edsl 0.1.38.dev3__py3-none-any.whl → 0.1.39__py3-none-any.whl

edsl/agents/PromptConstructor.py

@@ -1,353 +1,272 @@
-from __future__ import annotations
-from typing import Dict, Any, Optional, Set
-
-from jinja2 import Environment, meta
-
-from edsl.prompts.Prompt import Prompt
-from edsl.agents.prompt_helpers import PromptPlan
-
-
-class PlaceholderAnswer:
-    """A placeholder answer for when a question is not yet answered."""
-
-    def __init__(self):
-        self.answer = "N/A"
-        self.comment = "Will be populated by prior answer"
-
-    def __getitem__(self, index):
-        return ""
-
-    def __str__(self):
-        return "<<PlaceholderAnswer>>"
-
-    def __repr__(self):
-        return "<<PlaceholderAnswer>>"
-
-
-def get_jinja2_variables(template_str: str) -> Set[str]:
-    """
-    Extracts all variable names from a Jinja2 template using Jinja2's built-in parsing.
-
-    Args:
-    template_str (str): The Jinja2 template string
-
-    Returns:
-    Set[str]: A set of variable names found in the template
-    """
-    env = Environment()
-    ast = env.parse(template_str)
-    return meta.find_undeclared_variables(ast)
-
-
-class PromptConstructor:
-    """
-    The pieces of a prompt are:
-    - The agent instructions - "You are answering questions as if you were a human. Do not break character."
-    - The persona prompt - "You are an agent with the following persona: {'age': 22, 'hair': 'brown', 'height': 5.5}"
-    - The question instructions - "You are being asked the following question: Do you like school? The options are 0: yes 1: no Return a valid JSON formatted like this, selecting only the number of the option: {"answer": <put answer code here>, "comment": "<put explanation here>"} Only 1 option may be selected."
-    - The memory prompt - "Before the question you are now answering, you already answered the following question(s): Question: Do you like school? Answer: Prior answer"
-
-    This is mixed into the Invigilator class.
-    """
-
-    def __init__(self, invigilator, prompt_plan: Optional["PromptPlan"] = None):
-        self.invigilator = invigilator
-        self.agent = invigilator.agent
-        self.question = invigilator.question
-        self.scenario = invigilator.scenario
-        self.survey = invigilator.survey
-        self.model = invigilator.model
-        self.current_answers = invigilator.current_answers
-        self.memory_plan = invigilator.memory_plan
-        self.prompt_plan = prompt_plan or PromptPlan()
-
-    @property
-    def scenario_file_keys(self) -> list:
-        """We need to find all the keys in the scenario that refer to FileStore objects.
-        These will be used to append to the prompt a list of files that are part of the scenario.
-        """
-        from edsl.scenarios.FileStore import FileStore
-
-        file_entries = []
-        for key, value in self.scenario.items():
-            if isinstance(value, FileStore):
-                file_entries.append(key)
-        return file_entries
-
-    @property
-    def agent_instructions_prompt(self) -> Prompt:
-        """
-        >>> from edsl.agents.InvigilatorBase import InvigilatorBase
-        >>> i = InvigilatorBase.example()
-        >>> i.prompt_constructor.agent_instructions_prompt
-        Prompt(text=\"""You are answering questions as if you were a human. Do not break character.\""")
-        """
-        from edsl import Agent
-
-        if self.agent == Agent():  # if agent is empty, then return an empty prompt
-            return Prompt(text="")
-
-        return Prompt(text=self.agent.instruction)
-
-    @property
-    def agent_persona_prompt(self) -> Prompt:
-        """
-        >>> from edsl.agents.InvigilatorBase import InvigilatorBase
-        >>> i = InvigilatorBase.example()
-        >>> i.prompt_constructor.agent_persona_prompt
-        Prompt(text=\"""Your traits: {'age': 22, 'hair': 'brown', 'height': 5.5}\""")
-        """
-        from edsl import Agent
-
-        if self.agent == Agent():  # if agent is empty, then return an empty prompt
-            return Prompt(text="")
-
-        return self.agent.prompt()
-
-    def prior_answers_dict(self) -> dict:
-        # this is all questions
-        d = self.survey.question_names_to_questions()
-        # This attaches the answer to the question
-        for question in d:
-            if question in self.current_answers:
-                d[question].answer = self.current_answers[question]
-            else:
-                d[question].answer = PlaceholderAnswer()
-
-                # if (new_question := question.split("_comment")[0]) in d:
-                #     d[new_question].comment = answer
-                # d[question].answer = PlaceholderAnswer()
-
-        # breakpoint()
-        return d
-
-    @property
-    def question_file_keys(self):
-        raw_question_text = self.question.question_text
-        variables = get_jinja2_variables(raw_question_text)
-        question_file_keys = []
-        for var in variables:
-            if var in self.scenario_file_keys:
-                question_file_keys.append(var)
-        return question_file_keys
-
-    def build_replacement_dict(self, question_data: dict):
-        """
-        Builds a dictionary of replacement values by combining multiple data sources.
