Enumeration ContextualElementType

Represents different types of contextual prompt elements that can be dynamically selected and integrated into prompts based on execution context. These elements allow for fine-grained adaptation of prompts.

Enumeration Members

SYSTEM_INSTRUCTION_ADDON: "system_instruction_addon"

Additional system-level instructions appended to base system prompt.

FEW_SHOT_EXAMPLE: "few_shot_example"

Dynamic few-shot examples selected based on context to guide the LLM.

BEHAVIORAL_GUIDANCE: "behavioral_guidance"

Behavioral guidance or tone adjustments for the persona.

TASK_SPECIFIC_INSTRUCTION: "task_specific_instruction"

Specific instructions or constraints related to the current task.

ERROR_HANDLING_GUIDANCE: "error_handling_guidance"

Instructions for handling errors or recovering from unexpected situations.

INTERACTION_STYLE_MODIFIER: "interaction_style_modifier"

Adjustments to the GMI's interaction style with the user.

DOMAIN_CONTEXT: "domain_context"

Domain-specific knowledge, facts, or context relevant to the current query.

ETHICAL_GUIDELINE: "ethical_guideline"

Ethical guidelines or safety instructions to ensure responsible AI behavior.

OUTPUT_FORMAT_SPEC: "output_format_spec"

Specifications for the desired output format (e.g., JSON, Markdown).

REASONING_PROTOCOL: "reasoning_protocol"

Instructions for specific reasoning protocols (e.g., chain-of-thought, tree-of-thought).

USER_PROMPT_AUGMENTATION: "user_prompt_augmentation"

Dynamic content to be injected directly into the user part of the prompt.

ASSISTANT_PROMPT_AUGMENTATION: "assistant_prompt_augmentation"

Content to be injected into the assistant part for few-shot or role-play setup.