ollama

library0.6.2pypypi✓ verified 25d ago

Official Python client for Ollama — the local LLM runtime. Wraps the Ollama REST API with native Python types. Requires Ollama to be installed and running locally (or pointed at https://ollama.com for cloud models). Not an inference provider — it's a runtime client.

llm-agents ai-ml http-networking

pip install ollama

github ↗package ↗homepage ↗

INSTALL

IMPORT

SIG · OLLAMA

ollama

llm-agentspythonv0.6.2

Install

4.0s avg

Import

774ms

Disk

30MB

Pass rate

10/ 10

Env Coverage10 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.6.2 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.95 runs

installs and imports cleanly · install 0.0s · import 0.798s · 31.7MB

glibc

py 3.10–3.95 runs

installs and imports cleanly · install 4.0s · import 0.750s · 31MB

30MB installed

● package 30MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

chat

✓ from ollama import chat

Basic chat with a locally running model

from ollama import chat response = chat( model='gemma3', messages=[{'role': 'user', 'content': 'Why is the sky blue?'}] ) print(response.message.content)

Debug

Known issues

breakingpip install ollama installs only the Python client — not the Ollama runtime. If the runtime is not installed and running, all calls raise ConnectionError immediately.

fix

Install the Ollama runtime separately from https://ollama.com/download, then run 'ollama serve' (or the desktop app). Verify with: curl http://localhost:11434

affects: all

breakingModels must be explicitly pulled before use. Calling chat() with a model that hasn't been pulled raises a ResponseError with status_code 404.

fix

Run 'ollama pull <model>' before use, or catch ResponseError and call ollama.pull(model) programmatically.

affects: all

breakingTool calling with stream=True is incomplete. When tools are provided, Ollama buffers the full response and returns it as a single block even with stream=True set — true incremental streaming does not occur.

fix

Use stream=False when tools are involved. Track https://github.com/ollama/ollama/issues/9084 for resolution.

affects: all (as of 0.12.x)

gotchapip install ollama-python installs a different, unofficial third-party package with a completely different API (ModelManagementAPI, GenerateAPI classes). It is not the official client.

fix

Use pip install ollama (no hyphen suffix). Official package is at pypi.org/project/ollama.

affects: all

gotchaThe Ollama Python library defaults to http://localhost:11434. To connect to a remote Ollama instance, you must pass host explicitly via Client(host='http://<remote>:11434'). The OLLAMA_HOST env var is respected by the runtime but NOT automatically picked up by the Python client.

fix

Pass host explicitly: Client(host=os.environ.get('OLLAMA_HOST', 'http://localhost:11434'))

affects: all

gotchaThe OpenAI-compatible endpoint is at http://localhost:11434/v1 — but this is a separate REST interface, not the native ollama Python library. Using openai SDK against this endpoint requires api_key='ollama' (any non-empty string) as a placeholder.

fix

from openai import OpenAI; client = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')

affects: all

gotchaCloud models (e.g. gpt-oss:120b-cloud, deepseek-v3.1:671b-cloud) require ollama signin and ollama pull before use. They are routed through ollama.com and require an API key when accessed via the cloud API endpoint directly.

fix

Run 'ollama signin' first. For direct cloud API access, set host='https://ollama.com' and pass Authorization header with OLLAMA_API_KEY.

affects: >=0.6.0

Upgrade

Version history

0.6.2latest on PyPI · released Apr 29, 2026

Audit

Dependencies

ollama (the runtime)requiredThe Python library is a client for the Ollama runtime. Ollama must be separately installed and running — pip install alone is not sufficient.

Agent activity

57 hits · last 30 days

node

Amazon

OpenAI (training)

Resources

githubhttps://github.com/ollama/ollama-python ↗

packagehttps://pypi.org/project/ollama/ ↗

homepagehttps://ollama.com ↗