Example Selector

Logic for selecting examples to include in prompts.

pydantic model langchain.prompts.example_selector.LengthBasedExampleSelector

Select examples based on length.

Validators

• calculate_example_text_lengths » example_text_lengths

field example_prompt: langchain.prompts.prompt.PromptTemplate [Required]

Prompt template used to format the examples.

field examples: List[dict] [Required]

A list of the examples that the prompt template expects.

field get_text_length: Callable[[str], int] = <function _get_length_based>

Function to measure prompt length. Defaults to word count.

field max_length: int = 2048

Max length for the prompt, beyond which examples are cut.

add_example(example: Dict[str, str]) → None

Add new example to list.

select_examples(input_variables: Dict[str, str]) → List[dict]

Select which examples to use based on the input lengths.

pydantic model langchain.prompts.example_selector.MaxMarginalRelevanceExampleSelector

ExampleSelector that selects examples based on Max Marginal Relevance.

This was shown to improve performance in this paper: https://arxiv.org/pdf/2211.13892.pdf

field fetch_k: int = 20

Number of examples to fetch to rerank.

classmethod from_examples(examples: List[dict], embeddings: langchain.embeddings.base.Embeddings, vectorstore_cls: Type[langchain.vectorstores.base.VectorStore], k: int = 4, input_keys: Optional[List[str]] = None, fetch_k: int = 20, **vectorstore_cls_kwargs: Any) → langchain.prompts.example_selector.semantic_similarity.MaxMarginalRelevanceExampleSelector

Create k-shot example selector using example list and embeddings.

Reshuffles examples dynamically based on query similarity.

Parameters

• examples – List of examples to use in the prompt.

• embeddings – An iniialized embedding API interface, e.g. OpenAIEmbeddings().

• vectorstore_cls – A vector store DB interface class, e.g. FAISS.

• k – Number of examples to select

• input_keys – If provided, the search is based on the input variables instead of all variables.

• vectorstore_cls_kwargs – optional kwargs containing url for vector store

Returns

The ExampleSelector instantiated, backed by a vector store.

select_examples(input_variables: Dict[str, str]) → List[dict]

Select which examples to use based on semantic similarity.

pydantic model langchain.prompts.example_selector.SemanticSimilarityExampleSelector

Example selector that selects examples based on SemanticSimilarity.

field example_keys: Optional[List[str]] = None

Optional keys to filter examples to.

field input_keys: Optional[List[str]] = None

Optional keys to filter input to. If provided, the search is based on the input variables instead of all variables.

field k: int = 4

Number of examples to select.

field vectorstore: langchain.vectorstores.base.VectorStore [Required]

VectorStore than contains information about examples.

add_example(example: Dict[str, str]) → str

Add new example to vectorstore.

classmethod from_examples(examples: List[dict], embeddings: langchain.embeddings.base.Embeddings, vectorstore_cls: Type[langchain.vectorstores.base.VectorStore], k: int = 4, input_keys: Optional[List[str]] = None, **vectorstore_cls_kwargs: Any) → langchain.prompts.example_selector.semantic_similarity.SemanticSimilarityExampleSelector

Create k-shot example selector using example list and embeddings.

Reshuffles examples dynamically based on query similarity.

Parameters

• examples – List of examples to use in the prompt.

• embeddings – An initialized embedding API interface, e.g. OpenAIEmbeddings().

• vectorstore_cls – A vector store DB interface class, e.g. FAISS.

• k – Number of examples to select

• input_keys – If provided, the search is based on the input variables instead of all variables.

• vectorstore_cls_kwargs – optional kwargs containing url for vector store

Returns

The ExampleSelector instantiated, backed by a vector store.

select_examples(input_variables: Dict[str, str]) → List[dict]

Select which examples to use based on semantic similarity.