edsl 0.1.39.dev3__py3-none-any.whl → 0.1.39.dev5__py3-none-any.whl

edsl/agents/prompt_helpers.py

@@ -1,129 +1,129 @@
-import enum
-from typing import Dict, Optional
-from collections import UserList
-from edsl.prompts import Prompt
-
-
-class PromptComponent(enum.Enum):
-    AGENT_INSTRUCTIONS = "agent_instructions"
-    AGENT_PERSONA = "agent_persona"
-    QUESTION_INSTRUCTIONS = "question_instructions"
-    PRIOR_QUESTION_MEMORY = "prior_question_memory"
-
-
-class PromptList(UserList):
-    separator = Prompt(" ")
-
-    def reduce(self):
-        """Reduce the list of prompts to a single prompt.
-
-        >>> p = PromptList([Prompt("You are a happy-go lucky agent."), Prompt("You are an agent with the following persona: {'age': 22, 'hair': 'brown', 'height': 5.5}")])
-        >>> p.reduce()
-        Prompt(text=\"""You are a happy-go lucky agent. You are an agent with the following persona: {'age': 22, 'hair': 'brown', 'height': 5.5}\""")
-
-        """
-        p = self[0]
-        for prompt in self[1:]:
-            if len(prompt) > 0:
-                p = p + self.separator + prompt
-        return p
-
-
-class PromptPlan:
-    """A plan for constructing prompts for the LLM call.
-    Every prompt plan has a user prompt order and a system prompt order.
-    It must contain each of the values in the PromptComponent enum.
-
-
-    >>> p = PromptPlan(user_prompt_order=(PromptComponent.AGENT_INSTRUCTIONS, PromptComponent.AGENT_PERSONA),system_prompt_order=(PromptComponent.QUESTION_INSTRUCTIONS, PromptComponent.PRIOR_QUESTION_MEMORY))
-    >>> p._is_valid_plan()
-    True
-
-    >>> p.arrange_components(agent_instructions=1, agent_persona=2, question_instructions=3, prior_question_memory=4)
-    {'user_prompt': ..., 'system_prompt': ...}
-
-    >>> p = PromptPlan(user_prompt_order=("agent_instructions", ), system_prompt_order=("question_instructions", "prior_question_memory"))
-    Traceback (most recent call last):
-    ...
-    ValueError: Invalid plan: must contain each value of PromptComponent exactly once.
-
-    """
-
-    def __init__(
-        self,
-        user_prompt_order: Optional[tuple] = None,
-        system_prompt_order: Optional[tuple] = None,
-    ):
-        """Initialize the PromptPlan."""
-
-        if user_prompt_order is None:
-            user_prompt_order = (
-                PromptComponent.QUESTION_INSTRUCTIONS,
-                PromptComponent.PRIOR_QUESTION_MEMORY,
-            )
-        if system_prompt_order is None:
-            system_prompt_order = (
-                PromptComponent.AGENT_INSTRUCTIONS,
-                PromptComponent.AGENT_PERSONA,
-            )
-
-        # very commmon way to screw this up given how python treats single strings as iterables
-        if isinstance(user_prompt_order, str):
-            user_prompt_order = (user_prompt_order,)
-
-        if isinstance(system_prompt_order, str):
-            system_prompt_order = (system_prompt_order,)
-
-        if not isinstance(user_prompt_order, tuple):
-            raise TypeError(
-                f"Expected a tuple, but got {type(user_prompt_order).__name__}"
-            )
-
-        if not isinstance(system_prompt_order, tuple):
-            raise TypeError(
-                f"Expected a tuple, but got {type(system_prompt_order).__name__}"
-            )
-
-        self.user_prompt_order = self._convert_to_enum(user_prompt_order)
-        self.system_prompt_order = self._convert_to_enum(system_prompt_order)
-        if not self._is_valid_plan():
-            raise ValueError(
-                "Invalid plan: must contain each value of PromptComponent exactly once."
-            )
-
-    def _convert_to_enum(self, prompt_order: tuple):
-        """Convert string names to PromptComponent enum values."""
-        return tuple(
-            PromptComponent(component) if isinstance(component, str) else component
-            for component in prompt_order
-        )
-
-    def _is_valid_plan(self):
-        """Check if the plan is valid."""
