skills.rest
eduardtomasek
eduardtomasekCOMMUNITY
Explore all skills by this author →
GitHub

grepai-embeddings-lmstudio

Configure LM Studio as the local embedding provider for GrepAI semantic code search.

Updated May 12, 2026
Search Tags:#semantic search#embeddings#configuration#code search#grepai#local llm#lm studio
One-click install
npx skills add https://github.com/eduardtomasek/codex-dev-stack --skill grepai-embeddings-lmstudio-eduardtomasek
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: grepai-embeddings-lmstudio
Source: https://github.com/eduardtomasek/codex-dev-stack/tree/main/skills/.agents/grepai-embeddings-lmstudio
Command: npx skills add https://github.com/eduardtomasek/codex-dev-stack --skill grepai-embeddings-lmstudio-eduardtomasek

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Setting up local embeddings for GrepAI semantic code search requires choosing a model, running an OpenAI-compatible server, and writing correct configuration, which is error-prone when done manually. This Skill walks through configuring LM Studio as the embedding provider so GrepAI can index and search code with fully local, private embeddings. ## Core Features & Use Cases - Step-by-step LM Studio setup: Covers downloading the app, pulling embedding models, and starting the local server on port 1234. - Ready-made GrepAI configurations: Provides YAML snippets for nomic-embed-text-v1.5, bge-small-en-v1.5, and bge-large-en-v1.5 with correct dimensions and endpoints. - Troubleshooting and comparison guidance: Addresses connection failures, missing models, slow embeddings, and compares LM Studio against Ollama for background-service reliability. - Use Case: A developer wants semantic code search over a private repository without sending code to a cloud API. They use this Skill to run nomic-embed-text-v1.5 in LM Studio and point GrepAI at http://localhost:1234. ## Quick Start Ask the assistant to configure GrepAI to use LM Studio with the nomic-embed-text-v1.5 model as its embedding provider.

Frequently Asked Questions about grepai-embeddings-lmstudio

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

FAQPage Schema
How do I configure GrepAI to use LM Studio for embeddings?▼

Set the embedder provider to lmstudio in .grepai/config.yaml with your model name and endpoint http://localhost:1234. First download an embedding model in LM Studio and start its local server from the Local Server tab.

Which embedding model should I use with LM Studio and GrepAI?▼

nomic-embed-text-v1.5 is recommended with 768 dimensions and a 260 MB size, balancing quality and speed. Use bge-small-en-v1.5 for faster indexing on smaller codebases or bge-large-en-v1.5 for maximum accuracy.

LM Studio vs Ollama for local embeddings, which is better?▼

LM Studio offers a graphical interface and visual model management but requires the app to stay running. Ollama runs as a background system service, making it more reliable for always-on embedding workloads.

Why does GrepAI fail to connect to the LM Studio server?▼

Connection refused errors mean the LM Studio server is not running. Open LM Studio, go to the Local Server tab, select your embedding model, and click Start Server, then verify with curl http://localhost:1234/v1/models.

Can LM Studio run as a headless server without the GUI?▼

LM Studio supports a CLI mode for starting the server without the desktop interface, though exact syntax depends on the LM Studio version. For production-style background services, migrating to Ollama is recommended.

Related Skills

Explore More Software Engineering Skills→
yoanbernabeuyoanbernabeu
18

grepai-quickstart

Install and initialize GrepAI for semantic code searching with Ollama.

Community
Basic
kochetkov-makochetkov-ma
30

brewcode:grepai

Manage grepai semantic code search with Ollama and bge-m3 embeddings.

Community
Intermediate
FutureMLS-LabFutureMLS-Lab
556

sglang-auto-benchmark

Search SGLang server configurations against throughput and latency objectives.

Official
Advanced
fgarofalo56fgarofalo56
6

localai

Run local AI models via a self-hosted OpenAI-compatible API.

Community
Advanced