responses
Process independent strings via the unified Algenta response envelope to return token counts, embeddings, or generated text per selected model. Stateless single-turn requests with no conversation storage.
Instructions
Run the unified Algenta response envelope over one string or a list of independent strings, each processed as its own single-turn request. The output item per input depends on the model: tokenization models (default text.tokenizer) return the input's tokens and token_count; embedding models return a deterministic vector of dimensions length; provider-backed chat models advertised by list_models return generated text. Use chat_completions for an ordered multi-role transcript and embeddings when you specifically need vectors. Stateless and non-destructive: no conversation state is created, continued, or stored by this tool. An unsupported model id fails with model_not_supported.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | One string, or a list of independent strings each processed as its own single-turn request. | |
| model | No | Model id from list_models; selects the output item type. | text.tokenizer |
| dimensions | No | Embedding vector length when the selected model produces embeddings. |