51d029d960
- Re-introduction of EveAIAsset - Make translation services resistent for situation with and without current_event defined. - Ensure first question is asked in eveai_chat_client - Start of version 1.4.0 of TRAICIE_SELECTION_SPECIALIST
33 lines
1.1 KiB
Markdown
33 lines
1.1 KiB
Markdown
# CrewAI Specialist Implementation Guide
|
|
|
|
## Name Sensitivity
|
|
A lot of the required functionality to implement specialists has been automated. This automation is based on naming
|
|
conventions. So ... names of variables, attributes, ... needs to be precise, or you'll get problems.
|
|
|
|
## Base Class: CrewAIBaseSpecialistExecutor
|
|
|
|
Inherit your SpecialistExecutor class from the base class CrewAIBaseSpecialistExecutor
|
|
|
|
### Conventions
|
|
- tasks are referenced by using the lower case name of the configured task
|
|
- agents idem dito
|
|
|
|
### Specialise the __init__ method
|
|
|
|
- Define the crews you want to use in your specialist implementation
|
|
- Do other initialisations you require
|
|
- Call super
|
|
|
|
### Type and Typeversion properties
|
|
|
|
- Adapt the type and type_version properties to define the correct specialist. This refers to the actual specialist configuration!
|
|
|
|
### Implement _config_task_agents
|
|
|
|
This method links the tasks to the agents that will perform LLM interactions. You can call the method _add_task_agent
|
|
to link both.
|
|
|
|
### Implement _config_pydantic_outputs
|
|
|
|
This method links the tasks to their pydantic outputs, and their name in the state class.
|