rally-custom/custom_tracks/elasticsearch/dense_vector/track.py [177:220]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class KnnRecallParamSource:
    def __init__(self, track, params, **kwargs):
        if len(track.indices) == 1:
            default_index = track.indices[0].name
        else:
            default_index = "_all"

        self._index_name = params.get("index", default_index)
        self._cache = params.get("cache", False)
        self._params = params
        self.infinite = True
        self._target_k = 1_000
        cwd = os.path.dirname(__file__)
        self._queries_file: str = os.path.join(cwd, "queries.json")
        self._vector_field: str = "vector"

    def partition(self, partition_index, total_partitions):
        return self

    def params(self):
        return {
            "index": self._index_name,
            "cache": self._params.get("cache", False),
            "size": self._params.get("k", 10),
            "num_candidates": self._params.get("num-candidates", 100),
            "target_k": self._target_k,
            "knn_vector_store": KnnVectorStore.get_instance(self._queries_file, self._vector_field),
            "invalidate_vector_store": self._params.get("invalidate-vector-store", False),
        }


# Used in tandem with the KnnRecallParamSource. This executes both a knn query
# and an equivalent score script query. Results are then compared to gauge
# the accuracy of the knn query.
class KnnRecallRunner:
    async def __call__(self, es, params):
        k = params["size"]
        num_candidates = params["num_candidates"]
        index = params["index"]
        request_cache = params["cache"]
        target_k = max(params["target_k"], k)
        recall_total = 0
        exact_total = 0
        min_recall = k
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



rally-custom/custom_tracks/opensearch/dense_vector/track.py [186:229]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class KnnRecallParamSource:
    def __init__(self, track, params, **kwargs):
        if len(track.indices) == 1:
            default_index = track.indices[0].name
        else:
            default_index = "_all"

        self._index_name = params.get("index", default_index)
        self._cache = params.get("cache", False)
        self._params = params
        self.infinite = True
        self._target_k = 1_000
        cwd = os.path.dirname(__file__)
        self._queries_file: str = os.path.join(cwd, "queries.json")
        self._vector_field: str = "vector"

    def partition(self, partition_index, total_partitions):
        return self

    def params(self):
        return {
            "index": self._index_name,
            "cache": self._params.get("cache", False),
            "size": self._params.get("k", 10),
            "num_candidates": self._params.get("num-candidates", 100),
            "target_k": self._target_k,
            "knn_vector_store": KnnVectorStore.get_instance(self._queries_file, self._vector_field),
            "invalidate_vector_store": self._params.get("invalidate-vector-store", False),
        }


# Used in tandem with the KnnRecallParamSource. This executes both a knn query
# and an equivalent score script query. Results are then compared to gauge
# the accuracy of the knn query.
class KnnRecallRunner:
    async def __call__(self, es, params):
        k = params["size"]
        num_candidates = params["num_candidates"]
        index = params["index"]
        request_cache = params["cache"]
        target_k = max(params["target_k"], k)
        recall_total = 0
        exact_total = 0
        min_recall = k
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -