Grepai Config Reference
Look up every GrepAI .grepai/config.yaml option—embedder, storage, watch paths—when tuning semantic search for your stack.
Overview
grepai-config-reference is an agent skill most often used in Build (also Operate infra tuning) that documents all GrepAI .grepai/config.yaml options for embedders, storage, and watch behavior.
Install
npx skills add https://github.com/yoanbernabeu/grepai-skills --skill grepai-config-referenceWhat is this skill?
- Full schema for embedder providers: ollama, openai, lmstudio with model and endpoint fields
- Documented dimension defaults (e.g. nomic-embed-text 768, text-embedding-3-small 1536)
- Vector backend and watch-path sections for project-scoped indexing behavior
- Use when optimizing latency, cost, or troubleshooting misconfigured endpoints
- Config lives at /your/project/.grepai/config.yaml with version: 1
- Embedder providers documented: ollama, openai, lmstudio
- Example dimensions: 768 (nomic-embed-text), 1536 (text-embedding-3-small), 3072 (text-embedding-3-large)
Adoption & trust: 490 installs on skills.sh; 17 GitHub stars; 3/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You are editing GrepAI settings blind and keep breaking indexing because provider models, dimensions, or endpoints do not match what the daemon expects.
Who is it for?
Builders self-hosting embeddings (Ollama/LM Studio) or mixing OpenAI APIs who need a single schema cheat sheet in the agent session.
Skip if: Users who only need a one-command quickstart with defaults and no customization, or teams not using GrepAI at all.
When should I use this skill?
Understanding all available configuration options, optimizing GrepAI for your use case, troubleshooting configuration issues, or setting up advanced configurations.
What do I get? / Deliverables
A correctly structured config.yaml aligned with your embedder and vector backend so watch and search commands run without silent mismatches.
- Validated config.yaml field choices documented in session
- Troubleshooting notes tied to schema sections
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Configuration is first touched while wiring agent search during Build, but the same file is revisited when optimizing or fixing production-adjacent indexing behavior. agent-tooling is the canonical shelf because the YAML directly controls embeddings and vector backends that agents query.
Where it fits
Pick text-embedding-3-small versus a local Ollama model before the first full-repo watch.
Adjust endpoint URLs after moving the embedder from laptop Docker to a LAN inference box.
How it compares
Structured config reference for the GrepAI CLI stack—not a generic dotenv or Docker compose guide.
Common Questions / FAQ
Who is grepai-config-reference for?
Solo developers operating GrepAI who need exhaustive YAML documentation for embedders, models, endpoints, and storage when tuning semantic code search.
When should I use grepai-config-reference?
During Build when creating or editing .grepai/config.yaml; during Operate when troubleshooting indexing after provider or dimension changes; whenever optimizing cost or latency for embeddings.
Is grepai-config-reference safe to install?
It is read-only reference material; still review the Security Audits panel on this page and avoid pasting live API keys into chat logs.
Workflow Chain
Then invoke: grepai watch daemon
SKILL.md
READMESKILL.md - Grepai Config Reference
# GrepAI Configuration Reference This skill provides a complete reference for all GrepAI configuration options in `.grepai/config.yaml`. ## When to Use This Skill - Understanding all available configuration options - Optimizing GrepAI for your specific use case - Troubleshooting configuration issues - Setting up advanced configurations ## Configuration File Location ``` /your/project/.grepai/config.yaml ``` ## Complete Configuration Schema ```yaml version: 1 # ═══════════════════════════════════════════════════════════════ # EMBEDDER CONFIGURATION # Converts code text into vector embeddings # ═══════════════════════════════════════════════════════════════ embedder: # Provider: ollama | openai | lmstudio provider: ollama # Model name (depends on provider) # Ollama: nomic-embed-text, bge-m3, mxbai-embed-large # OpenAI: text-embedding-3-small, text-embedding-3-large # LM Studio: nomic-embed-text-v1.5, bge-small-en-v1.5 model: nomic-embed-text # API endpoint URL # Ollama default: http://localhost:11434 # LM Studio default: http://localhost:1234 # OpenAI: uses official API endpoint: http://localhost:11434 # Vector dimensions (auto-detected if omitted) # nomic-embed-text: 768 # text-embedding-3-small: 1536 # text-embedding-3-large: 3072 dimensions: 768 # API key (for OpenAI, supports env vars) api_key: ${OPENAI_API_KEY} # Parallel requests (OpenAI only, for speed) parallelism: 4 # ═══════════════════════════════════════════════════════════════ # STORE CONFIGURATION # Where vector embeddings are stored # ═══════════════════════════════════════════════════════════════ store: # Backend: gob | postgres | qdrant backend: gob # PostgreSQL configuration (when backend: postgres) postgres: dsn: postgres://user:password@localhost:5432/grepai # Qdrant configuration (when backend: qdrant) qdrant: endpoint: localhost port: 6334 use_tls: false api_key: your-qdrant-api-key # Optional # ═══════════════════════════════════════════════════════════════ # CHUNKING CONFIGURATION # How code files are split for embedding # ═══════════════════════════════════════════════════════════════ chunking: # Tokens per chunk (smaller = more precise, larger = more context) # Recommended: 256-1024 size: 512 # Overlap between chunks (preserves context at boundaries) # Recommended: 10-20% of size overlap: 50 # ═══════════════════════════════════════════════════════════════ # WATCH CONFIGURATION # File watching daemon settings # ═══════════════════════════════════════════════════════════════ watch: # Debounce delay in milliseconds # Groups rapid file changes together debounce_ms: 500 # ═══════════════════════════════════════════════════════════════ # TRACE CONFIGURATION # Call graph analysis settings # ═══════════════════════════════════════════════════════════════ trace: # Extraction mode: fast | precise # fast: Uses regex, no dependencies, faster # precise: Uses tree-sitter AST parsing, more accurate mode: fast # Languages to analyze for call graphs enabled_languages: - .go - .js - .ts - .jsx - .tsx - .py - .php - .c - .h - .cpp - .hpp - .cc - .cxx - .rs - .zig - .cs - .pas - .dpr # Patterns to exclude from trace analysis exclude_patterns: - "*_test.go" - "*.spec.ts" - "*.test.js" # ═══════════════════════════════════════════════════════════════ # SEARCH CONFIGURATION # Search result scoring and ranking # ═══════════════════════════════════════════════════════════════ search: # Score boosting configuration boost: enabled: true # Reduce scores for certain paths penalties: - pattern: /tests/ factor: 0.5 - pattern: _test. factor: 0.5 -