Method query_storage

document_qa/document_qa_engine.py:348–368

Retrieve relevant text passages without calling the LLM. Useful for debugging which chunks would be used as context, or for building custom pipelines on top of the retrieval step. Args: query: The natural-language question. doc_id: Document identifie

(self, query: str, doc_id, context_size=4)

            return None, response, coordinates

    def query_storage(self, query: str, doc_id, context_size=4) -> tuple[List[str], list]:
        """Retrieve relevant text passages without calling the LLM.

        Useful for debugging which chunks would be used as context, or for
        building custom pipelines on top of the retrieval step.

        Args:
            query: The natural-language question.
            doc_id: Document identifier.
            context_size: Number of chunks to retrieve (default 4).

        Returns:
            tuple: ``(texts, coordinates)``

            - *texts* — list of passage strings.
            - *coordinates* — list of lists of coordinate strings.
        """
        documents, coordinates = self._get_context(doc_id, query, context_size)

        context_as_text = [doc.page_content for doc in documents]
        return context_as_text, coordinates

    def query_storage_and_embeddings(self, query: str, doc_id, context_size=4) -> List[Document]:
        """Retrieve passages with their similarity scores and raw embeddings.