-        """
-        # File references dictionary
-        file_refs = {key: f"<see file {key}>" for key in self.scenario_file_keys}
-
-        # Scenario items excluding file keys
-        scenario_items = {
-            k: v for k, v in self.scenario.items() if k not in self.scenario_file_keys
-        }
-
-        # Question settings with defaults
-        question_settings = {
-            "use_code": getattr(self.question, "_use_code", True),
-            "include_comment": getattr(self.question, "_include_comment", False),
-        }
-
-        # Combine all dictionaries using dict.update() for clarity
-        replacement_dict = {}
-        for d in [
-            file_refs,
-            question_data,
-            scenario_items,
-            self.prior_answers_dict(),
-            {"agent": self.agent},
-            question_settings,
-        ]:
-            replacement_dict.update(d)
-
-        return replacement_dict
-
-    def _get_question_options(self, question_data):
-        question_options_entry = question_data.get("question_options", None)
-        question_options = question_options_entry
-
-        placeholder = ["<< Option 1 - Placholder >>", "<< Option 2 - Placholder >>"]
-
-        if isinstance(question_options_entry, str):
-            env = Environment()
-            parsed_content = env.parse(question_options_entry)
-            question_option_key = list(meta.find_undeclared_variables(parsed_content))[
-                0
-            ]
-            if isinstance(self.scenario.get(question_option_key), list):
-                question_options = self.scenario.get(question_option_key)
-
-            # might be getting it from the prior answers
-            if self.prior_answers_dict().get(question_option_key) is not None:
-                prior_question = self.prior_answers_dict().get(question_option_key)
-                if hasattr(prior_question, "answer"):
-                    if isinstance(prior_question.answer, list):
-                        question_options = prior_question.answer
-                    else:
-                        question_options = placeholder
-                else:
-                    question_options = placeholder
-
-        return question_options
-
-    def build_question_instructions_prompt(self):
-        """Buils the question instructions prompt."""
-
-        question_prompt = Prompt(self.question.get_instructions(model=self.model.model))
-
-        # Get the data for the question - this is a dictionary of the question data
-        # e.g., {'question_text': 'Do you like school?', 'question_name': 'q0', 'question_options': ['yes', 'no']}
-        question_data = self.question.data.copy()
-
-        if "question_options" in question_data:
-            question_options = self._get_question_options(question_data)
-            question_data["question_options"] = question_options
-
-        # check to see if the question_options is actually a string
-        # This is used when the user is using the question_options as a variable from a scenario
-        # if "question_options" in question_data:
-        replacement_dict = self.build_replacement_dict(question_data)
-        rendered_instructions = question_prompt.render(replacement_dict)
-
-        # is there anything left to render?