-        combined = self.user_prompt_order + self.system_prompt_order
-        return set(combined) == set(PromptComponent)
-
-    def arrange_components(self, **kwargs) -> Dict[PromptComponent, Prompt]:
-        """Arrange the components in the order specified by the plan."""
-        # check is valid components passed
-        component_strings = set([pc.value for pc in PromptComponent])
-        if not set(kwargs.keys()) == component_strings:
-            raise ValueError(
-                f"Invalid components passed: {set(kwargs.keys())} but expected {PromptComponent}"
-            )
-
-        user_prompt = PromptList(
-            [kwargs[component.value] for component in self.user_prompt_order]
-        )
-        system_prompt = PromptList(
-            [kwargs[component.value] for component in self.system_prompt_order]
-        )
-        return {"user_prompt": user_prompt, "system_prompt": system_prompt}
-
-    def get_prompts(self, **kwargs) -> Dict[str, Prompt]:
-        """Get both prompts for the LLM call."""
-        prompts = self.arrange_components(**kwargs)
-        return {
-            "user_prompt": prompts["user_prompt"].reduce(),
-            "system_prompt": prompts["system_prompt"].reduce(),
-        }
+import enum
+from typing import Dict, Optional
+from collections import UserList
+from edsl.prompts.Prompt import Prompt
+
+
+class PromptComponent(enum.Enum):
+    AGENT_INSTRUCTIONS = "agent_instructions"
+    AGENT_PERSONA = "agent_persona"
+    QUESTION_INSTRUCTIONS = "question_instructions"
+    PRIOR_QUESTION_MEMORY = "prior_question_memory"
+
+
+class PromptList(UserList):
+    separator = Prompt("")
+
+    def reduce(self):
+        """Reduce the list of prompts to a single prompt.
+
+        >>> p = PromptList([Prompt("You are a happy-go lucky agent."), Prompt("You are an agent with the following persona: {'age': 22, 'hair': 'brown', 'height': 5.5}")])
+        >>> p.reduce()
+        Prompt(text=\"""You are a happy-go lucky agent.You are an agent with the following persona: {'age': 22, 'hair': 'brown', 'height': 5.5}\""")
+
+        """
+        p = self[0]
+        for prompt in self[1:]:
+            if len(prompt) > 0:
+                p = p + self.separator + prompt
+        return p
+
+
+class PromptPlan:
+    """A plan for constructing prompts for the LLM call.
+    Every prompt plan has a user prompt order and a system prompt order.
+    It must contain each of the values in the PromptComponent enum.
+
+
+    >>> p = PromptPlan(user_prompt_order=(PromptComponent.AGENT_INSTRUCTIONS, PromptComponent.AGENT_PERSONA),system_prompt_order=(PromptComponent.QUESTION_INSTRUCTIONS, PromptComponent.PRIOR_QUESTION_MEMORY))
+    >>> p._is_valid_plan()
+    True
+
+    >>> p.arrange_components(agent_instructions=1, agent_persona=2, question_instructions=3, prior_question_memory=4)
+    {'user_prompt': ..., 'system_prompt': ...}
+
+    >>> p = PromptPlan(user_prompt_order=("agent_instructions", ), system_prompt_order=("question_instructions", "prior_question_memory"))
+    Traceback (most recent call last):
+    ...
+    ValueError: Invalid plan: must contain each value of PromptComponent exactly once.
+
+    """
+
+    def __init__(
+        self,
+        user_prompt_order: Optional[tuple] = None,
+        system_prompt_order: Optional[tuple] = None,
+    ):
+        """Initialize the PromptPlan."""
