class jina.executors.evaluators.BaseEvaluator(*args, **kwargs)[source]

Bases: jina.executors.BaseExecutor

A BaseEvaluator is used to evaluate different messages coming from any kind of executor


metric = ''

Get the name of the evaluation metric


Initialize running stats.

evaluate(actual, desired, *args, **kwargs)[source]

Evaluates difference between param:actual and param:desired, needs to be implemented in subclass.

Return type


property mean

Get the running mean.

Return type


property std

Get the running standard variance.

Return type


property variance

Get the running variance.

Return type


class jina.executors.evaluators.FileBasedEvaluator(routes=None, resolve_all=True, *args, **kwargs)[source]

Bases: jina.executors.compound.CompoundExecutor

A Frequently used pattern for combining A BinaryPbIndexer and BaseEvaluator.

It will be equipped with predefined requests.on behaviors:

  • At evaluation time(query or index)
      1. Checks for the incoming document, gets its value from the BinaryPbIndexer and fills the `groundtruth of the request

      1. Filter the documents that do not have a corresponding groundtruth

      1. The BaseEvaluator works as if the groundtruth had been provided by the client as it comes in the request.


The documents that are not found to have an indexed groundtruth are removed from the request so that the Evaluator only works with documents which have groundtruth.

One can use the FileBasedEvaluator via

  - !BinaryPbIndexer
      index_filename: ground_truth.gz
      name: groundtruth_index  # a customized name
      workspace: ${{TEST_WORKDIR}}
  - !BaseEvaluator

Without defining any requests.on logic. When load from this YAML, it will be auto equipped with

  [SearchRequest, IndexRequest]:
    - !LoadGroundTruthDriver
        executor: BaseKVIndexer
    - !BaseEvaluateDriver
        executor: BaseEvaluator
    - !ControlReqDriver {}

Create a new CompoundExecutor object

  • routes (Optional[Dict[str, Dict]]) –

    a map of function routes. The key is the function name, the value is a tuple of two pieces, where the first element is the name of the referred component (metas.name) and the second element is the name of the referred function.

    See also


  • resolve_all (bool) – universally add *_all() to all functions that have the identical name


We have two dummy executors as follows:

class dummyA(BaseExecutor):
    def say(self):
        return 'a'

    def sayA(self):
        print('A: im A')

class dummyB(BaseExecutor):
    def say(self):
        return 'b'

    def sayB(self):
        print('B: im B')

and we create a CompoundExecutor consisting of these two via

da, db = dummyA(), dummyB()
ce = CompoundExecutor()
ce.components = lambda: [da, db]

Now the new executor ce have two new methods, i.e ce.sayA() and ce.sayB(). They point to the original dummyA.sayA() and dummyB.sayB() respectively. One can say ce has inherited these two methods.

The interesting part is say(), as this function name is shared between dummyA and dummyB. It requires some resolution. When resolve_all=True, then a new function say_all() is add to ce. ce.say_all works as if you call dummyA.sayA() and dummyB.sayB() in a row. This makes sense in some cases such as training, saving. In other cases, it may require a more sophisticated resolution, where one can use add_route() to achieve that. For example,

ce.add_route('say', db.name, 'say')
assert b.say() == 'b'

Such resolution is what we call routes here, and it can be specified in advance with the arguments routes in __init__(), or using YAML.

components: ...
  resolve_all: true
    - dummyB-e3acc910
    - say


When setting inner executors in components the workspace configuration will not be used and will be overriden by a workspace extracted considering the name of the CompoundExecutor, the name of each internal Component and the pea_id