Skip to content

Commit 1a200ca

Browse files
martaldsantosmartaldsantos
committed
added previous hacks
1 parent 9520015 commit 1a200ca

File tree

145 files changed

+21287
-0
lines changed

Some content is hidden

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

145 files changed

+21287
-0
lines changed

‎01-ClaimsProcessing/.devcontainer/devcontainer.json‎

Lines changed: 42 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,42 @@
1+
{
2+
"name": "Python 3",
3+
"image": "mcr.microsoft.com/devcontainers/python:1-3.11-bullseye",
4+
"features": {
5+
"ghcr.io/devcontainers/features/azure-cli:1": {
6+
"installBicep": true
7+
},
8+
"ghcr.io/jlaundry/devcontainer-features/azure-functions-core-tools:1": {},
9+
"ghcr.io/devcontainers/features/docker-in-docker:2": {
10+
"version": "latest",
11+
"enableNonRootDocker": "true"
12+
}
13+
},
14+
"postCreateCommand": "pip3 install --user -r requirements.txt",
15+
"customizations": {
16+
"vscode": {
17+
"extensions": [
18+
"github.copilot",
19+
"github.copilot-chat",
20+
"ms-azuretools.vscode-azurefunctions",
21+
"ms-python.autopep8",
22+
"ms-python.debugpy",
23+
"ms-python.python",
24+
"ms-python.vscode-pylance",
25+
"ms-python.vscode-python-envs",
26+
"ms-toolsai.jupyter",
27+
"ms-toolsai.jupyter-keymap",
28+
"ms-toolsai.jupyter-renderers",
29+
"ms-toolsai.vscode-jupyter-cell-tags",
30+
"ms-toolsai.vscode-jupyter-slideshow",
31+
"benjaminbenais.copilot-theme",
32+
"Azurite.azurite",
33+
"ms-azuretools.vscode-azurestorage",
34+
"ms-azuretools.vscode-bicep",
35+
"vs-publisher-1448185.keyoti-changeallendoflinesequence"
36+
],
37+
"settings": {
38+
"workbench.colorTheme": "Copilot Theme"
39+
}
40+
}
41+
}
42+
}

‎01-ClaimsProcessing/.env.sample‎

Lines changed: 25 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,25 @@
1+
AZURE_STORAGE_ACCOUNT_NAME=""
2+
AZURE_STORAGE_ACCOUNT_KEY=""
3+
AZURE_STORAGE_CONNECTION_STRING=""
4+
LOG_ANALYTICS_WORKSPACE_NAME=""
5+
SEARCH_SERVICE_NAME=""
6+
SEARCH_SERVICE_ENDPOINT=""
7+
SEARCH_ADMIN_KEY=""
8+
AI_FOUNDRY_HUB_NAME=""
9+
AI_FOUNDRY_PROJECT_NAME=""
10+
AI_FOUNDRY_ENDPOINT=""
11+
AI_FOUNDRY_KEY=""
12+
AI_FOUNDRY_HUB_ENDPOINT=""
13+
AI_FOUNDRY_PROJECT_ENDPOINT=""
14+
AZURE_AI_CONNECTION_ID=""
15+
COSMOS_ENDPOINT=""
16+
COSMOS_KEY=""
17+
COSMOS_CONNECTION_STRING=""
18+
AZURE_OPENAI_SERVICE_NAME=""
19+
AZURE_OPENAI_ENDPOINT=""
20+
AZURE_OPENAI_KEY=""
21+
AZURE_OPENAI_DEPLOYMENT_NAME=""
22+
MODEL_DEPLOYMENT_NAME=""
23+
ACR_NAME=""
24+
ACR_USERNAME=""
25+
ACR_PASSWORD=""