+
+        if user_prompt_order is None:
+            user_prompt_order = (
+                PromptComponent.QUESTION_INSTRUCTIONS,
+                PromptComponent.PRIOR_QUESTION_MEMORY,
+            )
+        if system_prompt_order is None:
+            system_prompt_order = (
+                PromptComponent.AGENT_INSTRUCTIONS,
+                PromptComponent.AGENT_PERSONA,
+            )
+
+        # very commmon way to screw this up given how python treats single strings as iterables
+        if isinstance(user_prompt_order, str):
+            user_prompt_order = (user_prompt_order,)
+
+        if isinstance(system_prompt_order, str):
+            system_prompt_order = (system_prompt_order,)
+
+        if not isinstance(user_prompt_order, tuple):
+            raise TypeError(
+                f"Expected a tuple, but got {type(user_prompt_order).__name__}"
+            )
+
+        if not isinstance(system_prompt_order, tuple):
+            raise TypeError(
+                f"Expected a tuple, but got {type(system_prompt_order).__name__}"
+            )
+
+        self.user_prompt_order = self._convert_to_enum(user_prompt_order)
+        self.system_prompt_order = self._convert_to_enum(system_prompt_order)
+        if not self._is_valid_plan():
+            raise ValueError(
+                "Invalid plan: must contain each value of PromptComponent exactly once."
+            )
+
+    def _convert_to_enum(self, prompt_order: tuple):
+        """Convert string names to PromptComponent enum values."""
+        return tuple(
+            PromptComponent(component) if isinstance(component, str) else component
+            for component in prompt_order
+        )
+
+    def _is_valid_plan(self):
+        """Check if the plan is valid."""
+        combined = self.user_prompt_order + self.system_prompt_order
+        return set(combined) == set(PromptComponent)
+
+    def arrange_components(self, **kwargs) -> Dict[PromptComponent, Prompt]:
+        """Arrange the components in the order specified by the plan."""
+        # check is valid components passed
+        component_strings = set([pc.value for pc in PromptComponent])
+        if not set(kwargs.keys()) == component_strings:
+            raise ValueError(
+                f"Invalid components passed: {set(kwargs.keys())} but expected {PromptComponent}"
+            )
+
+        user_prompt = PromptList(
+            [kwargs[component.value] for component in self.user_prompt_order]
+        )
+        system_prompt = PromptList(
+            [kwargs[component.value] for component in self.system_prompt_order]
+        )
+        return {"user_prompt": user_prompt, "system_prompt": system_prompt}
+
+    def get_prompts(self, **kwargs) -> Dict[str, Prompt]:
+        """Get both prompts for the LLM call."""
+        prompts = self.arrange_components(**kwargs)
+        return {
+            "user_prompt": prompts["user_prompt"].reduce(),
+            "system_prompt": prompts["system_prompt"].reduce(),
+        }

edsl/agents/question_option_processor.py

@@ -0,0 +1,172 @@
+from jinja2 import Environment, meta
+from typing import List, Optional, Union
+
+
+class QuestionOptionProcessor:
+    """
+    Class that manages the processing of question options.
+    These can be provided directly, as a template string, or fetched from prior answers or the scenario.
+    """
+
+    def __init__(self, prompt_constructor):
+        self.prompt_constructor = prompt_constructor
+
+    @staticmethod
+    def _get_default_options() -> list:
+        """Return default placeholder options."""
+        return [f"<< Option {i} - Placeholder >>" for i in range(1, 4)]
+
+    @staticmethod
+    def _parse_template_variable(template_str: str) -> str:
+        """
+        Extract the variable name from a template string.
+
+        Args:
+            template_str (str): Jinja template string
+
+        Returns:
+            str: Name of the first undefined variable in the template
+
+        >>> QuestionOptionProcessor._parse_template_variable("Here are some {{ options }}")
+        'options'
+        >>> QuestionOptionProcessor._parse_template_variable("Here are some {{ options }} and {{ other }}")
+        Traceback (most recent call last):
+        ...
+        ValueError: Multiple variables found in template string
+        >>> QuestionOptionProcessor._parse_template_variable("Here are some")
+        Traceback (most recent call last):
+        ...
+        ValueError: No variables found in template string
+        """
+        env = Environment()
+        parsed_content = env.parse(template_str)
+        undeclared_variables = list(meta.find_undeclared_variables(parsed_content))
+        if not undeclared_variables:
+            raise ValueError("No variables found in template string")
+        if len(undeclared_variables) > 1:
+            raise ValueError("Multiple variables found in template string")
+        return undeclared_variables[0]
+
+    @staticmethod
+    def _get_options_from_scenario(
+        scenario: dict, option_key: str
+    ) -> Union[list, None]:
+        """
+        Try to get options from scenario data.
