edsl 0.1.39.dev3__py3-none-any.whl → 0.1.39.dev4__py3-none-any.whl

edsl/jobs/JobsChecks.py

@@ -1,147 +1,172 @@
-import os
-from edsl.exceptions import MissingAPIKeyError
-
-
-class JobsChecks:
-    def __init__(self, jobs):
-        """ """
-        self.jobs = jobs
-
-    def check_api_keys(self) -> None:
-        from edsl import Model
-
-        for model in self.jobs.models + [Model()]:
-            if not model.has_valid_api_key():
-                raise MissingAPIKeyError(
-                    model_name=str(model.model),
-                    inference_service=model._inference_service_,
-                )
-
-    def get_missing_api_keys(self) -> set:
-        """
-        Returns a list of the api keys that a user needs to run this job, but does not currently have in their .env file.
-        """
-        missing_api_keys = set()
-
-        from edsl import Model
-        from edsl.enums import service_to_api_keyname
-
-        for model in self.jobs.models + [Model()]:
-            if not model.has_valid_api_key():
-                key_name = service_to_api_keyname.get(
-                    model._inference_service_, "NOT FOUND"
-                )
-                missing_api_keys.add(key_name)
-
-        return missing_api_keys
-
-    def user_has_ep_api_key(self) -> bool:
-        """
-        Returns True if the user has an EXPECTED_PARROT_API_KEY in their env.
-
-        Otherwise, returns False.
-        """
-
-        coop_api_key = os.getenv("EXPECTED_PARROT_API_KEY")
-
-        if coop_api_key is not None:
-            return True
-        else:
-            return False
-
-    def user_has_all_model_keys(self):
-        """
-        Returns True if the user has all model keys required to run their job.
-
-        Otherwise, returns False.
-        """
-
-        try:
-            self.check_api_keys()
-            return True
-        except MissingAPIKeyError:
-            return False
-        except Exception:
-            raise
-
-    def needs_external_llms(self) -> bool:
-        """
-        Returns True if the job needs external LLMs to run.
-
-        Otherwise, returns False.
-        """
-        # These cases are necessary to skip the API key check during doctests
-
-        # Accounts for Results.example()
-        all_agents_answer_questions_directly = len(self.jobs.agents) > 0 and all(
-            [hasattr(a, "answer_question_directly") for a in self.jobs.agents]
-        )
-
-        # Accounts for InterviewExceptionEntry.example()
-        only_model_is_test = set([m.model for m in self.jobs.models]) == set(["test"])
-
-        # Accounts for Survey.__call__
-        all_questions_are_functional = set(
-            [q.question_type for q in self.jobs.survey.questions]
-        ) == set(["functional"])
-
-        if (
-            all_agents_answer_questions_directly
-            or only_model_is_test
-            or all_questions_are_functional
-        ):
-            return False
-        else:
-            return True
-
-    def needs_key_process(self):
-        return (
-            not self.user_has_all_model_keys()
-            and not self.user_has_ep_api_key()
-            and self.needs_external_llms()
-        )
-
-    def key_process(self):
-        import secrets
-        from dotenv import load_dotenv
-        from edsl import CONFIG
-        from edsl.coop.coop import Coop
-        from edsl.utilities.utilities import write_api_key_to_env
-
-        missing_api_keys = self.get_missing_api_keys()
-
-        edsl_auth_token = secrets.token_urlsafe(16)
-
-        print("You're missing some of the API keys needed to run this job:")
-        for api_key in missing_api_keys:
-            print(f"     🔑 {api_key}")
-        print(
-            "\nYou can either add the missing keys to your .env file, or use remote inference."
-        )
-        print("Remote inference allows you to run jobs on our server.")
-        print("\n🚀 To use remote inference, sign up at the following link:")
-
-        coop = Coop()
-        coop._display_login_url(edsl_auth_token=edsl_auth_token)
-
-        print(
-            "\nOnce you log in, we will automatically retrieve your Expected Parrot API key and continue your job remotely."
-        )
-
-        api_key = coop._poll_for_api_key(edsl_auth_token)
-
-        if api_key is None:
-            print("\nTimed out waiting for login. Please try again.")
