skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
yoanbernabeu/grepai-skills560 installs

grepai-embeddings-openai

Configure OpenAI as embedding provider for GrepAI. Use this skill for high-quality cloud embeddings.

How do I install this agent skill?

npx skills add https://github.com/yoanbernabeu/grepai-skills --skill grepai-embeddings-openai
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    This skill provides documentation and configuration examples for using OpenAI embeddings with GrepAI. It correctly identifies security risks associated with API key management and promotes industry-standard best practices such as using environment variables and excluding secrets from version control.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

  • Runlayerwarn

    1/1 file flagged

  • ZeroLeakspass

    1 finding · Score: 82/100

What does this agent skill do?

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

AspectDetails
✅ QualityState-of-the-art embeddings
✅ SpeedFast, no local compute needed
✅ ScalabilityHandles any codebase size
⚠️ PrivacyCode sent to OpenAI servers
⚠️ CostPay per token
⚠️ InternetRequires 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

# .grepai/config.yaml
embedder:
  provider: openai
  model: text-embedding-3-small

Set the environment variable:

export OPENAI_API_KEY="sk-..."

With no api_key and no endpoint, grepai uses the official endpoint (https://api.openai.com/v1) and reads OPENAI_API_KEY from the environment.

Note: grepai does not expand variables in config.yaml. api_key: ${OPENAI_API_KEY} is sent as the literal string ${OPENAI_API_KEY}; leave api_key out to use the environment variable.

With Parallel Processing

embedder:
  provider: openai
  model: text-embedding-3-small
  parallelism: 8  # Concurrent requests for speed

Direct API Key (Not Recommended)

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)

PropertyValue
Dimensions1536
Price$0.00002 / 1K tokens
QualityVery high
SpeedFast

Best for: Most use cases, good balance of cost/quality.

embedder:
  provider: openai
  model: text-embedding-3-small

text-embedding-3-large

PropertyValue
Dimensions3072
Price$0.00013 / 1K tokens
QualityHighest
SpeedFast

Best for: Maximum accuracy, cost not a concern.

embedder:
  provider: openai
  model: text-embedding-3-large
  dimensions: 3072

Dimension Reduction

You can reduce dimensions to save storage:

embedder:
  provider: openai
  model: text-embedding-3-large
  dimensions: 1024  # Reduced from 3072

Model Comparison

ModelDimensionsCost/1K tokensQuality
text-embedding-3-small1536$0.00002⭐⭐⭐⭐
text-embedding-3-large3072$0.00013⭐⭐⭐⭐⭐

Cost Estimation

Approximate costs per 1000 source files:

Codebase SizeChunksSmall ModelLarge 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:

embedder:
  provider: openai
  model: text-embedding-3-small
  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:

TierRPMTPM
Free3150,000
Tier 15001,000,000
Tier 25,0005,000,000

GrepAI handles rate limiting automatically with adaptive backoff.

Environment Variables

Setting the API Key

macOS/Linux:

# In ~/.bashrc, ~/.zshrc, or ~/.profile
export OPENAI_API_KEY="sk-..."

Windows (PowerShell):

$env:OPENAI_API_KEY = "sk-..."
# Or permanently
[System.Environment]::SetEnvironmentVariable('OPENAI_API_KEY', 'sk-...', 'User')

grepai does not read .env files: the variable must be exported in the shell (or in the env block of your MCP client config) that starts grepai.

Environment Keys Only Go to the Official Endpoint

Since grepai v1.2.0, a key read from the environment is sent only to https://api.openai.com. With any other endpoint (Azure, LiteLLM, vLLM, a proxy…), set embedder.api_key in .grepai/config.yaml (or ~/.grepai/workspace.yaml for a workspace). If api_key is empty while OPENAI_API_KEY is exported, grepai stops with an error naming the variable and the endpoint, instead of sending the key.

This protects you from a .grepai/config.yaml committed in a cloned repository that points endpoint at a server controlled by someone else.

Azure OpenAI

For Azure-hosted OpenAI (or any OpenAI-compatible API):

embedder:
  provider: openai
  model: your-deployment-name
  endpoint: https://your-resource.openai.azure.com/openai/v1
  api_key: your-azure-key  # required: OPENAI_API_KEY is never sent to a custom endpoint

grepai sends POST {endpoint}/embeddings with an Authorization: Bearer header. Keep a config holding a key out of version control.

Local OpenAI-Compatible Servers (vLLM, TEI…)

The openai provider always requires a non-empty key, so a server that needs no authentication still needs a placeholder. Without one, grepai stops with OpenAI API key not set (no variable exported) or with the custom endpoint error (OPENAI_API_KEY exported):

embedder:
  provider: openai
  model: your-model
  endpoint: http://localhost:8000/v1
  api_key: unused

Security Best Practices

  1. Use environment variables with the official endpoint: Never hardcode API keys for api.openai.com
  2. Custom endpoints: The key must be in api_key; never commit that config
  3. Rotate keys: Regularly rotate API keys
  4. Monitor usage: Check OpenAI dashboard for unexpected usage
  5. Review code: Ensure sensitive code isn't being indexed

Common Issues

❌ Problem: 401 Unauthorized ✅ Solution: Check API key is correct and environment variable is set:

echo $OPENAI_API_KEY

❌ Problem: API keys from the environment (OPENAI_API_KEY) are only sent to the official endpoint ... not to the custom endpoint ... ✅ Solution: You use a custom endpoint. Set embedder.api_key in the config (api_key: unused for a server without authentication).

❌ Problem: 429 Rate limit exceeded ✅ Solution: Reduce parallelism or upgrade OpenAI tier:

embedder:
  parallelism: 2  # Lower value

❌ Problem: High costs ✅ Solutions:

  • Use text-embedding-3-small instead of large
  • Reduce dimension size
  • Add more ignore patterns to reduce indexed files

❌ Problem: Slow indexing ✅ Solution: Increase parallelism:

embedder:
  parallelism: 8

❌ Problem: Privacy concerns ✅ Solution: Use Ollama for local embeddings instead

Migrating from Ollama to OpenAI

  1. Update configuration:
embedder:
  provider: openai
  model: text-embedding-3-small
  1. Delete existing index:
rm .grepai/index.gob
  1. Re-index:
grepai watch

Important: You cannot mix embeddings from different models/providers.

Output Format

Successful OpenAI configuration:

✅ OpenAI Embedding Provider Configured

   Provider: OpenAI
   Model: text-embedding-3-small
   Dimensions: 1536
   Parallelism: 4
   API Key: sk-...xxxx (from environment)

   Estimated cost for this codebase:
   - Files: 245
   - Chunks: ~1,200
   - Cost: ~$0.02

   Note: Code will be sent to OpenAI servers.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/yoanbernabeu/grepai-skills/grepai-embeddings-openai">View grepai-embeddings-openai on skillZs</a>