embeddings_create
Generate dense vector embeddings for semantic search, similarity comparison, and RAG. Converts text strings into base64-encoded vectors for retrieval applications.
Instructions
Generate dense vector embeddings for one or more text strings (POST /v1/embeddings). Use for semantic search, similarity comparison, or retrieval-augmented generation (RAG). Returns vectors in base64 format.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"input": "<input>"
},
"name": "embeddings_create"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | Text string or array of strings to embed. | |
| model | No | Embedding model. '0.6b' is faster and cheaper; '4b' produces higher quality vectors. | pplx-embed-v1-0.6b |
| dimensions | No | Output vector dimensions (128-2560). Defaults to model's native dimensionality. | |
| encoding_format | No | Encoding format for the returned embedding vectors. |