Skip to main content
Loading navigation
Back to challenges

Google ADK Multimodal Traditional Medicine Diagnostic Assistant

Integrating traditional medicine taxonomy with modern clinical diagnostic frameworks requires rich multimodal reasoning over clinical text and herbal imagery. Build an agent using Google ADK and Gemini 1.5 Pro to standardize clinical research records.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Develop an AI assistant for traditional medicine taxonomy using Google Agent Development Kit and Gemini.

How work is evaluated

Evaluation

Evaluates accuracy of herbal mapping and medical terminology alignment.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

valid_standard_name

Ensures output maps to correct botanical entity.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

botanical_accuracy

Accuracy of botanical mapping • target: 0.92 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

  • Utilize Google ADK to structure multimodal analysis tasks

  • Leverage Gemini vision capabilities for herbal sample identification

  • Map traditional formulations onto WHO ICD-11 global standards

Resources

Dataset notes

Annotated corpus of traditional medicine texts and botanical classifications.

Challenge setup

Evaluates accuracy of herbal mapping and medical terminology alignment.

Challenge input

JSON containing query and image descriptor

Google ADK

Mandatory framework requirement

Evaluated output

JSON mapped diagnostic record

Evaluation checks
  • Ensures output maps to correct botanical entity.
  • Accuracy of botanical mapping • target: 0.92 • range: 0-1
Configured evaluation evidence
  • Benchmark: Health-Taxonomy-Bench
  • Botanical Accuracy target: 0.92
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Environment
  • Modal · Optional
Action Space
  • Google ADK · Required
  • Google · Optional
Policy Serving
  • Modal · Optional

Evaluation contract

  • valid_standard_name · Weight 1
  • botanical_accuracy · Weight 1

Metrics

  • botanical_accuracy · Target 0.92

Benchmarks

  • Health-Taxonomy-Bench
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing query and image descriptor

    Output: JSON mapped diagnostic record

    Execution harness: Python

Evaluation tools

  • Google ADK · Agent SDK

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Google ADK Multimodal Traditional Medicine Diagnostic Assistant