+
+        >>> from edsl import Scenario
+        >>> scenario = Scenario({"options": ["Option 1", "Option 2"]})
+        >>> QuestionOptionProcessor._get_options_from_scenario(scenario, "options")
+        ['Option 1', 'Option 2']
+
+
+        Returns:
+            list | None: List of options if found in scenario, None otherwise
+        """
+        scenario_options = scenario.get(option_key)
+        return scenario_options if isinstance(scenario_options, list) else None
+
+    @staticmethod
+    def _get_options_from_prior_answers(
+        prior_answers: dict, option_key: str
+    ) -> Union[list, None]:
+        """
+        Try to get options from prior answers.
+
+        prior_answers (dict): Dictionary of prior answers
+        option_key (str): Key to look up in prior answers
+
+        >>> from edsl import QuestionList as Q
+        >>> q = Q.example()
+        >>> q.answer = ["Option 1", "Option 2"]
+        >>> prior_answers = {"options": q}
+        >>> QuestionOptionProcessor._get_options_from_prior_answers(prior_answers, "options")
+        ['Option 1', 'Option 2']
+        >>> QuestionOptionProcessor._get_options_from_prior_answers(prior_answers, "wrong_key") is None
+        True
+
+        Returns:
+            list | None: List of options if found in prior answers, None otherwise
+        """
+        prior_answer = prior_answers.get(option_key)
+        if prior_answer and hasattr(prior_answer, "answer"):
+            if isinstance(prior_answer.answer, list):
+                return prior_answer.answer
+        return None
+
+    def get_question_options(self, question_data: dict) -> list:
+        """
+        Extract and process question options from question data.
+
+        Args:
+            question_data (dict): Dictionary containing question configuration
+
+        Returns:
+            list: List of question options. Returns default placeholders if no valid options found.
+
+        >>> class MockPromptConstructor:
+        ...     pass
+        >>> mpc = MockPromptConstructor()
+        >>> from edsl import Scenario
+        >>> mpc.scenario = Scenario({"options": ["Option 1", "Option 2"]})
+        >>> processor = QuestionOptionProcessor(mpc)
+
+        The basic case where options are directly provided:
+
+        >>> question_data = {"question_options": ["Option 1", "Option 2"]}
+        >>> processor.get_question_options(question_data)
+        ['Option 1', 'Option 2']
+
+        The case where options are provided as a template string:
+
+        >>> question_data = {"question_options": "{{ options }}"}
+        >>> processor.get_question_options(question_data)
+        ['Option 1', 'Option 2']
+
+        The case where there is a templace string but it's in the prior answers:
+
+        >>> class MockQuestion:
+        ...     pass
+        >>> q0 = MockQuestion()
+        >>> q0.answer = ["Option 1", "Option 2"]
+        >>> mpc.prior_answers_dict = lambda: {'q0': q0}
+        >>> processor = QuestionOptionProcessor(mpc)
+        >>> question_data = {"question_options": "{{ q0 }}"}
+        >>> processor.get_question_options(question_data)
+        ['Option 1', 'Option 2']
+
+        The case we're no options are found:
+        >>> processor.get_question_options({"question_options": "{{ poop }}"})
+        ['<< Option 1 - Placeholder >>', '<< Option 2 - Placeholder >>', '<< Option 3 - Placeholder >>']
+
+        """
+        options_entry = question_data.get("question_options")
+
+        # If not a template string, return as is or default
+        if not isinstance(options_entry, str):
+            return options_entry if options_entry else self._get_default_options()
+
+        # Parse template to get variable name
+        option_key = self._parse_template_variable(options_entry)
+
+        # Try getting options from scenario
+        scenario_options = self._get_options_from_scenario(
+            self.prompt_constructor.scenario, option_key
+        )
+        if scenario_options:
+            return scenario_options
+
+        # Try getting options from prior answers
+        prior_answer_options = self._get_options_from_prior_answers(
+            self.prompt_constructor.prior_answers_dict(), option_key
+        )
+        if prior_answer_options:
+            return prior_answer_options
+
+        return self._get_default_options()
+
+
+if __name__ == "__main__":
+    import doctest
+
+    doctest.testmod()