-        undefined_template_variables = (
-            rendered_instructions.undefined_template_variables({})
-        )
-
-        # Check if it's the name of a question in the survey
-        for question_name in self.survey.question_names:
-            if question_name in undefined_template_variables:
-                print(
-                    "Question name found in undefined_template_variables: ",
-                    question_name,
-                )
-
-        if undefined_template_variables:
-            msg = f"Question instructions still has variables: {undefined_template_variables}."
-            import warnings
-
-            warnings.warn(msg)
-            # raise QuestionScenarioRenderError(
-            #     f"Question instructions still has variables: {undefined_template_variables}."
-            # )
-
-        # Check if question has instructions - these are instructions in a Survey that can apply to multiple follow-on questions
-        relevant_instructions = self.survey.relevant_instructions(
-            self.question.question_name
-        )
-
-        if relevant_instructions != []:
-            # preamble_text = Prompt(
-            #    text="You were given the following instructions: "
-            # )
-            preamble_text = Prompt(text="")
-            for instruction in relevant_instructions:
-                preamble_text += instruction.text
-            rendered_instructions = preamble_text + rendered_instructions
-
-        return rendered_instructions
-
-    @property
-    def question_instructions_prompt(self) -> Prompt:
-        """
-        >>> from edsl.agents.InvigilatorBase import InvigilatorBase
-        >>> i = InvigilatorBase.example()
-        >>> i.prompt_constructor.question_instructions_prompt
-        Prompt(text=\"""...
-        ...
-        """
-        if not hasattr(self, "_question_instructions_prompt"):
-            self._question_instructions_prompt = (
-                self.build_question_instructions_prompt()
-            )
-
-        return self._question_instructions_prompt
-
-    @property
-    def prior_question_memory_prompt(self) -> Prompt:
-        if not hasattr(self, "_prior_question_memory_prompt"):
-            from edsl.prompts.Prompt import Prompt
-
-            memory_prompt = Prompt(text="")
-            if self.memory_plan is not None:
-                memory_prompt += self.create_memory_prompt(
-                    self.question.question_name
-                ).render(self.scenario | self.prior_answers_dict())
-            self._prior_question_memory_prompt = memory_prompt
-        return self._prior_question_memory_prompt
-
-    def create_memory_prompt(self, question_name: str) -> Prompt:
-        """Create a memory for the agent.
-
-        The returns a memory prompt for the agent.
-
-        >>> from edsl.agents.InvigilatorBase import InvigilatorBase
-        >>> i = InvigilatorBase.example()
-        >>> i.current_answers = {"q0": "Prior answer"}
-        >>> i.memory_plan.add_single_memory("q1", "q0")
-        >>> p = i.prompt_constructor.create_memory_prompt("q1")
-        >>> p.text.strip().replace("\\n", " ").replace("\\t", " ")
-        'Before the question you are now answering, you already answered the following question(s):          Question: Do you like school?  Answer: Prior answer'
-        """
-        return self.memory_plan.get_memory_prompt_fragment(
-            question_name, self.current_answers
-        )
-
-    def construct_system_prompt(self) -> Prompt:
-        """Construct the system prompt for the LLM call."""
-        import warnings
-
-        warnings.warn(
-            "This method is deprecated. Use get_prompts instead.", DeprecationWarning
-        )
-        return self.get_prompts()["system_prompt"]
-
-    def construct_user_prompt(self) -> Prompt:
-        """Construct the user prompt for the LLM call."""
-        import warnings
-
-        warnings.warn(
-            "This method is deprecated. Use get_prompts instead.", DeprecationWarning
-        )
-        return self.get_prompts()["user_prompt"]
-
-    def get_prompts(self) -> Dict[str, Prompt]:
-        """Get both prompts for the LLM call.
