BasicPromptingStrategy

class ragger_duck.prompt.BasicPromptingStrategy(*, llm, retriever, use_retrieved_context=True)

Prompting strategy for answering a query.

Once we retrieve the context, we request to answer the query using the context. We allow to not use the retrieved context to answer the query.

Parameters:

llmllm instance

The language model to use for the prompting. We expect the model to implement a __call__ method that takes a prompt and returns a response. It should be an “Instruct”-based model.

retrieverretriever instance

The retriever to use for retrieving the context. We expect the retriever to implement a query method.

use_retrieved_contextbool, default=True

Whether to use the retriever to retrieve the context before prompting.

Methods

fit([X, y])	No-op operation, only validate parameters.
get_metadata_routing()	Get metadata routing of this object.
get_params([deep])	Get parameters for this estimator.
set_params(**params)	Set the parameters of this estimator.

fit(X=None, y=None)

No-op operation, only validate parameters.

Parameters:

XNone

This parameter is ignored.

yNone

This parameter is ignored.

Returns:

self

The fitted estimator.

get_metadata_routing()

Get metadata routing of this object.

Please check User Guide on how the routing mechanism works.

Returns:

routingMetadataRequest

A MetadataRequest encapsulating routing information.

get_params(deep=True)

Get parameters for this estimator.

Parameters:

deepbool, default=True

If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns:

paramsdict

Parameter names mapped to their values.

set_params(**params)

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:

**paramsdict

Estimator parameters.

Returns:

selfestimator instance

Estimator instance.