Concepts

Here are the core concepts that we have built Composable around.

Prompt Templates

Prompt Templates are the core concept of Composable. They are the building blocks of prompts and are used to create prompts. Prompts are then assembled to define a prompt for a task (Interaction).

Name
JS Template
Description
It's a Javascript Template engine, running in a jailed environment. You can use standard javascript string replacement syntax (${var}), as well as control blocks (for, if, else, etc.), and array functions map, reduce, filter, etc. It needs to retur a string.
Name
Plain Text
Description
Simple plain text format, with no variable replacement. Useful for application context or safety prompts.

Interactions

Interactions are the core concept of Composable. They define the tasks the LLM are requested to perform.

An interaction is defined by the following main components:

Name
Name
Description
The name of the interaction.
Name
Description
Description
A description of the interaction.
Name
Prompt Segments
Description
A list of prompts templates to be rendered as part of the final prompt.
Name
Schema
Description
JSON Schema requested from the generative model for the response. It will be used to validate the response as well.
Name
Configuration
Description
Environment and Model to execute the interaction on, and execution parameters.

Runs

Runs are the execution of an interaction, it is both the request to and the response from the generative model.

Runs have the following statuses:

Name
created
Description
The run has been created, but not yet started. Typically the case when waiting for the streaming start from the client.
Name
processing
Description
The run is currently executing.
Name
completed
Description
The run has completed successfully.
Name
failed
Description
The run has failed. The failure reason is in the field error.

Environments

Environments are the execution runtime environment for the generative model.

We currently support the following environments:

Name
OpenAI
Description
OpenAI are supported. This is where you find notably GPT3.5 and GPT4.
Name
AWS Bedrock
Description
AWS Bedrock are supported. You can run Anthropic Claude, Cohere, LLama2, A21's model, AWS Titan, and more natively.
Name
Replicate
Description
Replicate are supported. This is where you can find Llama2 for example and many others.
Name
Huggingface
Description
Huggingface Inference Endpoints are supported. This is where you can find GPT2, Llama2, etc.