-
-        >>> from edsl import QuestionFreeText
-        >>> from edsl.agents.InvigilatorBase import InvigilatorBase
-        >>> q = QuestionFreeText(question_text="How are you today?", question_name="q_new")
-        >>> i = InvigilatorBase.example(question = q)
-        >>> i.get_prompts()
-        {'user_prompt': ..., 'system_prompt': ...}
-        """
-        # breakpoint()
-        prompts = self.prompt_plan.get_prompts(
-            agent_instructions=self.agent_instructions_prompt,
-            agent_persona=self.agent_persona_prompt,
-            question_instructions=Prompt(self.question_instructions_prompt),
-            prior_question_memory=self.prior_question_memory_prompt,
-        )
-        if self.question_file_keys:
-            files_list = []
-            for key in self.question_file_keys:
-                files_list.append(self.scenario[key])
-            prompts["files_list"] = files_list
-        return prompts
-
-    def _get_scenario_with_image(self) -> Scenario:
-        """This is a helper function to get a scenario with an image, for testing purposes."""
-        from edsl import Scenario
-
-        try:
-            scenario = Scenario.from_image("../../static/logo.png")
-        except FileNotFoundError:
-            scenario = Scenario.from_image("static/logo.png")
-        return scenario
-
-
-if __name__ == "__main__":
-    import doctest
-
-    doctest.testmod(optionflags=doctest.ELLIPSIS)
+from __future__ import annotations
+from typing import Dict, Any, Optional, Set, Union, TYPE_CHECKING
+from functools import cached_property
+
+from edsl.prompts.Prompt import Prompt
+
+from dataclasses import dataclass
+
+from .prompt_helpers import PromptPlan
+from .QuestionTemplateReplacementsBuilder import (
+    QuestionTemplateReplacementsBuilder,
+)
+from .question_option_processor import QuestionOptionProcessor
+
+if TYPE_CHECKING:
+    from edsl.agents.InvigilatorBase import InvigilatorBase
+    from edsl.questions.QuestionBase import QuestionBase
+    from edsl.agents.Agent import Agent
+    from edsl.surveys.Survey import Survey
+    from edsl.language_models.LanguageModel import LanguageModel
+    from edsl.surveys.MemoryPlan import MemoryPlan
+    from edsl.questions.QuestionBase import QuestionBase
+    from edsl.scenarios.Scenario import Scenario
+
+
+class BasePlaceholder:
+    """Base class for placeholder values when a question is not yet answered."""
+
+    def __init__(self, placeholder_type: str = "answer"):
+        self.value = "N/A"
+        self.comment = "Will be populated by prior answer"
+        self._type = placeholder_type
+
+    def __getitem__(self, index):
+        return ""
+
+    def __str__(self):
+        return f"<<{self.__class__.__name__}:{self._type}>>"
+
+    def __repr__(self):
+        return self.__str__()
+
+
+class PlaceholderAnswer(BasePlaceholder):
+    def __init__(self):
+        super().__init__("answer")
+
+
+class PlaceholderComment(BasePlaceholder):
+    def __init__(self):
+        super().__init__("comment")
+
+
+class PlaceholderGeneratedTokens(BasePlaceholder):
+    def __init__(self):
+        super().__init__("generated_tokens")
+
+
+class PromptConstructor:
+    """
+    This class constructs the prompts for the language model.
+
+    The pieces of a prompt are:
+    - The agent instructions - "You are answering questions as if you were a human. Do not break character."
+    - The persona prompt - "You are an agent with the following persona: {'age': 22, 'hair': 'brown', 'height': 5.5}"
+    - The question instructions - "You are being asked the following question: Do you like school? The options are 0: yes 1: no Return a valid JSON formatted like this, selecting only the number of the option: {"answer": <put answer code here>, "comment": "<put explanation here>"} Only 1 option may be selected."
+    - The memory prompt - "Before the question you are now answering, you already answered the following question(s): Question: Do you like school? Answer: Prior answer"
+    """
+
+    def __init__(
+        self, invigilator: "InvigilatorBase", prompt_plan: Optional["PromptPlan"] = None
+    ):
+        self.invigilator = invigilator
+        self.prompt_plan = prompt_plan or PromptPlan()
+
+        self.agent = invigilator.agent
+        self.question = invigilator.question
+        self.scenario = invigilator.scenario
+        self.survey = invigilator.survey
+        self.model = invigilator.model
+        self.current_answers = invigilator.current_answers
+        self.memory_plan = invigilator.memory_plan
+
+    def get_question_options(self, question_data):
+        """Get the question options."""
