Module example_selectors

Example selectors for FerricLink Core.

Example selector implements logic for selecting examples to include them in prompts. This allows us to select examples that are most relevant to the input.

Example selectors are crucial for:

• Few-shot learning and prompting
• Dynamic prompt construction
• Semantic similarity-based example selection
• Length-based prompt management
• Max Marginal Relevance algorithms

Structs

LengthBasedExampleSelector

Select examples based on length.

MaxMarginalRelevanceExampleSelector

Select examples based on Max Marginal Relevance (MMR).

SemanticSimilarityExampleSelector

Select examples based on semantic similarity using vector stores.

Traits

BaseExampleSelector

Interface for selecting examples to include in prompts.

Functions

sorted_values

Utility function to return values in a dictionary sorted by key.

Type Aliases

Example

A type alias for example data