RS Infer
Server Endpoints

/embed

Create embeddings (TEI-compatible). Text-Embeddings-Inference compatible shape: `{"inputs": ["..."]}` → `[[f32, ...]]`. Uses the default embedding model (no `model` field). Always returns float arrays (no `base64` mode).

POST
/embed

Create embeddings (TEI-compatible). Text-Embeddings-Inference compatible shape: {"inputs": ["..."]} → [[f32, ...]]. Uses the default embedding model (no model field). Always returns float arrays (no base64 mode).

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

Response Body

application/json

application/json

application/json

curl -X POST "https://example.com/embed" \  -H "Content-Type: application/json" \  -d '{    "inputs": [      "string"    ]  }'
[  [    0.1  ]]

/v1/embeddings POST

Create embeddings (OpenAI/vLLM compatible). Accepts either a string, an array of strings, an array of token ids, or an array of token-id arrays. Returns one embedding per input in `data`, ordered by the `index` field. `dimensions` performs Matryoshka truncation and re-normalizes. `encoding_format: "base64"` returns each vector as a little-endian f32 blob.

/v1/rerank POST

Rerank documents against a query (vLLM/Jina/Cohere compatible). Scores every `(query, document)` pair, sorts by descending `relevance_score`, and truncates to `top_n`. Scoring modes are configured per model in the YAML — all modes except `logit` return scores in `(0, 1)`.