skills.rest
yonatangross
yonatangrossCOMMUNITY
Explore all skills by this author →
𝕏@yonyonizGitHub

llm-integration

Integrate LLMs with function calling, SSE streaming, Ollama, and LoRA fine-tuning.

217|20|Updated Dec 31, 2025
Search Tags:#prompt engineering#llm#fine-tuning#streaming#function calling#ollama
One-click install
npx skills add https://github.com/yonatangross/orchestkit --skill llm-integration-yonatangross
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-integration
Source: https://github.com/yonatangross/orchestkit/tree/main/plugins/ork/skills/llm-integration
Command: npx skills add https://github.com/yonatangross/orchestkit --skill llm-integration-yonatangross

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and checklists (resource) components.

What problem does it solve?

This Skill provides comprehensive patterns and best practices for integrating Large Language Models (LLMs) into your applications, covering everything from basic API calls to advanced fine-tuning and local deployment.

Core Features & Use Cases

  • Function Calling: Implement robust tool use with strict schemas for reliable LLM-driven automation.
  • Streaming Responses: Deliver real-time LLM output via SSE for enhanced user experience.
  • Local Inference: Deploy and manage LLMs locally using Ollama for cost savings and privacy.
  • Fine-Tuning: Customize LLMs for specific tasks using LoRA/QLoRA and DPO alignment.
  • Use Case: Build an AI assistant that can search your knowledge base (function calling), provide instant chat responses (streaming), run locally on developer machines (local inference), and adapt to your company's specific jargon (fine-tuning).

Quick Start

Use the llm-integration skill to implement a FastAPI SSE endpoint for streaming LLM responses.

Frequently Asked Questions about llm-integration

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I implement LLM function calling with strict schemas for reliable automation?▼

LLM function calling with strict schemas enforces reliable tool use by validating LLM outputs against predefined JSON structures. This Skill provides patterns to implement robust tool-use automation, ensuring your LLM-driven workflows execute predictably without schema violations.

What's the best way to stream LLM responses via SSE using FastAPI?▼

Streaming LLM responses via SSE is best achieved by building a FastAPI endpoint that delivers real-time output. This Skill provides implementation patterns for Server-Sent Events streaming, enhancing user experience with instant token-by-token chat responses.

Can I run local LLM inference with Ollama for cost savings and privacy?▼

You can run local LLM inference using Ollama to ensure data privacy and reduce API costs. This Skill provides deployment and management patterns for local models, enabling offline AI assistant capabilities directly on developer machines.

How do I fine-tune an LLM with LoRA and DPO alignment for custom jargon?▼

Fine-tuning an LLM with LoRA and DPO alignment adapts the model to specific domain jargon efficiently. This Skill provides parameter-efficient fine-tuning patterns using LoRA, QLoRA, and Direct Preference Optimization to customize LLM behavior for your specific tasks.

What evaluation metrics and context management patterns are needed for production LLM applications?▼

Production LLM applications require robust context management to maintain conversation state and specific evaluation metrics to measure output quality. This Skill covers essential prompt engineering patterns, context window optimization, and evaluation frameworks for deployment.

Related Skills

Explore More Software Engineering Skills→
rawvegrawveg
40

ollama

Run and interact with local AI models via the Ollama API.

Community
Advanced
ScientiaCapitalScientiaCapital
1

model-deployment

Export fine-tuned models to GGUF and deploy with vLLM or Ollama.

Community
Advanced
machenjiemachenjie
4

ai-product-extension

Enforce engineering discipline for LLM, RAG, and agentic product changes.

Community
Advanced
granietgraniet
247

peft

Fine-tune 7B-70B LLMs with LoRA and QLoRA on consumer GPUs.

Community
Advanced