+        return QuestionOptionProcessor(self).get_question_options(question_data)
+
+    @cached_property
+    def agent_instructions_prompt(self) -> Prompt:
+        """
+        >>> from edsl.agents.InvigilatorBase import InvigilatorBase
+        >>> i = InvigilatorBase.example()
+        >>> i.prompt_constructor.agent_instructions_prompt
+        Prompt(text=\"""You are answering questions as if you were a human. Do not break character.\""")
+        """
+        from edsl.agents.Agent import Agent
+
+        if self.agent == Agent():  # if agent is empty, then return an empty prompt
+            return Prompt(text="")
+
+        return Prompt(text=self.agent.instruction)
+
+    @cached_property
+    def agent_persona_prompt(self) -> Prompt:
+        """
+        >>> from edsl.agents.InvigilatorBase import InvigilatorBase
+        >>> i = InvigilatorBase.example()
+        >>> i.prompt_constructor.agent_persona_prompt
+        Prompt(text=\"""Your traits: {'age': 22, 'hair': 'brown', 'height': 5.5}\""")
+        """
+        from edsl.agents.Agent import Agent
+
+        if self.agent == Agent():  # if agent is empty, then return an empty prompt
+            return Prompt(text="")
+
+        return self.agent.prompt()
+
+    def prior_answers_dict(self) -> dict[str, "QuestionBase"]:
+        """This is a dictionary of prior answers, if they exist."""
+        return self._add_answers(
+            self.survey.question_names_to_questions(), self.current_answers
+        )
+
+    @staticmethod
+    def _extract_quetion_and_entry_type(key_entry) -> tuple[str, str]:
+        """
+        Extracts the question name and type for the current answer dictionary key entry.
+
+        >>> PromptConstructor._extract_quetion_and_entry_type("q0")
+        ('q0', 'answer')
+        >>> PromptConstructor._extract_quetion_and_entry_type("q0_comment")
+        ('q0', 'comment')
+        >>> PromptConstructor._extract_quetion_and_entry_type("q0_alternate_generated_tokens")
+        ('q0_alternate', 'generated_tokens')
+        >>> PromptConstructor._extract_quetion_and_entry_type("q0_alt_comment")
+        ('q0_alt', 'comment')
+        """
+        split_list = key_entry.rsplit("_", maxsplit=1)
+        if len(split_list) == 1:
+            question_name = split_list[0]
+            entry_type = "answer"
+        else:
+            if split_list[1] == "comment":
+                question_name = split_list[0]
+                entry_type = "comment"
+            elif split_list[1] == "tokens":  # it's actually 'generated_tokens'
+                question_name = key_entry.replace("_generated_tokens", "")
+                entry_type = "generated_tokens"
+            else:
+                question_name = key_entry
+                entry_type = "answer"
+        return question_name, entry_type
+
+    @staticmethod
+    def _augmented_answers_dict(current_answers: dict) -> dict:
+        """
+        >>> PromptConstructor._augmented_answers_dict({"q0": "LOVE IT!", "q0_comment": "I love school!"})
+        {'q0': {'answer': 'LOVE IT!', 'comment': 'I love school!'}}
+        """
+        from collections import defaultdict
+
+        d = defaultdict(dict)
+        for key, value in current_answers.items():
+            question_name, entry_type = (
+                PromptConstructor._extract_quetion_and_entry_type(key)
+            )
+            d[question_name][entry_type] = value
+        return dict(d)
+
+    @staticmethod
+    def _add_answers(
+        answer_dict: dict, current_answers: dict
+    ) -> dict[str, "QuestionBase"]:
+        """
+        >>> from edsl import QuestionFreeText
+        >>> d = {"q0": QuestionFreeText(question_text="Do you like school?", question_name = "q0")}
+        >>> current_answers = {"q0": "LOVE IT!"}
+        >>> PromptConstructor._add_answers(d, current_answers)['q0'].answer
+        'LOVE IT!'