‎01-ClaimsProcessing/.gitignore‎

Lines changed: 206 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,206 @@
1+
# Byte-compiled / optimized / DLL files
2+
__pycache__/
3+
*.py[cod]
4+
*$py.class
5+
6+
# C extensions
7+
*.so
8+
9+
# Distribution / packaging
10+
.Python
11+
build/
12+
develop-eggs/
13+
dist/
14+
downloads/
15+
eggs/
16+
.eggs/
17+
lib/
18+
lib64/
19+
parts/
20+
sdist/
21+
var/
22+
wheels/
23+
share/python-wheels/
24+
*.egg-info/
25+
.installed.cfg
26+
*.egg
27+
MANIFEST
28+
eval-output-simple.json
29+
eval-input-simple.jsonl
30+
container-apps.sh
31+
32+
simplified_crash_reports.json
33+
structured_crash_reports.json
34+
# PyInstaller
35+
# Usually these files are written by a python script from a template
36+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
37+
*.manifest
38+
*.spec
39+
40+
# Installer logs
41+
pip-log.txt
42+
pip-delete-this-directory.txt
43+
44+
# Unit test / coverage reports
45+
htmlcov/
46+
.tox/
47+
.nox/
48+
.coverage
49+
.coverage.*
50+
.cache
51+
nosetests.xml
52+
coverage.xml
53+
*.cover
54+
*.py,cover
55+
.hypothesis/
56+
.pytest_cache/
57+
cover/
58+
eval-metrics-table.csv
59+
60+
# Translations
61+
*.mo
62+
*.pot
63+
64+
# Django stuff:
65+
*.log
66+
local_settings.py
67+
db.sqlite3
68+
db.sqlite3-journal
69+
70+
# Flask stuff:
71+
instance/
72+
.webassets-cache
73+
74+
# Scrapy stuff:
75+
.scrapy
76+
77+
# Sphinx documentation
78+
docs/_build/
79+
80+
# PyBuilder
81+
.pybuilder/
82+
target/
83+
84+
# Jupyter Notebook
85+
.ipynb_checkpoints
86+
87+
# IPython
88+
profile_default/
89+
ipython_config.py
90+
91+
# pyenv
92+
# For a library or package, you might want to ignore these files since the code is
93+
# intended to run in multiple environments; otherwise, check them in:
94+
# .python-version
95+
96+
# pipenv
97+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
98+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
99+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
100+
# install all needed dependencies.
101+
#Pipfile.lock
102+
103+
# UV
104+
# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
105+
# This is especially recommended for binary packages to ensure reproducibility, and is more
106+
# commonly ignored for libraries.
107+
#uv.lock
108+
109+
# poetry
110+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
111+
# This is especially recommended for binary packages to ensure reproducibility, and is more
112+
# commonly ignored for libraries.
113+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
114+
#poetry.lock
115+
116+
# pdm
117+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
118+
#pdm.lock
119+
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
120+
# in version control.
121+
# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
122+
.pdm.toml
123+
.pdm-python
124+
.pdm-build/
125+
126+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
127+
__pypackages__/
128+
129+
# Celery stuff
130+
celerybeat-schedule
131+
celerybeat.pid
132+
133+
# SageMath parsed files
134+
*.sage.py
135+
136+
# Environments
137+
.env
138+
.venv
139+
env/
140+
venv/
141+
ENV/
142+
env.bak/
143+
venv.bak/
144+
145+
# Spyder project settings
146+
.spyderproject
147+
.spyproject
148+
149+
# Rope project settings
150+
.ropeproject
151+
152+
# mkdocs documentation
153+
/site
154+
155+
# mypy
156+
.mypy_cache/
157+
.dmypy.json
158+
dmypy.json
159+
160+
# Pyre type checker
161+
.pyre/
162+
163+
# pytype static type analyzer
164+
.pytype/
165+
166+
# Cython debug symbols
167+
cython_debug/
168+
169+
# PyCharm
170+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
171+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
172+
# and can be added to the global gitignore or merged into this file. For a more nuclear
173+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
174+
#.idea/
175+
176+
# Abstra
177+
# Abstra is an AI-powered process automation framework.
178+
# Ignore directories containing user credentials, local state, and settings.
179+
# Learn more at https://abstra.io/docs
180+
.abstra/
181+
182+
# Visual Studio Code
183+
# Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
184+
# that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
185+
# and can be added to the global gitignore or merged into this file. However, if you prefer,
186+
# you could uncomment the following to ignore the enitre vscode folder
187+
# .vscode/
188+
189+
# Ruff stuff:
190+
.ruff_cache/
191+
192+
# PyPI configuration file
193+
.pypirc
194+
195+
# Cursor
196+
# Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
197+
# exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
198+
# refer to https://docs.cursor.com/context/ignore-files
199+
.cursorignore
200+
.cursorindexingignore
201+
202+
203+
# Other files
204+
azure_search_integration_summary.json
205+
processed_documents_for_vectorization.json
206+
processing_summary_gpt4o.json