-            return
-
-        write_api_key_to_env(api_key)
-        print("✨ API key retrieved and written to .env file.\n")
-
-        # Retrieve API key so we can continue running the job
-        load_dotenv()
-
-
-if __name__ == "__main__":
-    import doctest
-
-    doctest.testmod()
+import os
+from edsl.exceptions.general import MissingAPIKeyError
+
+
+class JobsChecks:
+    def __init__(self, jobs):
+        """Checks a Jobs object for missing API keys and other requirements."""
+        self.jobs = jobs
+
+    def check_api_keys(self) -> None:
+        from edsl.language_models.model import Model
+
+        if len(self.jobs.models) == 0:
+            models = [Model()]
+        else:
+            models = self.jobs.models
+
+        for model in models:  # + [Model()]:
+            if not model.has_valid_api_key():
+                raise MissingAPIKeyError(
+                    model_name=str(model.model),
+                    inference_service=model._inference_service_,
+                )
+
+    def get_missing_api_keys(self) -> set:
+        """
+        Returns a list of the api keys that a user needs to run this job, but does not currently have in their .env file.
+        """
+        missing_api_keys = set()
+
+        from edsl.language_models.model import Model
+        from edsl.enums import service_to_api_keyname
+
+        for model in self.jobs.models + [Model()]:
+            if not model.has_valid_api_key():
+                key_name = service_to_api_keyname.get(
+                    model._inference_service_, "NOT FOUND"
+                )
+                missing_api_keys.add(key_name)
+
+        return missing_api_keys
+
+    def user_has_ep_api_key(self) -> bool:
+        """
+        Returns True if the user has an EXPECTED_PARROT_API_KEY in their env.
+
+        Otherwise, returns False.
+        """
+
+        coop_api_key = os.getenv("EXPECTED_PARROT_API_KEY")
+
+        if coop_api_key is not None:
+            return True
+        else:
+            return False
+
+    def user_has_all_model_keys(self):
+        """
+        Returns True if the user has all model keys required to run their job.
+
+        Otherwise, returns False.
+        """
+
+        try:
+            self.check_api_keys()
+            return True
+        except MissingAPIKeyError:
+            return False
+        except Exception:
+            raise
+
+    def needs_external_llms(self) -> bool:
+        """
+        Returns True if the job needs external LLMs to run.
+
+        Otherwise, returns False.
+        """
+        # These cases are necessary to skip the API key check during doctests
+
+        # Accounts for Results.example()
+        all_agents_answer_questions_directly = len(self.jobs.agents) > 0 and all(
+            [hasattr(a, "answer_question_directly") for a in self.jobs.agents]
+        )
+
+        # Accounts for InterviewExceptionEntry.example()
+        only_model_is_test = set([m.model for m in self.jobs.models]) == set(["test"])
+
+        # Accounts for Survey.__call__
+        all_questions_are_functional = set(
+            [q.question_type for q in self.jobs.survey.questions]
+        ) == set(["functional"])
+
+        if (
+            all_agents_answer_questions_directly
+            or only_model_is_test
+            or all_questions_are_functional
+        ):
+            return False
+        else:
+            return True
+
+    def needs_key_process(self):
+        """
+        A User needs the key process when:
+        1. They don't have all the model keys
+        2. They don't have the EP API
+        3. They need external LLMs to run the job
+        """
+        return (
+            not self.user_has_all_model_keys()
+            and not self.user_has_ep_api_key()
+            and self.needs_external_llms()
+        )
+
+    def status(self) -> dict:
+        """
+        Returns a dictionary with the status of the job checks.
+        """
+        return {
+            "user_has_ep_api_key": self.user_has_ep_api_key(),
+            "user_has_all_model_keys": self.user_has_all_model_keys(),
+            "needs_external_llms": self.needs_external_llms(),
+            "needs_key_process": self.needs_key_process(),
+        }
+
+    def key_process(self):
+        import secrets
+        from dotenv import load_dotenv
+        from edsl.config import CONFIG
+        from edsl.coop.coop import Coop
+        from edsl.utilities.utilities import write_api_key_to_env
+
+        missing_api_keys = self.get_missing_api_keys()
+
+        edsl_auth_token = secrets.token_urlsafe(16)
+
+        print("You're missing some of the API keys needed to run this job:")
+        for api_key in missing_api_keys:
+            print(f"     🔑 {api_key}")
+        print(
+            "\nYou can either add the missing keys to your .env file, or use remote inference."
