval purposes for the retrieval-augmented generation (RAG) pattern, this workflow reads documents and images, using OCR powered by Azure Document Intelligence, from Microsoft SharePoint, chunks the text, creates vector embeddings, formats the resulting data into a JSON document, and inserts that content into Azure Cosmos DB for NoSQL.",
3+
"title": "Document ingestion from SharePoint using Azure Document Intelligence OCR into Azure Cosmos DB",
4+
"summary": "To support search and retrieval purposes for the retrieval-augmented generation (RAG) pattern, this workflow reads documents and images, using OCR powered by Azure Document Intelligence, from Microsoft SharePoint, chunks the text, creates vector embeddings, formats the resulting data into a JSON document, and inserts that content into Azure Cosmos DB for NoSQL. Please send any feedback or questions to CDB4AI@Microsoft.com.",
55
"description": "",
6-
"prerequisites": "Before you use this template, you need to configure an Azure Open AI instance with an embedding model. For more detailed prerequisites, see the [Azure Logic Apps project sample on GitHub - Create a Chat with Your Data](https://github.com/Azure/logicapps/tree/master/LogicApps-AI-RAG-Demo](https://github.com/Azure/logicapps/tree/master/LogicApps-AI-RAG-Demo). You need to [create an Azure Document Intelligence resource](https://learn.microsoft.com/azure/ai-services/document-intelligence/overview). You also need to [create an Azure Cosmos DB database](https://learn.microsoft.com/azure/cosmos-db/nosql/quickstart-dotnet), and create a connection by using the keys and endpoint. Also, get more familiar with [Vector Search in Azure Cosmos DB](https://learn.microsoft.com/azure/cosmos-db/nosql/vector-search).",
6+
"prerequisites": "Before you use this template, you need to configure an Azure Open AI instance with an embedding model. You need to [create an Azure Document Intelligence resource](https://learn.microsoft.com/azure/ai-services/document-intelligence/overview). You also need to [create an Azure Cosmos DB database](https://learn.microsoft.com/azure/cosmos-db/nosql/quickstart-dotnet), and create a connection by using the keys and endpoint. Also, get more familiar with [Vector Search in Azure Cosmos DB](https://learn.microsoft.com/azure/cosmos-db/nosql/vector-search).",
77
"kinds": [
88
"stateful",
99
"stateless"
1010
],
1111
"workflows": {
1212
"default": {
13-
"name": "ingest-doc-sharepoint-document-intelligence-cosmos"
13+
"name": "cdb-doc-indexer-sp"
1414
}
1515
},
1616
"artifacts": [
@@ -25,22 +25,22 @@
2525
},
2626
"parameters": [
2727
{
28-
"name": "OpenAI_TextEmbedding_Deployment_#workflowname#",
29-
"displayName": "OpenAI text embedding deployment identifier",
28+
"name": "AOAI_Emb_Dep_#workflowname#",
29+
"displayName": "OpenAI embedding deployment",
3030
"type": "String",
3131
"description": "Provide the deployment model for Azure OpenAI.",
3232
"required": true
3333
},
3434
{
3535
"name": "Sharepoint_Library_Name_#workflowname#",
36-
"displayName": "SharePoint Library Name",
36+
"displayName": "SharePoint Library name",
3737
"type": "String",
3838
"description": "Provide the name of the SharePoint Library.",
3939
"required": true
4040
},
4141
{
4242
"name": "Sharepoint_Site_Address_#workflowname#",
43-
"displayName": "SharePoint Site address",
43+
"displayName": "SharePoint site address",
4444
"type": "String",
4545
"description": "Provide the address of the SharePoint Site.",
4646
"required": true
@@ -53,35 +53,35 @@
5353
"required": true
5454
}, {
5555
"name": "CosmosDB_Account_#workflowname#",
56-
"displayName": "Cosmos DB Account",
56+
"displayName": "Azure Cosmos DB Account",
5757
"type": "String",
5858
"description": "Provide the name for the Azure Cosmos DB Account.",
5959
"required": true
6060
},
6161
{
6262
"name": "CosmosDB_Database_#workflowname#",
63-
"displayName": "Azure Cosmos DB name",
63+
"displayName": "Azure Cosmos DB database",
6464
"type": "String",
6565
"description": "Provide the name for the Azure Cosmos DB database.",
6666
"required": true
6767
},
6868
{
6969
"name": "CosmosDB_Collection_#workflowname#",
70-
"displayName": "Cosmos DB collection name",
70+
"displayName": "Azure Cosmos DB collection",
7171
"type": "String",
7272
"description": "Provide the name for the Azure Cosmos DB collection.",
7373
"required": true
7474
},
7575
{
76-
"name": "CosmosDB_Vector_Path_#workflowname#",
77-
"displayName": "Vector embeddings path or property",
76+
"name": "CDB_Vector_#workflowname#",
77+
"displayName": "Vector embeddings property",
7878
"type": "String",
7979
"description": "Provide the path or property for the vector embeddings in the Cosmos DB data items.",
8080
"required": true
8181
},
8282
{
83-
"name": "CosmosDB_Text_Path_#workflowname#",
84-
"displayName": "Property with the document text in data items",
83+
"name": "CDB_Text_#workflowname#",
84+
"displayName": "Property with document text",
8585
"type": "String",
8686
"description": "Provide the property that contains the document text in the Cosmos DB data items.",
8787
"required": true

