Query Transform

Query Transforms.

class llama_index.indices.query.query_transform.DecomposeQueryTransform(llm_predictor: Optional[BaseLLMPredictor] = 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[LLMPredictor]) – LLM for generating hypothetical documents

run(query_bundle_or_str: Union[str, QueryBundle], metadata: Optional[Dict] = None) → QueryBundle

Run query transform.

class llama_index.indices.query.query_transform.HyDEQueryTransform(llm_predictor: Optional[BaseLLMPredictor] = 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)

run(query_bundle_or_str: Union[str, QueryBundle], metadata: Optional[Dict] = None) → QueryBundle

Run query transform.

class llama_index.indices.query.query_transform.StepDecomposeQueryTransform(llm_predictor: Optional[BaseLLMPredictor] = 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[LLMPredictor]) – LLM for generating hypothetical documents

run(query_bundle_or_str: Union[str, QueryBundle], metadata: Optional[Dict] = None) → QueryBundle

Run query transform.