+        )
+        print("Remote inference allows you to run jobs on our server.")
+
+        coop = Coop()
+        coop._display_login_url(
+            edsl_auth_token=edsl_auth_token,
+            link_description="\n🚀 To use remote inference, sign up at the following link:",
+        )
+
+        print(
+            "\nOnce you log in, we will automatically retrieve your Expected Parrot API key and continue your job remotely."
+        )
+
+        api_key = coop._poll_for_api_key(edsl_auth_token)
+
+        if api_key is None:
+            print("\nTimed out waiting for login. Please try again.")
+            return
+
+        path_to_env = write_api_key_to_env(api_key)
+        print("\n✨ API key retrieved and written to .env file at the following path:")
+        print(f"    {path_to_env}")
+
+        # Retrieve API key so we can continue running the job
+        load_dotenv()
+
+
+if __name__ == "__main__":
+    import doctest
+
+    doctest.testmod()

edsl/jobs/JobsComponentConstructor.py

@@ -0,0 +1,189 @@
+from typing import Union, Sequence, TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from edsl.agents.Agent import Agent
+    from edsl.language_models.LanguageModel import LanguageModel
+    from edsl.scenarios.Scenario import Scenario
+    from edsl.jobs.Jobs import Jobs
+
+
+class JobsComponentConstructor:
+    "Handles the creation of Agents, Scenarios, and LanguageModels in a job."
+
+    def __init__(self, jobs: "Jobs"):
+        self.jobs = jobs
+
+    def by(
+        self,
+        *args: Union[
+            "Agent",
+            "Scenario",
+            "LanguageModel",
+            Sequence[Union["Agent", "Scenario", "LanguageModel"]],
+        ],
+    ) -> "Jobs":
+        """
+        Add Agents, Scenarios and LanguageModels to a job.
+
+        :param args: objects or a sequence (list, tuple, ...) of objects of the same type
+
+        If no objects of this type exist in the Jobs instance, it stores the new objects as a list in the corresponding attribute.
+        Otherwise, it combines the new objects with existing objects using the object's `__add__` method.
+
+        This 'by' is intended to create a fluent interface.
+
+        >>> from edsl.surveys import Survey
+        >>> from edsl.questions import QuestionFreeText
+        >>> q = QuestionFreeText(question_name="name", question_text="What is your name?")
+        >>> from edsl.jobs import Jobs
+        >>> j = Jobs(survey = Survey(questions=[q]))
+        >>> j
+        Jobs(survey=Survey(...), agents=AgentList([]), models=ModelList([]), scenarios=ScenarioList([]))
+        >>> from edsl import Agent; a = Agent(traits = {"status": "Sad"})
+        >>> j.by(a).agents
+        AgentList([Agent(traits = {'status': 'Sad'})])
+
+
+        Notes:
+        - all objects must implement the 'get_value', 'set_value', and `__add__` methods
+        - agents: traits of new agents are combined with traits of existing agents. New and existing agents should not have overlapping traits, and do not increase the # agents in the instance
+        - scenarios: traits of new scenarios are combined with traits of old existing. New scenarios will overwrite overlapping traits, and do not increase the number of scenarios in the instance
+        - models: new models overwrite old models.
+        """
+        from edsl.results.Dataset import Dataset
+
+        if isinstance(
+            args[0], Dataset
+        ):  # let the user use a Dataset as if it were a ScenarioList
+            args = args[0].to_scenario_list()
+
+        passed_objects = self._turn_args_to_list(
+            args
+        )  # objects can also be passed comma-separated
+
+        current_objects, objects_key = self._get_current_objects_of_this_type(
+            passed_objects[0]
+        )
+
+        if not current_objects:
+            new_objects = passed_objects
+        else:
+            new_objects = self._merge_objects(passed_objects, current_objects)
+
+        setattr(self.jobs, objects_key, new_objects)  # update the job object
+        return self.jobs
+
+    @staticmethod
+    def _turn_args_to_list(args):
+        """Return a list of the first argument if it is a sequence, otherwise returns a list of all the arguments.