‎ingest-doc-sharepoint-document-intelligence-cosmos/default/workflow.json‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
"type": "ServiceProvider",
66
"inputs": {
77
"parameters": {
8-
"deploymentId": "@parameters('OpenAI_TextEmbedding_Deployment_#workflowname#')",
8+
"deploymentId": "@parameters('AOAI_Emb_Dep_#workflowname#')",
99
"input": "@take(body('Chunk_text')?['value'], length(body('Chunk_text')['value']))"
1010
},
1111
"serviceProviderConfiguration": {
@@ -30,9 +30,9 @@
3030
"inputs": {
3131
"from": "@range(0, length(body('Chunk_text')['value']))\r\n",
3232
"select": {
33-
"@{parameters('CosmosDB_Text_Path_#workflowname#')}": "@{body('Chunk_text')['value'][item()]}",
33+
"@{parameters('CDB_Text_#workflowname#')}": "@{body('Chunk_text')['value'][item()]}",
3434
"documentName": "@{triggerBody()?['{FilenameWithExtension}']}",
35-
"@{parameters('CosmosDB_Vector_Path_#workflowname#')}": "@body('Get_multiple_embeddings')['embeddings'][item()]",
35+
"@{parameters('CDB_Vector_#workflowname#')}": "@body('Get_multiple_embeddings')['embeddings'][item()]",
3636
"fileLink": "@{triggerBody()?['{Link}']}",
3737
"id": "@{guid()}",
3838
"chunkNumber": "@{add(item(),1)}",

‎ingest-doc-sharepoint-document-intelligence-cosmos/manifest.json‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,13 +1,13 @@
11
{
22
"id": "ingest-doc-sharepoint-document-intelligence-cosmos",
3-
"title": "Document ingestion from SharePoint using Azure Document Intelligence OCR into Azure Cosmos DB for RAG",
4-
"summary": "To support search and retrieval purposes for the retrieval-augmented generation (RAG) pattern, this workflow reads documents and images, using OCR powered by Azure Document Intelligence, from Microsoft SharePoint, chunks the text, creates vector embeddings, formats the resulting data into a JSON document, and inserts that content into Azure Cosmos DB for NoSQL.",
3+
"title": "Document ingestion from SharePoint using Azure Document Intelligence OCR into Azure Cosmos DB",
4+
"summary": "To support search and retrieval purposes for the retrieval-augmented generation (RAG) pattern, this workflow reads documents and images, using OCR powered by Azure Document Intelligence, from Microsoft SharePoint, chunks the text, creates vector embeddings, formats the resulting data into a JSON document, and inserts that content into Azure Cosmos DB for NoSQL. Please send any feedback or questions to CDB4AI@Microsoft.com.",
55
"skus": [
66
"standard"
77
],
88
"workflows": {
99
"default": {
10-
"name": "ingest-doc-sharepoint-document-intelligence-cosmos"
10+
"name": "cdb-doc-indexer-sp"
1111
}
1212
},
1313
"featuredConnectors": [

0 commit comments

Comments
 (0)