Method handle

apps/knowledge/vector/pg_vector.py:309–343

(
        self,
        query_set,
        query_text,
        query_embedding,
        top_number: int,
        similarity: float,
        search_mode: SearchMode,
        knowledge_id_list: list[str] = None,
    )

class BlendSearch(ISearch):
    def handle(
        self,
        query_set,
        query_text,
        query_embedding,
        top_number: int,
        similarity: float,
        search_mode: SearchMode,
        knowledge_id_list: list[str] = None,
    ):
        exec_sql, exec_params = generate_sql_by_query_dict(
            {"embedding_query": query_set},
            select_string=get_file_content(os.path.join(PROJECT_DIR, "apps", "knowledge", "sql", "blend_search.sql")),
            with_table_name=True,
        )
        terms = (
            list(QuerySet(Termbase).filter(knowledge_id__in=knowledge_id_list).values_list("content", flat=True))
            if knowledge_id_list
            else None
        )
        embedding_model = select_list(
            exec_sql,
            [
                len(query_embedding),
                json.dumps(query_embedding),
                *exec_params,
                len(query_embedding),
                json.dumps(query_embedding),
                top_number,
                to_query(query_text, user_words=terms),
                similarity,
                top_number,
            ],
        )
        return embedding_model

    def support(self, search_mode: SearchMode):
        return search_mode.value == SearchMode.blend.value