How to use the jedi.inference.base_value.ValueSet.from_sets function in jedi

def execute_with_values(self, *args, **kwargs):
        return ValueSet.from_sets(c.execute_with_values(*args, **kwargs) for c in self._set)

if python_value_set is None:
            if parent_module_value is not None and parent_module_value.is_stub():
                parent_module_values = parent_module_value.non_stub_value_set
            else:
                parent_module_values = [parent_module_value]
            if import_names == ('os', 'path'):
                # This is a huge exception, we follow a nested import
                # ``os.path``, because it's a very important one in Python
                # that is being achieved by messing with ``sys.modules`` in
                # ``os``.
                python_value_set = ValueSet.from_sets(
                    func(inference_state, (n,), None, sys_path,)
                    for n in [u'posixpath', u'ntpath', u'macpath', u'os2emxpath']
                )
            else:
                python_value_set = ValueSet.from_sets(
                    func(inference_state, import_names, p, sys_path,)
                    for p in parent_module_values
                )
            inference_state.module_cache.add(import_names, python_value_set)

        if not prefer_stubs:
            return python_value_set

        stub = try_to_load_stub_cached(inference_state, import_names, python_value_set,
                                       parent_module_value, sys_path)
        if stub is not None:
            return ValueSet([stub])
        return python_value_set

def py__simple_getitem__(self, index):
        if self.array_type == 'dict':
            # Logic for dict({'foo': bar}) and dict(foo=bar)
            # reversed, because:
            # >>> dict({'a': 1}, a=3)
            # {'a': 3}
            # TODO tuple initializations
            # >>> dict([('a', 4)])
            # {'a': 4}
            for key, lazy_context in reversed(list(self._arguments.unpack())):
                if key is None:
                    values = ValueSet.from_sets(
                        dct_value.py__simple_getitem__(index)
                        for dct_value in lazy_context.infer()
                        if dct_value.array_type == 'dict'
                    )
                    if values:
                        return values
                else:
                    if key == index:
                        return lazy_context.infer()
        return super(TreeInstance, self).py__simple_getitem__(index)

stub_value = stub_value.py__class__()

    qualified_names = stub_value.get_qualified_names()
    if qualified_names is None:
        return NO_VALUES

    was_bound_method = stub_value.is_bound_method()
    if was_bound_method:
        # Infer the object first. We can infer the method later.
        method_name = qualified_names[-1]
        qualified_names = qualified_names[:-1]
        was_instance = True

    values = _infer_from_stub(stub_module_context, qualified_names, ignore_compiled)
    if was_instance:
        values = ValueSet.from_sets(
            c.execute_with_values()
            for c in values
            if c.is_class()
        )
    if was_bound_method:
        # Now that the instance has been properly created, we can simply get
        # the method.
        values = values.py__getattribute__(method_name)
    if decorates is not None:
        values = ValueSet(Decoratee(v, decorates) for v in values)
    return values

if check_yields:
            value_set = NO_VALUES
            returns = get_yield_exprs(self.inference_state, funcdef)
        else:
            value_set = self._infer_annotations()
            if value_set:
                # If there are annotations, prefer them over anything else.
                # This will make it faster.
                return value_set
            value_set |= docstrings.infer_return_types(self._value)
            returns = funcdef.iter_return_stmts()

        for r in returns:
            if check_yields:
                value_set |= ValueSet.from_sets(
                    lazy_value.infer()
                    for lazy_value in self._get_yield_lazy_value(r)
                )
            else:
                check = flow_analysis.reachability_check(self, funcdef, r)
                if check is flow_analysis.UNREACHABLE:
                    debug.dbg('Return unreachable: %s', r)
                else:
                    try:
                        children = r.children
                    except AttributeError:
                        ctx = compiled.builtin_from_name(self.inference_state, u'None')
                        value_set |= ValueSet([ctx])
                    else:
                        value_set |= self.infer_node(children[1])
                if check is flow_analysis.REACHABLE:

def _infer_comparison(context, left_values, operator, right_values):
    state = context.inference_state
    if not left_values or not right_values:
        # illegal slices e.g. cause left/right_result to be None
        result = (left_values or NO_VALUES) | (right_values or NO_VALUES)
        return _literals_to_types(state, result)
    else:
        # I don't think there's a reasonable chance that a string
        # operation is still correct, once we pass something like six
        # objects.
        if len(left_values) * len(right_values) > 6:
            return _literals_to_types(state, left_values | right_values)
        else:
            return ValueSet.from_sets(
                _infer_comparison_part(state, context, left, operator, right)
                for left in left_values
                for right in right_values
            )

def merge_yield_values(self, is_async=False):
        return ValueSet.from_sets(
            lazy_value.infer()
            for lazy_value in self.get_yield_lazy_values()
        )

def convert_values(values, only_stubs=False, prefer_stubs=False, ignore_compiled=True):
    assert not (only_stubs and prefer_stubs)
    with debug.increase_indent_cm('convert values'):
        if only_stubs or prefer_stubs:
            return ValueSet.from_sets(
                to_stub(value)
                or (ValueSet({value}) if prefer_stubs else NO_VALUES)
                for value in values
            )
        else:
            return ValueSet.from_sets(
                _stub_to_python_value_set(stub_value, ignore_compiled=ignore_compiled)
                or ValueSet({stub_value})
                for stub_value in values
            )

def py__next__(self):
        return ValueSet.from_sets(lazy_value.infer() for lazy_value in self.py__iter__())