edsl 0.1.31.dev1__py3-none-any.whl → 0.1.31.dev2__py3-none-any.whl

edsl/__version__.py

@@ -1 +1 @@
-__version__ = "0.1.31.dev1"
+__version__ = "0.1.31.dev2"

edsl/agents/PromptConstructionMixin.py

@@ -275,8 +275,20 @@ class PromptConstructorMixin:
                     if (new_question := question.split("_comment")[0]) in d:
                         d[new_question].comment = answer
 
+            question_data = self.question.data.copy()
+
+            # check to see if the questio_options is actuall a string
+            if "question_options" in question_data:
+                if isinstance(self.question.data["question_options"], str):
+                    from jinja2 import Environment, meta
+                    env = Environment()
+                    parsed_content = env.parse(self.question.data['question_options'])
+                    question_option_key = list(meta.find_undeclared_variables(parsed_content))[0]
+                    question_data["question_options"] = self.scenario.get(question_option_key)   
+
+            #breakpoint()        
             rendered_instructions = question_prompt.render(
-                self.question.data | self.scenario | d | {"agent": self.agent}
+                question_data | self.scenario | d | {"agent": self.agent}
             )
 
             undefined_template_variables = (

edsl/inference_services/InferenceServicesCollection.py

@@ -21,7 +21,10 @@ class InferenceServicesCollection:
             service_models = service.available()
         except Exception as e:
             warnings.warn(
-                f"Error getting models for {service._inference_service_}. Relying on cache.",
+                f"""Error getting models for {service._inference_service_}. 
+                Check that you have properly stored your Expected Parrot API key and activated remote inference, or stored your own API keys for the language models that you want to use.
+                See https://docs.expectedparrot.com/en/latest/api_keys.html for instructions on storing API keys.
+                Relying on cache.""",
                 UserWarning,
             )
             from edsl.inference_services.models_available_cache import models_available

edsl/jobs/Jobs.py

@@ -3,9 +3,7 @@ from __future__ import annotations
 import warnings
 from itertools import product
 from typing import Optional, Union, Sequence, Generator
-
 from edsl.Base import Base
-
 from edsl.exceptions import MissingAPIKeyError
 from edsl.jobs.buckets.BucketCollection import BucketCollection
 from edsl.jobs.interviews.Interview import Interview
@@ -461,12 +459,11 @@ class Jobs(Base):
             remote_inference = False
 
         if remote_inference:
-            from edsl.agents.Agent import Agent
-            from edsl.language_models.registry import Model
-            from edsl.results.Result import Result
-            from edsl.results.Results import Results
-            from edsl.scenarios.Scenario import Scenario
-            from edsl.surveys.Survey import Survey
+            import time
+            from datetime import datetime
+            from edsl.config import CONFIG
+
+            expected_parrot_url = CONFIG.get("EXPECTED_PARROT_URL")
 
             self._output("Remote inference activated. Sending job to server...")
             if remote_cache:
@@ -474,33 +471,59 @@ class Jobs(Base):
                     "Remote caching activated. The remote cache will be used for this job."
                 )
 
-            remote_job_data = coop.remote_inference_create(
+            remote_job_creation_data = coop.remote_inference_create(
                 self,
                 description=remote_inference_description,
                 status="queued",
             )
-            self._output("Job sent!")
-            # Create mock results object to store job data
-            results = Results(
-                survey=Survey(),
-                data=[
-                    Result(
-                        agent=Agent.example(),
-                        scenario=Scenario.example(),
-                        model=Model(),
-                        iteration=1,
-                        answer={"info": "Remote job details"},
+            time_queued = datetime.now().strftime("%m/%d/%Y %I:%M:%S %p")
+            job_uuid = remote_job_creation_data.get("uuid")
+            print(f"Remote inference started (Job uuid={job_uuid}).")
+            # print(f"Job queued at {time_queued}.")
+            job_in_queue = True
+            while job_in_queue:
+                remote_job_data = coop.remote_inference_get(job_uuid)
+                status = remote_job_data.get("status")
+                if status == "cancelled":
+                    print("\r" + " " * 80 + "\r", end="")
+                    print("Job cancelled by the user.")
+                    print(
+                        f"See {expected_parrot_url}/home/remote-inference for more details."
                     )
-                ],
-            )
-            results.add_columns_from_dict([remote_job_data])
-            if self.verbose:
-                results.select(["info", "uuid", "status", "version"]).print(
-                    format="rich"
-                )
-            return results
+                    return None
+                elif status == "failed":
+                    print("\r" + " " * 80 + "\r", end="")
+                    print("Job failed.")
+                    print(
+                        f"See {expected_parrot_url}/home/remote-inference for more details."
+                    )
+                    return None
+                elif status == "completed":
+                    results_uuid = remote_job_data.get("results_uuid")
+                    results = coop.get(results_uuid, expected_object_type="results")
+                    print("\r" + " " * 80 + "\r", end="")
+                    print(
+                        f"Job completed and Results stored on Coop (Results uuid={results_uuid})."
+                    )
+                    return results
+                else:
+                    duration = 10 if len(self) < 10 else 60
+                    time_checked = datetime.now().strftime("%Y-%m-%d %I:%M:%S %p")
+                    frames = ["⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏"]
+                    start_time = time.time()
+                    i = 0
+                    while time.time() - start_time < duration:
+                        print(
+                            f"\r{frames[i % len(frames)]} Job status: {status} - last update: {time_checked}",
+                            end="",
+                            flush=True,
+                        )
+                        time.sleep(0.1)
+                        i += 1
         else:
             if check_api_keys:
+                from edsl import Model
+
                 for model in self.models + [Model()]:
                     if not model.has_valid_api_key():
                         raise MissingAPIKeyError(

edsl/language_models/LanguageModel.py

@@ -7,9 +7,35 @@ import asyncio
 import json
 import time
 import os
+import hashlib
 from typing import Coroutine, Any, Callable, Type, List, get_type_hints
 from abc import ABC, abstractmethod
 
