Ollama

Run open-source models locally with OllamaModel — no cloud API key required. Ideal for offline development and testing agents against local LLMs.

For standalone invoke / stream usage, see LLM Models — Ollama.

Local setup

# Install Ollama (macOS/Linux)
curl -fsSL https://ollama.com/install.sh | sh

# Pull a model (downloads to ~/.ollama/models on your machine)
ollama pull llama3.2

# Confirm the local server is running
ollama list

Install

pip install --extra-index-url https://core-packages.elsai.ai/root/elsai-model/ elsai-model==2.0.0
pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents==0.3.0

Setup

export OLLAMA_HOST=http://localhost:11434   # optional — local server default
export OLLAMA_MODEL_NAME=llama3.2             # must match a pulled local model

Agent — basic

import os
from elsai import Agent
from elsai_model.ollama import OllamaModel

model = OllamaModel(
    host=os.getenv("OLLAMA_HOST"),
    model_id=os.getenv("OLLAMA_MODEL_NAME", "llama3.2"),
    temperature=0.2,
)
agent = Agent(
    model=model,
    system_prompt="You are a concise assistant.",
)
result = agent("What is 17 + 28? Reply with just the number.")
print(result.message["content"][0]["text"])

Popular models

ollama pull llama3.2
ollama pull mistral
ollama pull codellama
ollama pull phi3