Skip to main content

Semantic Embeddings with instructions

POST 

/instructable_embed

Embeds the input using an instruction and a specific model. Resulting vectors that can be used for downstream tasks (e.g. semantic similarity) and models (e.g. classifiers). To obtain a valid model, use GET /model-settings.

Request

Query Parameters

    nice boolean

    Setting this to True, will signal to the API that you intend to be nice to other users by de-prioritizing your request below concurrent ones.

Body

required
    model stringrequired

    Name of the model to use. A model name refers to a model's architecture (number of parameters among others). The most recent version of the model is always used. The model output contains information as to the model version. To find out which models support semantic embeddings with instructions, please refer to the /model-settings endpoint.

    hosting Hostingnullable

    Possible values: [aleph-alpha, null]

    Optional parameter that specifies which datacenters may process the request. You can either set the parameter to "aleph-alpha" or omit it (defaulting to null).

    Not setting this value, or setting it to null, gives us maximal flexibility in processing your request in our own datacenters and on servers hosted with other providers. Choose this option for maximum availability.

    Setting it to "aleph-alpha" allows us to only process the request in our own datacenters. Choose this option for maximal data privacy.

    input object required

    This field is used to send prompts to the model. A prompt can either be a text prompt or a multimodal prompt. A text prompt is a string of text. A multimodal prompt is an array of prompt items. It can be a combination of text, images, and token ID arrays.

    In the case of a multimodal prompt, the prompt items will be concatenated and a single prompt will be used for the model.

    Tokenization:

    • Token ID arrays are used as as-is.
    • Text prompt items are tokenized using the tokenizers specific to the model.
    • Each image is converted into 144 tokens.
    oneOf

    string

    instruction stringrequired

    To further improve performance by steering the model, you can use instructions. Instructions can help the model understand nuances of your specific data and ultimately lead to embeddings that are more useful for your use-case. In this case, we aim to further increase the absolute difference between the cosine similarities. Instruction can also be the empty string.

    normalize boolean

    Default value: false

    Return normalized embeddings. This can be used to save on additional compute when applying a cosine similarity metric.

    contextual_control_threshold numbernullable

    If set to null, attention control parameters only apply to those tokens that have explicitly been set in the request. If set to a non-null value, we apply the control parameters to similar tokens as well. Controls that have been applied to one token will then be applied to all other tokens that have at least the similarity score defined by this parameter. The similarity score is the cosine similarity of token embeddings.

    control_log_additive boolean

    Default value: true

    true: apply controls on prompt items by adding the log(control_factor) to attention scores. false: apply controls on prompt items by (attention_scores - -attention_scores.min(-1)) * control_factor

Responses

OK

Schema
    model_version string

    model name and version (if any) of the used model for inference

    embedding float[]

    A list of floats that can be used to compare against other embeddings.

    num_tokens_prompt_total integer

    Number of tokens in the prompt.

    Tokenization:

    • Token ID arrays are used as as-is.
    • Text prompt items are tokenized using the tokenizers specific to the model.
    • Each image is converted into a fixed amount of tokens that depends on the chosen model.
Loading...