Skip to content

Commit 89b8eed

Browse files
Merge pull request #752 from microsoft/dev-v4
chore: Dev v4 to main
2 parents facbd06 + 6337ef1 commit 89b8eed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

57 files changed

+1091
-689
lines changed

docs/DeploymentGuide.md

Lines changed: 321 additions & 461 deletions
Large diffs are not rendered by default.

docs/LocalDevelopmentSetup.md

Lines changed: 608 additions & 0 deletions
Large diffs are not rendered by default.

docs/SampleQuestions.md

Lines changed: 45 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,10 +6,12 @@ To help you get started, here are some **Sample Prompts** you can ask in the app
66
## **Teams**
77
Select the Team option from the top-left section, then click Continue after choosing the desired team.
88

9-
By default, three teams are available after running the post-deployment scripts:
9+
> _Note: Five teams are available only if all teams are selected during post-deployment; otherwise, only selected teams are visible._
1010
- Retail
1111
- HR
1212
- Marketing
13+
- RFP
14+
- Contract Compliance
1315

1416
![Application](images/samplequestion_1.png)
1517

@@ -73,5 +75,47 @@ _Sample operation:_
7375
> _Observe: It goes into "Thinking Process", "Processing your plan" and "coordinating with AI Agents"_ <br>
7476
> _Review the output._
7577
78+
### **RFP Analysis Scenario**
79+
If you select the RFP team, follow the prompts below.
80+
81+
>**Agents Used:** RFP Summary, RFP Risk, RFP Compliance
82+
83+
The RFP Analysis Scenario allows users to explore and analyze Request for Proposal (RFP) and contract documents. Key tasks include:
84+
85+
_Sample operation:_
86+
87+
- Task: Switch to the **"RFP Team"** from the top left section and click **"Continue"** button.
88+
- Task: From the Quick Tasks, select **"RFP Document Summary"** and submit it.
89+
90+
> _Note: Average response time is 10–15 minutes._ <br>
91+
> _Observe: It will trigger the "Generating Plan Action" and give the Proposed Plan with 5 or more Steps_
92+
</br>
93+
94+
- Task: Click on **"Approve Task Plan"** Button.
95+
> _Note: Average response time is around 01 minute._ <br>
96+
> _Observe: It goes into "Thinking Process", "Processing your plan" and "coordinating with AI Agents"._ <br>
97+
> _Review the output._
98+
99+
### **Contract Compliance Review Scenario**
100+
If you select the Contract Compliance team, follow the prompts below.
101+
102+
>**Agents Used:** Contract Summary, Contract Risk, Contract Compliance
103+
104+
The Contract Compliance Review Scenario allows users to explore and analyze NDA and contract documents for compliance and risk assessment. Key tasks include:
105+
106+
_Sample operation:_
107+
108+
- Task: Switch to the **"Contract Compliance Review Team"** from the top left section and click **"Continue"** button.
109+
- Task: From the Quick Tasks, select **"NDA Contract Review"** and submit it.
110+
111+
> _Note: Average response time is 10–15 minutes._ <br>
112+
> _Observe: It will trigger the "Generating Plan Action" and give the Proposed Plan with 4 or more Steps_
113+
</br>
114+
115+
- Task: Click on **"Approve Task Plan"** Button.
116+
> _Note: Average response time is around 01 minute._ <br>
117+
> _Observe: It goes into "Thinking Process", "Processing your plan" and "coordinating with AI Agents"._ <br>
118+
> _Review the output._
119+
76120

77121
This structured approach ensures that users receive automated, AI-coordinated task execution and intelligent responses from specialized agents.
52.7 KB
Loading
127 KB
Loading

docs/images/Usecase_selection.png

51.1 KB
Loading
34.8 KB
Loading

infra/scripts/index_datasets.py

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -118,7 +118,7 @@ def extract_docx_text(docx_bytes):
118118

