<- References   Go to ToC      AI Modules ->

1. Technical Specification 2. Reference Software 3. Conformance Testing 4. Performance Assessment

1. Technical Specification

Technical Specification: Multimodal Conversation (MPAI-HMC) V2.0 assumes that workflows are based on Technical Specification: AI Framework (MPAI-AIF) V2.1 specifying the standard AI Framework (AIF) that enables initialisation, dynamic configuration, execution, and control of AI Workflows (AIW) composed of interconnected AI Modules (AIM).

Table 1 provides the full list of AIWs specified by MPAI-HMC V2.0 with links to the pages dedicated to each AI Workflow which includes its function, reference model, Input/Output Data, Functions of AIMs, Input/Output Data of AIMs, and links to the AIW-related AIW, AIMs, and JSON metadata.

All AI-Workflows specified by MPAI-HMC V2.0 are superseded by those specified by previous MPAI-MMC specifications which can still be used if their version is explicitly indicated.

Table 1 – AIWs of MPAI-HMC V2.0

Acronym Title JSON
MPAI-HMC Communicating Entities in Context X

2. Reference Software

As a rule, MPAI provides Reference Software implementing the Technical Specification released with the BSD-3-Clause licence and the following disclaimers:

  1. The purpose of the Reference Software is to demonstrate a working Implementation of an AIW, not to provide a ready-to-use product.
  2. MPAI disclaims the suitability of the Software for any other purposes that those of the MPAI-HMC Standard and does not guarantee that it is secure.
  3. Users shall verify that they have the right to use any third-party software required by the Reference Software Implementation.
  4. Users should note that the Reference Software Implementation may require the acceptance of licences from third-party repositories.

Note that, at this stage, the MPAI-HMC AIW is only partly implemented.

3. Conformance Testing

An implementation of an AI Workflow conforms with MPAI-HMC if it accepts as input and produces as output Data and/or Data Objects (Data and its Qualifier) conforming with those specified or referenced by MPAI-HMC.

The Conformance of an instance of a Data is to be expressed by a sentence like “Data validates against the Data Type Schema”. This means that:

  • Any Data Sub-Type is as indicated in the Qualifier.
  • The Data Format is indicated by the Qualifier.
  • Any File and/or Stream have the Formats indicated by the Qualifier.
  • Any Attribute of the Data is of the type or validates against the Schema specified in the Qualifier.

The method to Test the Conformance of a Data or Data Object instance is specified in the Data Types chapter.

4. Performance Assessment

Performance is multidimensional because it can have various connotations, and the Performance Assessment Specification should provide methods to measure how well an AIW performs its function, using a metric that depends on the nature of the function, such as:

  1. Quality: the Performance of a Communicating Entities in Context AIW can measure how well the AIW responds to a question.
  2. Bias: Performance of a Communicating Entities in Context AIW can measure the quality of responses in dependence of the type of  message received.
  3. Legal compliance: the Performance of an AIW can measure the compliance of the AIW to a regulation, e.g., the European AI Act.
  4. Ethical compliance: the Performance Assessment of an AIW can measure the compliance of an AIW to a target ethical standard.

Note that, at this stage, only some AIMs of the MPAI-HMC AIW include a Performance Assessment Specification.

<- References   Go to ToC      AI Modules ->