Metadata-Version: 2.4
Name: neurocore-skill-ollama
Version: 0.1.0
Summary: Local Ollama text-generation skill for NeuroCore
Author: NeuroCore Contributors
License-Expression: Apache-2.0
Keywords: ai,llm,local,neurocore,ollama,skill
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Typing :: Typed
Requires-Python: >=3.13
Requires-Dist: httpx>=0.27
Requires-Dist: neurocore-ai>=0.2.0
Provides-Extra: dev
Requires-Dist: mypy>=1.8; extra == 'dev'
Requires-Dist: pytest-asyncio>=0.24; extra == 'dev'
Requires-Dist: pytest>=9.0.2; extra == 'dev'
Requires-Dist: ruff>=0.8; extra == 'dev'
Description-Content-Type: text/markdown

# neurocore-skill-ollama

Direct text generation against a local [Ollama](https://ollama.com) server.

```bash
pip install neurocore-skill-ollama
ollama serve & ; ollama pull llama3.2
```

```yaml
components:
  - name: generate
    type: ollama
    config:
      model: llama3.2
      system: "You are concise."
flow:
  type: sequential
  steps:
    - component: generate
```

Reads `prompt`; writes `ollama_response` (the generated text).

> For chat-style LLM access from skills with `requires_llm=True`, prefer
> NeuroCore's built-in `ollama` **provider** (`llm.provider: ollama`). This
> skill is a provider-free direct call to `/api/generate`.
