ModuleNotFoundError: No Module Named ‘ollama’ (2026)

pip install ollama

# Or with poetry
poetry add ollama

# Or with uv (faster)
uv pip install ollama

import ollama

response = ollama.chat(model='llama3.1', messages=[
    {'role': 'user', 'content': 'Why is the sky blue?'}
])
print(response['message']['content'])

from ollama import AsyncClient
import asyncio

async def chat():
    client = AsyncClient()
    response = await client.chat(
        model='llama3.1',
        messages=[{'role': 'user', 'content': 'Hello!'}]
    )
    print(response['message']['content'])

asyncio.run(chat())

Frequently Asked Questions

Diagnostic checklist for “No module named ‘ollama'”

• Verify pip install target. Run pip show ollama — if not installed, run pip install ollama.
• Check the active Python interpreter. which python (mac/Linux) or where python (Windows). Both pip and python must point to the same environment.
• Check virtual environment activation. If you use venv/conda, activate before installing: source .venv/bin/activate.
• Rule out uppercase/lowercase. Python imports are case-sensitive: import PyPDF2 not import pypdf2.
• Rule out the pip-vs-package-name mismatch. Some packages install under a different name than you import (e.g. pip install beautifulsoup4 → import bs4).

Installing ollama

# Standard pip install
pip install ollama

# In a virtual environment (recommended)
python -m venv .venv
source .venv/bin/activate  # or .venv\Scripts\activate on Windows
pip install ollama

# With uv (faster alternative)
uv pip install ollama

Common causes for “No module named ‘ollama'”

• Python interpreter mismatch. Multiple Python installations can confuse pip. Verify with which python and which pip.
• Virtual environment not activated. If the venv isn’t activated, pip installs to your system Python instead.
• Notebook kernel mismatch. Jupyter uses a kernel that may differ from your terminal Python. Use %pip install ollama inside the notebook.
• Import name differs from install name. pip install beautifulsoup4 → import bs4. Check the package’s PyPI page.
• Windows PATH issues. Ensure Python is on PATH; use python -m pip install to invoke pip via the correct Python.

Working code example

# Verify install worked
import ollama
print(getattr(ollama, '__version__', 'no version attribute'))

Best practices

• Always use a virtual environment. Avoids most module-not-found errors.
• Use pip freeze to lock versions. pip freeze > requirements.txt makes your setup reproducible.
• Consider uv or Poetry. Modern package managers with better dep resolution and reproducibility.

Is ollama free to install and use?

Yes. Both the Ollama runtime and the Python client are open-source (MIT license). You can run models like Llama 3, Mistral, Phi, Gemma locally with no API costs. Hardware permitting (8GB+ RAM for small models, 16GB+ for 7B), everything runs offline.

Why does ollama.chat() fail even after pip install ollama?

The Python client connects to a local server. If the Ollama runtime isn’t running (or isn’t installed), you’ll get connection errors. Run “ollama serve” in a terminal or check the menu bar (macOS) / system tray (Windows) for the Ollama process.

Can I use ollama with LangChain?

Yes. Install both: pip install ollama langchain-ollama. Then use ChatOllama from langchain_ollama. This works for RAG, agents, and chains using your local Llama or Mistral model instead of OpenAI.

What models does Ollama support in 2026?

Llama 3.1, Llama 3.2 (multimodal), Mistral Nemo, Mistral Small, Phi-3.5, Gemma 2, Qwen 2.5, DeepSeek-Coder, CodeLlama, plus dozens of community variants. Pull any with: ollama pull modelname.

Can Ollama run in Docker or a server?

Yes. Official image: docker run -d -p 11434:11434 ollama/ollama. Then set OLLAMA_HOST=http://your-server:11434 in your Python script. Great for shared dev environments or capstone deployment.