9router-embeddings
Access vector embeddings through a unified 9Router endpoint supporting OpenAI, Gemini, Mistral, Voyage, Nvidia, GitHub, and other embedding models. Configure your preferred provider and send text to receive embeddings in standard OpenAI format, with optional base64 encoding and dimension control for compatible models.
9router-embeddings generates vector embeddings from text across OpenAI, Gemini, Mistral, Voyage, and other providers.
AI-generated summary based on this skill's SKILL.md
Install
decolua/9router/9router-embeddings · repository language: JavaScript
git clone https://github.com/decolua/9router
cp -r 9router/skills/9router-embeddings ~/.claude/skills/9router-embeddingsnpx skillfed install decolua/9router/9router-embeddingsFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is 9router-embeddings and which providers does it support?
9router-embeddings is a unified embedding service that routes requests across multiple providers including OpenAI, Gemini, Mistral, Voyage, Nvidia, GitHub, and others. It exposes a single endpoint where you configure your preferred embedding model and send text to receive vector embeddings in standard OpenAI format, simplifying multi-provider integration.
How do I generate embeddings for RAG with 9router-embeddings?
9router-embeddings supports generating embeddings for RAG retrieval and knowledge base indexing. Configure your chosen provider (OpenAI, Gemini, Mistral, Voyage, or others), send your text through the unified endpoint, and receive embeddings ready for semantic search and similarity matching in your RAG pipeline.
Can 9router-embeddings batch embed multiple text strings at once?
Yes, 9router-embeddings supports batch embedding of multiple text strings with configurable dimensions and encoding options. You can send multiple texts in a single request and receive all embeddings together, with optional base64 encoding and dimension control for compatible models.
What embedding dimensions and encoding options does 9router-embeddings offer?
9router-embeddings provides configurable embedding dimensions for compatible models and supports base64 encoding for your vectors. These options let you optimize embedding size and format for your specific use case, whether you need full-dimension embeddings or compressed representations.
How does 9router-embeddings handle multi-provider embedding routing?
9router-embeddings acts as a router that abstracts provider differences behind a unified API. Select your embedding provider (OpenAI, Gemini, Mistral, Voyage, Nvidia, GitHub, or others), send text to the single endpoint, and receive embeddings in standard OpenAI format regardless of the underlying provider.
Is 9router-embeddings suitable for semantic search and similarity matching?
Yes, 9router-embeddings is designed for semantic search and similarity matching use cases. It generates vector embeddings that capture semantic meaning, enabling you to find similar texts and perform relevance-based retrieval across your indexed content using any of its supported embedding providers.
SKILL.md
rendered from the published skill — quoted content, verbatim
9Router — Embeddings
Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.
Discover
curl $NINEROUTER_URL/v1/models/embedding | jq '.data[].id'
# Per-model dimensions
curl "$NINEROUTER_URL/v1/models/info?id=openai/text-embedding-3-small"
Endpoint
POST $NINEROUTER_URL/v1/embeddings
| Field | Required | Notes |
|---|---|---|
model |
yes | from /v1/models/embedding |
input |
yes | string OR array of strings |
encoding_format |
no | float (default) / base64 |
dimensions |
no | OpenAI v3 only |
Examples
```bash curl -X POST $NINEROUTER_URL/v1/embeddings \ -H "Authorization: Bearer $NINEROUTER_KEY" \ -H "Content-Type: application/json" \ -d
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
skills/9router-embeddings/SKILL.md