119119
print("Creating or updating Azure Search index...")
120120
search_index_client = SearchIndexClient(endpoint=ai_search_endpoint, credential=credential)
121-
index_result = search_index_client.create_or_update_index(index=index)
121+
search_index_client.create_or_update_index(index=index)
122122
print(f"Index '{ai_search_index_name}' created or updated successfully.")
123123
except Exception as e:
124124
print(f"Error creating/updating index: {e}")
@@ -163,7 +163,9 @@ def extract_docx_text(docx_bytes):
163163
print("Uploading documents to the index...")
164164
search_client = SearchClient(endpoint=ai_search_endpoint, index_name=ai_search_index_name, credential=credential)
165165
result = search_client.upload_documents(documents=data_list)
166-
print(f"Uploaded {len(data_list)} documents.")
166+
successes = sum(1 for r in result if getattr(r, "succeeded", False))
167+
failures = len(data_list) - successes
168+
print(f"Uploaded documents. Requested: {len(data_list)}, Succeeded: {successes}, Failed: {failures}")
167169
except Exception as e:
168170
print(f"Error uploading documents: {e}")
169171
sys.exit(1)

package-lock.json

Lines changed: 6 additions & 0 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

src/backend/.env.sample

Lines changed: 12 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -3,39 +3,32 @@ COSMOSDB_DATABASE=macae
33
COSMOSDB_CONTAINER=memory
44

55
AZURE_OPENAI_ENDPOINT=
6-
AZURE_OPENAI_MODEL_NAME=gpt-4o
7-
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
8-
AZURE_OPENAI_API_VERSION=2024-08-01-preview
6+
AZURE_OPENAI_MODEL_NAME=gpt-4.1-mini
7+
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4.1-mini
8+
AZURE_OPENAI_API_VERSION=2024-12-01-preview
99

1010
APPLICATIONINSIGHTS_INSTRUMENTATION_KEY=
11-
AZURE_AI_PROJECT_ENDPOINT=
1211
AZURE_AI_SUBSCRIPTION_ID=
1312
AZURE_AI_RESOURCE_GROUP=
1413
AZURE_AI_PROJECT_NAME=
14+
AZURE_AI_MODEL_DEPLOYMENT_NAME=gpt-4.1-mini
1515
APPLICATIONINSIGHTS_CONNECTION_STRING=
1616
AZURE_AI_AGENT_MODEL_DEPLOYMENT_NAME=gpt-4o
1717
AZURE_OPENAI_RAI_DEPLOYMENT_NAME=
18+
AZURE_AI_AGENT_MODEL_DEPLOYMENT_NAME=gpt-4.1-mini
1819
AZURE_COGNITIVE_SERVICES="https://cognitiveservices.azure.com/.default"
1920
AZURE_AI_AGENT_ENDPOINT=
2021
# AZURE_BING_CONNECTION_NAME=
21-
REASONING_MODEL_NAME=o3
22+
REASONING_MODEL_NAME="o4-mini"
2223
APP_ENV=dev
23-
MCP_SERVER_ENDPOINT=http://localhost:8080/mcp
24-
MCP_SERVER_NAME=MyMC
25-
MCP_SERVER_DESCRIPTION=My MCP Server
26-
TENANT_ID=
27-
CLIENT_ID=
24+
MCP_SERVER_ENDPOINT=http://localhost:9000/mcp
25+
MCP_SERVER_NAME=MacaeMcpServer
26+
MCP_SERVER_DESCRIPTION="MCP server with greeting, HR, and planning tools"
27+
AZURE_TENANT_ID=
28+
AZURE_CLIENT_ID=
2829
BACKEND_API_URL=http://localhost:8000
29-
FRONTEND_SITE_NAME=
30+
FRONTEND_SITE_NAME=*
3031
SUPPORTED_MODELS='["o3","o4-mini","gpt-4.1","gpt-4.1-mini"]'
3132
AZURE_AI_SEARCH_CONNECTION_NAME=
3233
AZURE_AI_SEARCH_ENDPOINT=
3334
BING_CONNECTION_NAME=
34-
35-
# Basic application logging (default: INFO level)
36-
AZURE_BASIC_LOGGING_LEVEL=INFO
37-
# Azure package logging (default: WARNING level to suppress INFO)
38-
AZURE_PACKAGE_LOGGING_LEVEL=WARNING
39-
# Comma-separated list of specific logger names to configure (default: empty - no custom loggers)
40-
# Example: AZURE_LOGGING_PACKAGES=azure.identity.aio._internal,azure.monitor.opentelemetry.exporter.export._base
41-
AZURE_LOGGING_PACKAGES=

0 commit comments

Comments
 (0)