# Installation took 10 minutes
curl -fsSL https://ollama.com/install.sh | sh
ollama pull gemma4:2b-instruct-fp16

# That's it. Seriously.

import ollama

def analyze_symptoms(symptoms: str, vital_signs: dict) -> dict:
    """
    Analyze patient symptoms using local Gemma 4.
    No internet required.
    """
    prompt = f"""
    You are a medical triage assistant. Based on these symptoms and vitals,
    provide:
    1. Potential conditions (with confidence levels)
    2. Recommended immediate actions
    3. Whether emergency care is needed

    Symptoms: {symptoms}
    Vitals: {vital_signs}

    Be conservative. When in doubt, recommend professional evaluation.
    """

    response = ollama.chat(
        model='gemma4:2b-instruct-fp16',
        messages=[{'role': 'user', 'content': prompt}]
    )

    return response['message']['content']

# Example usage
result = analyze_symptoms(
    symptoms="Severe headache, light sensitivity, nausea for 3 hours",
    vital_signs={
        "bp": "145/92",
        "temp": "38.2°C",
        "pulse": "88"
    }
)

print(result)

import base64
import ollama

def analyze_skin_condition(image_path: str) -> str:
    with open(image_path, 'rb') as f:
        image_data = base64.b64encode(f.read()).decode()

    response = ollama.chat(
        model='gemma4:2b-instruct-fp16',
        messages=[{
            'role': 'user',
            'content': 'Describe any visible skin abnormalities in this image. '
                      'Note areas of concern.',
            'images': [image_data]
        }]
    )

    return response['message']['content']

# On edge device (Raspberry Pi + Gemma E2B)
def should_send_to_cloud(data: dict) -> tuple[bool, str]:
    """
    Use local model to determine if cloud processing is required.
    Can reduce API calls by ~80% in typical deployments.
    """
    analysis = ollama.chat(
        model='gemma4:2b-instruct-fp16',
        messages=[{
            'role': 'user',
            'content': f'Is this data anomalous enough to require '
                      f'expert system analysis? {data}'
        }]
    )

    decision = 'yes' in analysis['message']['content'].lower()
    reason = analysis['message']['content']

    return decision, reason

# Typical result: 80-85% reduction in cloud API costs
# Only genuinely complex cases escalate to expensive models

# 1. Install Ollama
curl -fsSL https://ollama.com/install.sh | sh

# 2. Pull Gemma 4 E2B
ollama pull gemma4:2b-instruct-fp16

# 3. Test it
ollama run gemma4:2b-instruct-fp16 "Explain quantum computing in simple terms"

# 4. Install Python client
pip install ollama

import ollama

response = ollama.chat(
    model='gemma4:2b-instruct-fp16',
    messages=[
        {
            'role': 'system',
            'content': 'You are a helpful assistant running on a Raspberry Pi.'
        },
        {
            'role': 'user',
            'content': 'What can you help me with?'
        }
    ]
)

print(response['message']['content'])