+        """
+        augmented_answers = PromptConstructor._augmented_answers_dict(current_answers)
+
+        for question in answer_dict:
+            if question in augmented_answers:
+                for entry_type, value in augmented_answers[question].items():
+                    setattr(answer_dict[question], entry_type, value)
+            else:
+                answer_dict[question].answer = PlaceholderAnswer()
+                answer_dict[question].comment = PlaceholderComment()
+                answer_dict[question].generated_tokens = PlaceholderGeneratedTokens()
+        return answer_dict
+
+    @cached_property
+    def question_file_keys(self) -> list:
+        """Extracts the file keys from the question text.
+        It checks if the variables in the question text are in the scenario file keys.
+        """
+        return QuestionTemplateReplacementsBuilder(self).question_file_keys()
+
+    @cached_property
+    def question_instructions_prompt(self) -> Prompt:
+        """
+        >>> from edsl.agents.InvigilatorBase import InvigilatorBase
+        >>> i = InvigilatorBase.example()
+        >>> i.prompt_constructor.question_instructions_prompt
+        Prompt(text=\"""...
+        ...
+        """
+        return self.build_question_instructions_prompt()
+
+    def build_question_instructions_prompt(self) -> Prompt:
+        """Buils the question instructions prompt."""
+        from edsl.agents.QuestionInstructionPromptBuilder import (
+            QuestionInstructionPromptBuilder,
+        )
+
+        return QuestionInstructionPromptBuilder(self).build()
+
+    @cached_property
+    def prior_question_memory_prompt(self) -> Prompt:
+        memory_prompt = Prompt(text="")
+        if self.memory_plan is not None:
+            memory_prompt += self.create_memory_prompt(
+                self.question.question_name
+            ).render(self.scenario | self.prior_answers_dict())
+        return memory_prompt
+
+    def create_memory_prompt(self, question_name: str) -> Prompt:
+        """Create a memory for the agent.
+
+        The returns a memory prompt for the agent.
+
+        >>> from edsl.agents.InvigilatorBase import InvigilatorBase
+        >>> i = InvigilatorBase.example()
+        >>> i.current_answers = {"q0": "Prior answer"}
+        >>> i.memory_plan.add_single_memory("q1", "q0")
+        >>> p = i.prompt_constructor.create_memory_prompt("q1")
+        >>> p.text.strip().replace("\\n", " ").replace("\\t", " ")
+        'Before the question you are now answering, you already answered the following question(s):          Question: Do you like school?  Answer: Prior answer'
+        """
+        return self.memory_plan.get_memory_prompt_fragment(
+            question_name, self.current_answers
+        )
+
+    def get_prompts(self) -> Dict[str, Prompt]:
+        """Get both prompts for the LLM call.
+
+        >>> from edsl import QuestionFreeText
+        >>> from edsl.agents.InvigilatorBase import InvigilatorBase
+        >>> q = QuestionFreeText(question_text="How are you today?", question_name="q_new")
+        >>> i = InvigilatorBase.example(question = q)
+        >>> i.get_prompts()
+        {'user_prompt': ..., 'system_prompt': ...}
+        """
+        prompts = self.prompt_plan.get_prompts(
+            agent_instructions=self.agent_instructions_prompt,
+            agent_persona=self.agent_persona_prompt,
+            question_instructions=Prompt(self.question_instructions_prompt),
+            prior_question_memory=self.prior_question_memory_prompt,
+        )
+        if self.question_file_keys:
+            files_list = []
+            for key in self.question_file_keys:
+                files_list.append(self.scenario[key])
+            prompts["files_list"] = files_list
+        return prompts
+
+
+if __name__ == "__main__":
+    import doctest
+
+    doctest.testmod(optionflags=doctest.ELLIPSIS)