Create k-shot example selector using example list and embeddings.
Reshuffles examples dynamically based on Max Marginal Relevance.
from_examples(
cls,
examples: list[dict],
embeddings: Embeddings,
vectorstore_cls: type[VectorStore],
k: int = 4,
input_keys: list[str] | None = None,
fetch_k: int = 20,
example_keys: list[str] | None = None,
vectorstore_kwargs: dict | None = None,
**vectorstore_cls_kwargs: Any = {}
) -> MaxMarginalRelevanceExampleSelector| Name | Type | Description |
|---|---|---|
examples* | list[dict] | List of examples to use in the prompt. |
embeddings* | Embeddings | An initialized embedding API interface, e.g. OpenAIEmbeddings(). |
vectorstore_cls* | type[VectorStore] | A vector store DB interface class, e.g. FAISS. |
k | int | Default: 4Number of examples to select. |
fetch_k | int | Default: 20Number of |
input_keys | list[str] | None | Default: NoneIf provided, the search is based on the input variables instead of all variables. |
example_keys | list[str] | None | Default: NoneIf provided, keys to filter examples to. |
vectorstore_kwargs | dict | None | Default: NoneExtra arguments passed to similarity_search function
of the |
vectorstore_cls_kwargs | Any | Default: {}optional kwargs containing url for vector store |