API Access
MedGemma & MedSigLIP API Usage Guide
Get started with Google's medical AI models through comprehensive API access. Apply for API keys and integrate advanced medical AI capabilities into your applications.
Apply for API Access
Get started with MedGemma and MedSigLIP APIs
MedGemma API
Advanced medical text and multimodal AI models
Access MedGemma's powerful capabilities for medical text analysis, image understanding, and clinical decision support.
Key Features
- ✓Medical text generation and analysis
- ✓Multimodal medical image and text processing
- ✓Clinical question answering
- ✓Medical report generation
- ✓Fine-tuning capabilities
Available Models
MedGemma 4B Multimodal
Lightweight model for medical image and text tasks
4B parametersMedGemma 27B Text-only
Large language model specialized for medical text
27B parametersMedGemma 27B Multimodal
Advanced multimodal model for complex medical tasks
27B parametersMedSigLIP API
Medical image-text encoder for classification and retrieval
Leverage MedSigLIP's efficient dual-tower architecture for medical image classification, zero-shot inference, and semantic retrieval.
Key Features
- ✓Zero-shot medical image classification
- ✓Semantic image retrieval
- ✓Medical image embeddings
- ✓Data-efficient classification
- ✓Cross-modal similarity search
Model Specifications
Deployment Options
Choose the best deployment method for your needs
Local Deployment
Run models locally using Hugging Face transformers
Pros:
- +Full control
- +No API limits
- +Data privacy
Cons:
- -Requires GPU resources
- -Setup complexity
Vertex AI Deployment
Deploy as REST API endpoints on Google Cloud
Pros:
- +Scalable
- +Managed infrastructure
- +Production-ready
Cons:
- -Usage costs
- -Cloud dependency
Batch Processing
Process large datasets with Vertex AI batch jobs
Pros:
- +Cost-effective
- +Large-scale processing
Cons:
- -Not real-time
- -Batch scheduling
Code Examples
Get started with implementation examples
MedGemma Implementation
Local Deployment
from transformers import pipeline
# Load MedGemma model
pipe = pipeline(
"text-generation",
model="google/medgemma-27b-text-it",
torch_dtype="bfloat16",
device="cuda"
)
# Generate medical text
response = pipe(
"What are the symptoms of diabetes?",
max_length=200,
temperature=0.7
)
print(response[0]['generated_text'])Vertex AI REST API
import requests
import json
# Vertex AI endpoint
endpoint_url = "https://your-endpoint.googleapis.com/v1/projects/your-project/locations/us-central1/endpoints/your-endpoint:predict"
# Request payload
payload = {
"instances": [{
"prompt": "What are the symptoms of diabetes?",
"max_tokens": 200,
"temperature": 0.7
}]
}
# Make API request
headers = {
"Authorization": "Bearer YOUR_ACCESS_TOKEN",
"Content-Type": "application/json"
}
response = requests.post(endpoint_url, json=payload, headers=headers)
result = response.json()
print(result['predictions'][0]['generated_text'])MedSigLIP Implementation
Local Deployment
from transformers import AutoModel, AutoProcessor
import torch
from PIL import Image
# Load MedSigLIP model
model = AutoModel.from_pretrained("google/medsiglip")
processor = AutoProcessor.from_pretrained("google/medsiglip")
# Load and process image
image = Image.open("medical_image.jpg")
text = "chest x-ray showing pneumonia"
# Process inputs
inputs = processor(
text=[text],
images=[image],
return_tensors="pt",
padding=True
)
# Get embeddings
with torch.no_grad():
outputs = model(**inputs)
image_embeds = outputs.image_embeds
text_embeds = outputs.text_embeds
# Calculate similarity
similarity = torch.cosine_similarity(image_embeds, text_embeds)
print(f"Similarity score: {similarity.item():.4f}")Zero-shot Classification
import torch
from transformers import AutoModel, AutoProcessor
from PIL import Image
# Load model and processor
model = AutoModel.from_pretrained("google/medsiglip")
processor = AutoProcessor.from_pretrained("google/medsiglip")
# Define classification labels
labels = [
"normal chest x-ray",
"pneumonia chest x-ray",
"covid-19 chest x-ray",
"lung cancer chest x-ray"
]
# Load image
image = Image.open("chest_xray.jpg")
# Process inputs
inputs = processor(
text=labels,
images=[image] * len(labels),
return_tensors="pt",
padding=True
)
# Get predictions
with torch.no_grad():
outputs = model(**inputs)
logits = outputs.logits_per_image
probs = torch.softmax(logits, dim=-1)
# Get top prediction
top_idx = torch.argmax(probs, dim=-1)
confidence = probs[0, top_idx].item()
print(f"Prediction: {labels[top_idx]}")
print(f"Confidence: {confidence:.4f}")Official Resources
Complete documentation and examples