Does this skill require a running Ollama server?

Yes, the skill requires an Ollama server to be running and accessible, by default at http://localhost:11434, unless configured via the OLLAMA_HOST environment variable.

How does it handle conversation history?

The skill provides a clean Pythonic pattern for multi-turn conversations by appending messages to a list, which is then passed back to the chat API.

Is embedding generation supported?

Yes, the skill provides documentation and examples for generating vector embeddings from text input using any compatible Ollama model.

Can I use this skill for streaming responses?

Yes, it includes standard implementation patterns for both non-streaming and streaming responses for both text generation and chat completions.

Does it support model management commands?

Absolutely. You can list available models, check which models are currently running in VRAM, pull new models, and delete or copy existing ones.

Ollama Python Integration

Name: Ollama Python Integration
Author: atrawog

byatrawog

0•

데이터 과학 및 ML

Integrates local LLM inference into Python applications using the official Ollama library for text generation, chat, and model management.

This skill enables Claude to interact seamlessly with the official Ollama Python library, providing a high-level interface for local large language model (LLM) orchestration. It covers essential operations including chat completions, text generation, and embeddings, alongside comprehensive model management tasks like pulling, listing, and deleting models. Ideal for developers building AI-powered Python applications, it simplifies the process of managing local model lifecycles and implementing multi-turn conversations with production-ready patterns like streaming and robust error handling.

주요 기능

01Comprehensive model lifecycle management including pulling and copying

020 GitHub stars

03Vector embedding generation for local RAG and semantic search

04Built-in health checks and performance metric tracking

05Seamless text generation and multi-turn chat completions

06Real-time streaming response handling for interactive apps

사용 사례

01Automating model orchestration and environment setup for local LLMs

02Building local AI-powered Python applications and agents

03Generating text embeddings for semantic search or local RAG pipelines

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add atrawog/bazzite-ai-plugins ollama

For use in Claude.ai and ChatGPT

Download Skill