‎01-ClaimsProcessing/.vscode/extensions.json‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
1+
{
2+
"recommendations": [
3+
"ms-azuretools.vscode-azurefunctions",
4+
"ms-python.python"
5+
]
6+
}

‎01-ClaimsProcessing/.vscode/launch.json‎

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
{
2+
"version": "0.2.0",
3+
"configurations": [
4+
{
5+
"name": "Attach to Python Functions",
6+
"type": "debugpy",
7+
"request": "attach",
8+
"connect": {
9+
"host": "localhost",
10+
"port": 9091
11+
},
12+
"preLaunchTask": "func: host start"
13+
}
14+
]
15+
}

‎01-ClaimsProcessing/.vscode/settings.json‎

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
1+
{
2+
"azureFunctions.deploySubpath": "challenge-5/azure-function-orchestrator",
3+
"azureFunctions.scmDoBuildDuringDeployment": true,
4+
"azureFunctions.pythonVenv": ".venv",
5+
"azureFunctions.projectLanguage": "Python",
6+
"azureFunctions.projectRuntime": "~4",
7+
"debug.internalConsoleOptions": "neverOpen",
8+
"azureFunctions.projectLanguageModel": 2,
9+
"azureFunctions.projectSubpath": "challenge-5/azure-function-orchestrator"
10+
}

‎01-ClaimsProcessing/.vscode/tasks.json‎

Lines changed: 33 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,33 @@
1+
{
2+
"version": "2.0.0",
3+
"tasks": [
4+
{
5+
"label": "func: host start (shell fallback)",
6+
"type": "shell",
7+
"command": "func host start",
8+
"isBackground": true,
9+
"dependsOn": "pip install (functions)",
10+
"problemMatcher": [],
11+
"options": {
12+
"cwd": "${workspaceFolder}/challenge-5/azure-function-orchestrator"
13+
}
14+
},
15+
{
16+
"label": "pip install (functions)",
17+
"type": "shell",
18+
"osx": {
19+
"command": "${config:azureFunctions.pythonVenv}/bin/python -m pip install -r requirements.txt"
20+
},
21+
"windows": {
22+
"command": "${config:azureFunctions.pythonVenv}/Scripts/python -m pip install -r requirements.txt"
23+
},
24+
"linux": {
25+
"command": "${config:azureFunctions.pythonVenv}/bin/python -m pip install -r requirements.txt"
26+
},
27+
"problemMatcher": [],
28+
"options": {
29+
"cwd": "${workspaceFolder}/challenge-5/azure-function-orchestrator"
30+
}
31+
}
32+
]
33+
}

