Grepai Embeddings Openai
Point GrepAI at OpenAI embeddings when you want cloud-quality vectors without running a local embed server.
Overview
GrepAI Embeddings OpenAI is an agent skill for the Build phase that configures OpenAI as GrepAI’s cloud embedding provider via .grepai/config.yaml.
Install
npx skills add https://github.com/yoanbernabeu/grepai-skills --skill grepai-embeddings-openaiWhat is this skill?
- OpenAI embedder block for .grepai/config.yaml with env-based API key
- Models such as text-embedding-3-small with optional parallelism for concurrent requests
- Documents quality, speed, scalability vs privacy, cost, and internet dependency
- Team-friendly shared infrastructure without local embedding compute
- Prerequisites: OpenAI API key and billing-enabled account
- Optional parallelism: 8 concurrent embedding requests in config example
Adoption & trust: 1 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 want GrepAI semantic search with top-tier embeddings but do not want to host or tune a local embedding server on your laptop.
Who is it for?
Indie devs or tiny teams indexing large repos who accept sending code to OpenAI in exchange for quality, speed, and zero local embed ops.
Skip if: Air-gapped or strict data-residency codebases, or builders who refuse API spend and on-prem privacy requirements.
When should I use this skill?
You need highest-quality GrepAI embeddings, shared team setup, no local embed server, and accept OpenAI privacy/cost tradeoffs.
What do I get? / Deliverables
You get a working OpenAI-backed GrepAI embedder configuration—with optional parallelism—so indexing and agent retrieval use cloud vectors you can share on a team setup.
- .grepai/config.yaml embedder provider openai block
- OPENAI_API_KEY environment setup
- Tuned parallelism settings for large codebases
Recommended Skills
Journey fit
Embedding provider wiring is build-time agent-tooling setup that makes semantic code search work in your repo workflow. Integrations covers third-party APIs and config files like .grepai/config.yaml and OPENAI_API_KEY.
How it compares
Integration config for GrepAI’s embedder—not a standalone RAG framework or MCP server.
Common Questions / FAQ
Who is grepai-embeddings-openai for?
Developers using GrepAI who need high-quality cloud embeddings and are comfortable managing an OpenAI API key and token billing.
When should I use grepai-embeddings-openai?
During Build integrations when you are wiring agent-tooling search—after choosing GrepAI and before you index the repo for Claude Code, Cursor, or Codex workflows.
Is grepai-embeddings-openai safe to install?
The skill instructs sending codebase content to OpenAI when embeddings run—review the Security Audits panel on this Prism page and your org’s data policy before enabling it.
SKILL.md
READMESKILL.md - Grepai Embeddings Openai
# GrepAI Embeddings with OpenAI This skill covers using OpenAI's embedding API with GrepAI for high-quality, cloud-based embeddings. ## When to Use This Skill - Need highest quality embeddings - Team environment with shared infrastructure - Don't want to manage local embedding server - Willing to trade privacy for quality/convenience ## Considerations | Aspect | Details | |--------|---------| | ✅ **Quality** | State-of-the-art embeddings | | ✅ **Speed** | Fast, no local compute needed | | ✅ **Scalability** | Handles any codebase size | | ⚠️ **Privacy** | Code sent to OpenAI servers | | ⚠️ **Cost** | Pay per token | | ⚠️ **Internet** | Requires connection | ## Prerequisites 1. OpenAI API key 2. Billing enabled on OpenAI account Get your API key at: https://platform.openai.com/api-keys ## Configuration ### Basic Configuration ```yaml # .grepai/config.yaml embedder: provider: openai model: text-embedding-3-small api_key: ${OPENAI_API_KEY} ``` Set the environment variable: ```bash export OPENAI_API_KEY="sk-..." ``` ### With Parallel Processing ```yaml embedder: provider: openai model: text-embedding-3-small api_key: ${OPENAI_API_KEY} parallelism: 8 # Concurrent requests for speed ``` ### Direct API Key (Not Recommended) ```yaml embedder: provider: openai model: text-embedding-3-small api_key: sk-your-api-key-here # Avoid committing secrets! ``` **Warning:** Never commit API keys to version control. ## Available Models ### text-embedding-3-small (Recommended) | Property | Value | |----------|-------| | Dimensions | 1536 | | Price | $0.00002 / 1K tokens | | Quality | Very high | | Speed | Fast | **Best for:** Most use cases, good balance of cost/quality. ```yaml embedder: provider: openai model: text-embedding-3-small ``` ### text-embedding-3-large | Property | Value | |----------|-------| | Dimensions | 3072 | | Price | $0.00013 / 1K tokens | | Quality | Highest | | Speed | Fast | **Best for:** Maximum accuracy, cost not a concern. ```yaml embedder: provider: openai model: text-embedding-3-large dimensions: 3072 ``` ### Dimension Reduction You can reduce dimensions to save storage: ```yaml embedder: provider: openai model: text-embedding-3-large dimensions: 1024 # Reduced from 3072 ``` ## Model Comparison | Model | Dimensions | Cost/1K tokens | Quality | |-------|------------|----------------|---------| | `text-embedding-3-small` | 1536 | $0.00002 | ⭐⭐⭐⭐ | | `text-embedding-3-large` | 3072 | $0.00013 | ⭐⭐⭐⭐⭐ | ## Cost Estimation Approximate costs per 1000 source files: | Codebase Size | Chunks | Small Model | Large Model | |---------------|--------|-------------|-------------| | Small (100 files) | ~500 | $0.01 | $0.06 | | Medium (1000 files) | ~5,000 | $0.10 | $0.65 | | Large (10000 files) | ~50,000 | $1.00 | $6.50 | **Note:** Costs are one-time for initial indexing. Updates only re-embed changed files. ## Optimizing for Speed ### Parallel Requests GrepAI v0.24.0+ supports adaptive rate limiting and parallel requests: ```yaml embedder: provider: openai model: text-embedding-3-small api_key: ${OPENAI_API_KEY} parallelism: 8 # Adjust based on your rate limit tier ``` Parallelism recommendations: - **Tier 1 (Free):** 1-2 - **Tier 2:** 4-8 - **Tier 3+:** 8-16 ### Batching GrepAI automatically batches chunks for efficient API usage. ## Rate Limits OpenAI has rate limits based on your account tier: | Tier | RPM | TPM | |------|-----|-----| | Free | 3 | 150,000 | | Tier 1 | 500 | 1,000,000 | | Tier 2 | 5,000 | 5,000,000 | GrepAI handles rate limiting automatically with adaptive backoff. ## Environment Variables ### Setting the API Key **macOS/Linux:** ```bash # In ~/.bashrc, ~/.zshrc, or ~/.profile export OPENAI_API_KEY="sk-..." ``` **Windows (PowerShell):** ```powershell $env:OPENAI_API_K