+
+        Example:
+
+        >>> JobsComponentConstructor._turn_args_to_list([1,2,3])
+        [1, 2, 3]
+
+        """
+
+        def did_user_pass_a_sequence(args):
+            """Return True if the user passed a sequence, False otherwise.
+
+            Example:
+
+            >>> did_user_pass_a_sequence([1,2,3])
+            True
+
+            >>> did_user_pass_a_sequence(1)
+            False
+            """
+            return len(args) == 1 and isinstance(args[0], Sequence)
+
+        if did_user_pass_a_sequence(args):
+            container_class = JobsComponentConstructor._get_container_class(args[0][0])
+            return container_class(args[0])
+        else:
+            container_class = JobsComponentConstructor._get_container_class(args[0])
+            return container_class(args)
+
+    def _get_current_objects_of_this_type(
+        self, object: Union["Agent", "Scenario", "LanguageModel"]
+    ) -> tuple[list, str]:
+        from edsl.agents.Agent import Agent
+        from edsl.scenarios.Scenario import Scenario
+        from edsl.language_models.LanguageModel import LanguageModel
+
+        """Return the current objects of the same type as the first argument.
+
+        >>> from edsl.jobs import Jobs
+        >>> j = JobsComponentConstructor(Jobs.example())
+        >>> j._get_current_objects_of_this_type(j.agents[0])
+        (AgentList([Agent(traits = {'status': 'Joyful'}), Agent(traits = {'status': 'Sad'})]), 'agents')
+        """
+        class_to_key = {
+            Agent: "agents",
+            Scenario: "scenarios",
+            LanguageModel: "models",
+        }
+        for class_type in class_to_key:
+            if isinstance(object, class_type) or issubclass(
+                object.__class__, class_type
+            ):
+                key = class_to_key[class_type]
+                break
+        else:
+            raise ValueError(
+                f"First argument must be an Agent, Scenario, or LanguageModel, not {object}"
+            )
+        current_objects = getattr(self.jobs, key, None)
+        return current_objects, key
+
+    @staticmethod
+    def _get_empty_container_object(object):
+        from edsl.agents.AgentList import AgentList
+        from edsl.scenarios.ScenarioList import ScenarioList
+
+        return {"Agent": AgentList([]), "Scenario": ScenarioList([])}.get(
+            object.__class__.__name__, []
+        )
+
+    @staticmethod
+    def _merge_objects(passed_objects, current_objects) -> list:
+        """
+        Combine all the existing objects with the new objects.
+
+        For example, if the user passes in 3 agents,
+        and there are 2 existing agents, this will create 6 new agents
+        >>> from edsl.jobs import Jobs
+        >>> JobsComponentConstructor(Jobs(survey = []))._merge_objects([1,2,3], [4,5,6])
+        [5, 6, 7, 6, 7, 8, 7, 8, 9]
+        """
+        new_objects = JobsComponentConstructor._get_empty_container_object(
+            passed_objects[0]
+        )
+        for current_object in current_objects:
+            for new_object in passed_objects:
+                new_objects.append(current_object + new_object)
+        return new_objects
+
+    @staticmethod
+    def _get_container_class(object):
+        from edsl.agents.AgentList import AgentList
+        from edsl.agents.Agent import Agent
+        from edsl.scenarios.Scenario import Scenario
+        from edsl.scenarios.ScenarioList import ScenarioList
+        from edsl.language_models.ModelList import ModelList
+
+        if isinstance(object, Agent):
+            return AgentList
+        elif isinstance(object, Scenario):
+            return ScenarioList
+        elif isinstance(object, ModelList):
+            return ModelList
+        else:
+            return list
+
+
+if __name__ == "__main__":
+    """Run the module's doctests."""
+    import doctest
+
+    doctest.testmod(optionflags=doctest.ELLIPSIS)