Feature: Local Ollama / llama.cpp endpoint connector for Desktop JVM

Open
#10 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 2 days

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
55/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
kotlin, ollama
Domain
ai, desktop

Research direction

Start by locating LlmInferenceEngine and the Desktop JVM Settings implementation, then read how existing simulated and on-device providers are configured. Add a configurable local endpoint and model, handle an offline service, and write unit tests for serialization and mock response parsing. Done means both Ollama and llama-server endpoints can be configured and the tests cover the requested behavior.

Written by the indexing model from the issue text.

Description

enhancement help wanted
Summary

Currently, YAAN supports simulated and on-device SLM interfaces. For the Desktop JVM target, we should provide a configurable local inference connector allowing users to route prompts to a locally running Ollama instance (http://localhost:11434/api/generate) or llama-server without sending data over the internet.

Requirements
  • Add an OllamaClient / LocalLlmProvider implementing LlmInferenceEngine.
  • Allow configuring endpoint URL and model name (e.g. llama3.2:3b, qwen2.5:3b) in Settings.
  • Graceful error handling when local service is offline.
  • Unit tests verifying serialization and mock response parsing.
Dominant language
Kotlin
Stars
1
Forks
0
Avg merge
25m
Merged PRs (30d)
2

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from developmentwithyash/yaan

All issues in developmentwithyash/yaan

Similar issues

More Kotlin issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.