applied-ai-engineering-samples
applied-ai-engineering-samples copied to clipboard
Added langgraph example
Title: Add "Agentic Accessibility Checker" Demo
Description:
This pull request introduces a new demo to the AAIE samples repo: the Agentic Accessibility Checker. The demo provides an end-to-end example of building an autonomous agent for real estate accessibility analysis using Google’s cutting-edge AI tools, including Gemini and the Vertex AI Reasoning Engine. It includes:
- Synthetic Data Generation: Utilizes generative models to create realistic multimodal real estate data (text and images), stored in GCS and Firestore.
- Cloud Run API: A FastAPI-based service acting as the agent’s environment for retrieving property details.
- LangGraph Agent with Gemini: A ReAct-style agent that can reason about and interact with data, tools, and APIs, leveraging both text and image understanding capabilities.
- Streamlit Frontend: A user-friendly interface that allows interactive exploration of properties and direct engagement with the agent.
- Comprehensive Setup Instructions: Detailed steps for installation, data generation, API deployment, agent deployment, and frontend setup, ensuring a smooth onboarding experience.
- Integration with Google Cloud Services: integrates with Firestore, GCS, and Vertex AI Reasoning Engine, includes environment-specific parameters.
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).
View this failed invocation of the CLA check for more information.
For the most up to date status, view the checks section at the bottom of the pull request.
Gemini encountered an error creating the review. You can try again by commenting @code-review-assist review.
@code-review-assist review
@code-review-assist review