Query Transform#

Query Transforms.

class llama_index.core.indices.query.query_transform.DecomposeQueryTransform(llm: Optional[Union[LLMPredictor, LLM]] = None, decompose_query_prompt: Optional[PromptTemplate] = None, verbose: bool = False)#

Decompose query transform.

Decomposes query into a subquery given the current index struct. Performs a single step transformation.

Parameters: llm_predictor (Optional[LLM]) – LLM for generating hypothetical documents

as_query_component(partial: Optional[Dict[str, Any]] = None, **kwargs: Any) → QueryComponent#: Get query component.

get_prompts() → Dict[str, BasePromptTemplate]#: Get a prompt.

run(query_bundle_or_str: Union[str, QueryBundle], metadata: Optional[Dict] = None) → QueryBundle#: Run query transform.

update_prompts(prompts_dict: Dict[str, BasePromptTemplate]) → None#

Update prompts.

Other prompts will remain in place.

class llama_index.core.indices.query.query_transform.HyDEQueryTransform(llm: Optional[Union[LLMPredictor, LLM]] = None, hyde_prompt: Optional[BasePromptTemplate] = None, include_original: bool = True)#

Hypothetical Document Embeddings (HyDE) query transform.

It uses an LLM to generate hypothetical answer(s) to a given query, and use the resulting documents as embedding strings.

As described in [Precise Zero-Shot Dense Retrieval without Relevance Labels] (https://arxiv.org/abs/2212.10496)

as_query_component(partial: Optional[Dict[str, Any]] = None, **kwargs: Any) → QueryComponent#: Get query component.

get_prompts() → Dict[str, BasePromptTemplate]#: Get a prompt.

run(query_bundle_or_str: Union[str, QueryBundle], metadata: Optional[Dict] = None) → QueryBundle#: Run query transform.

update_prompts(prompts_dict: Dict[str, BasePromptTemplate]) → None#

Update prompts.

Other prompts will remain in place.

class llama_index.core.indices.query.query_transform.StepDecomposeQueryTransform(llm: Optional[Union[LLMPredictor, LLM]] = None, step_decompose_query_prompt: Optional[PromptTemplate] = None, verbose: bool = False)#

Step decompose query transform.

Decomposes query into a subquery given the current index struct and previous reasoning.

NOTE: doesn’t work yet.

Parameters: llm_predictor (Optional[LLM]) – LLM for generating hypothetical documents

as_query_component(partial: Optional[Dict[str, Any]] = None, **kwargs: Any) → QueryComponent#: Get query component.

get_prompts() → Dict[str, BasePromptTemplate]#: Get a prompt.

run(query_bundle_or_str: Union[str, QueryBundle], metadata: Optional[Dict] = None) → QueryBundle#: Run query transform.

update_prompts(prompts_dict: Dict[str, BasePromptTemplate]) → None#

Update prompts.

Other prompts will remain in place.