‎01-ClaimsProcessing/README.md‎

Lines changed: 38 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
1+
# Unlocking Multi-Agent Capabilities with Azure AI Services
2+
3+
Welcome to the Multi-Agent Insurance Claims Processing Hackathon! Today, you'll explore intelligent agent systems powered by Azure AI to streamline complex insurance workflows. Get ready for a hands-on, high-impact day of learning and innovation!
4+
5+
## Introduction
6+
Get ready to transform insurance with AI! In this hackathon, you'll build intelligent agents that process claims, analyze documents, and make smart decisions—just like real insurance pros. From reading handwritten forms to detecting fraud, your agents will collaborate to handle complex workflows in minutes, not weeks. By the end, you'll have created a powerful multi-agent system that redefines insurance claim processing.
7+
8+
## Learning Objectives
9+
10+
By participating in this hackathon, you will learn how to:
11+
- **Build Intelligent Document Systems** using Azure Document Intelligence and GPT-4.1-mini to extract and analyze data from complex insurance documents.
12+
- **Create and Test AI Agents** with Azure AI Agent Service for automated claim processing.
13+
- **Monitor and Evaluate Agents** using Azure AI Foundry for performance, safety, and reliability.
14+
- **Develop Specialized Agents** (e.g., Policy Checker, Claim Reviewer, Risk Analyzer) with Semantic Kernel.
15+
- **Orchestrate Multi-Agent Systems** using Azure Container Apps and advanced coordination patterns for seamless claims handling.
16+
17+
## Architecture
18+
This solution automates insurance claim processing using a multi-agent AI system on Azure. Claims are uploaded along crash documents to Storage Accounts, triggering workflows that clean and structure data with Azure AI Foundry (GPT-4.1-mini). Structured data is stored in Cosmos DB and indexed with Azure AI Search. If you want to know more about how to automatize this, have a look at [last year's hackathon](https://github.com/martaldsantos/doc-process-hack/tree/main/Challenge4). Then, follows the orchestration of specialized AI agents—a Policy Checker, Claim Reviewer, and Risk Analyser—that collaborate to assess claims, detect fraud, and generate a comprehensive summary for human review. Application Insights and Log Analytics monitors the system for performance and reliability, enabling efficient, accurate, and scalable claim handling.
19+
20+
<img width="1828" height="815" alt="image" src="https://github.com/user-attachments/assets/f776cc4b-90da-4898-8a1c-a96282f39bbc" />
21+
22+
## Requirements
23+
To successfully complete this hackathon, you will need the following:
24+
25+
- GitHub account to access the repository and run GitHub Codespaces and Github Copilot.
26+
- Be familiar with Python programming, including handling JSON data and making API calls.​
27+
- Be familiar with Generative AI Solutions and Azure AI Services.
28+
- An active Azure subscription, with Owner or Contributor rights.
29+
- Ability to provision resources in **Sweden Central** or [another supported region](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#global-standard-model-availability).
30+
31+
## Challenges
32+
33+
- Challenge 00: **[Environment Setup & Azure Resource Deployment](challenge-0/README.md)** : Deploy foundational Azure services and set up your development environment for the hackathon
34+
- Challenge 01: **[Document Processing and Vectorized Search](challenge-1/README.md)**: Build a comprehensive document processing system using multimodal analysis and Azure AI Search for semantic understanding
35+
- Challenge 02: **[Build and Test Your First Agent](challenge-2/README.md)**: Create your first intelligent agent using Azure AI Agent Service to handle insurance claim processing workflows
36+
- Challenge 03: **[Agent Observability and Evaluation](challenge-3/README.md)**: Implement comprehensive observability and evaluation frameworks for your AI agents using Azure AI Foundry's evaluation capabilities
37+
- Challenge 04: **[Semantic Kernel + Azure AI Agent Service Agents](challenge-4/readme.md)**: Create specialized AI agents (Policy Checker, Claim Reviewer, Risk Analyser) using Semantic Kernel integration for enhanced capabilities
38+
- Challenge 05: **[Agent Orchestration](challenge-5/README.md)** Coordinate multiple specialized agents to work together on complex tasks through various orchestration patterns with Azure Container Apps

0 commit comments

Comments
 (0)