+class IntendedModelCallOutcome:
+    "This is a tuple-like class that holds the response, cache_used, and cache_key."
+
+    def __init__(self, response: dict, cache_used: bool, cache_key: str):
+        self.response = response
+        self.cache_used = cache_used
+        self.cache_key = cache_key
+
+    def __iter__(self):
+        """Iterate over the class attributes.
+        
+        >>> a, b, c = IntendedModelCallOutcome({'answer': "yes"}, True, 'x1289')
+        >>> a
+        {'answer': 'yes'}
+        """
+        yield self.response
+        yield self.cache_used
+        yield self.cache_key
+
+    def __len__(self):
+        return 3
+    
+    def __repr__(self):
+        return f"IntendedModelCallOutcome(response = {self.response}, cache_used = {self.cache_used}, cache_key = '{self.cache_key}')"
+
 from edsl.config import CONFIG
 
 from edsl.utilities.decorators import sync_wrapper, jupyter_nb_handler
@@ -149,7 +175,7 @@ class LanguageModel(
         key_value = os.getenv(key_name)
         return key_value is not None
 
-    def __hash__(self):
+    def __hash__(self) -> str:
         """Allow the model to be used as a key in a dictionary."""
         from edsl.utilities.utilities import dict_hash
 
@@ -176,6 +202,8 @@ class LanguageModel(
         """
         self._set_rate_limits(rpm=rpm, tpm=tpm)
 
+        
+
     def _set_rate_limits(self, rpm=None, tpm=None) -> None:
         """Set the rate limits for the model.
 
@@ -216,19 +244,23 @@ class LanguageModel(
         >>> LanguageModel._overide_default_parameters(passed_parameter_dict={"temperature": 0.5}, default_parameter_dict={"temperature":0.9, "max_tokens": 1000})
         {'temperature': 0.5, 'max_tokens': 1000}
         """
-        parameters = dict({})
-        for parameter, default_value in default_parameter_dict.items():
-            if parameter in passed_parameter_dict:
-                parameters[parameter] = passed_parameter_dict[parameter]
-            else:
-                parameters[parameter] = default_value
-        return parameters
-
+        #parameters = dict({})
+
+        return {parameter_name: passed_parameter_dict.get(parameter_name, default_value) 
+                for parameter_name, default_value in default_parameter_dict.items()}
+    
+    def __call__(self, user_prompt:str, system_prompt:str):
+        return self.execute_model_call(user_prompt, system_prompt)
+    
     @abstractmethod
     async def async_execute_model_call(user_prompt: str, system_prompt: str):
-        """Execute the model call and returns the result as a coroutine.
+        """Execute the model call and returns a coroutine.
 
         >>> m = LanguageModel.example(test_model = True)
+        >>> async def test(): return await m.async_execute_model_call("Hello, model!", "You are a helpful agent.")
+        >>> asyncio.run(test())
+        {'message': '{"answer": "Hello world"}'}
+
         >>> m.execute_model_call("Hello, model!", "You are a helpful agent.")
         {'message': '{"answer": "Hello world"}'}
 
@@ -274,10 +306,37 @@ class LanguageModel(
 
         What is returned by the API is model-specific and often includes meta-data that we do not need.
         For example, here is the results from a call to GPT-4:
-        To actually tract the response, we need to grab
+        To actually track the response, we need to grab
         data["choices[0]"]["message"]["content"].
         """
         raise NotImplementedError
+    
+    async def _async_prepare_response(self, model_call_outcome: IntendedModelCallOutcome, cache: "Cache") -> dict:
+        """Prepare the response for return."""
+
+        model_response = {
+            "cache_used": model_call_outcome.cache_used,
+            "cache_key": model_call_outcome.cache_key,
+            "usage": model_call_outcome.response.get("usage", {}),
+            "raw_model_response": model_call_outcome.response,
+        }
+
+        answer_portion = self.parse_response(model_call_outcome.response)  
+        try:
+            answer_dict = json.loads(answer_portion)
+        except json.JSONDecodeError as e:
+            # TODO: Turn into logs to generate issues
+            answer_dict, success = await repair(
+                bad_json=answer_portion, 
+                error_message=str(e), 
+                cache=cache
+            )
+            if not success:
+                raise Exception(
+                    f"""Even the repair failed. The error was: {e}. The response was: {answer_portion}."""
+                )
+    
+        return {**model_response, **answer_dict}
 
     async def async_get_raw_response(
         self,
@@ -286,7 +345,26 @@ class LanguageModel(
         cache: "Cache",
         iteration: int = 0,
         encoded_image=None,
-    ) -> tuple[dict, bool, str]:
+    ) -> IntendedModelCallOutcome:
+        import warnings
+        warnings.warn("This method is deprecated. Use async_get_intended_model_call_outcome.")
+        return await self._async_get_intended_model_call_outcome(
+            user_prompt=user_prompt,
+            system_prompt=system_prompt,
+            cache=cache,
+            iteration=iteration,
+            encoded_image=encoded_image
+        )
+
+
+    async def _async_get_intended_model_call_outcome(
+        self,
+        user_prompt: str,
+        system_prompt: str,
+        cache: "Cache",
+        iteration: int = 0,
+        encoded_image=None,
+    ) -> IntendedModelCallOutcome:
         """Handle caching of responses.
 
         :param user_prompt: The user's prompt.
@@ -304,52 +382,41 @@ class LanguageModel(
 
         >>> from edsl import Cache
         >>> m = LanguageModel.example(test_model = True)
-        >>> m.get_raw_response(user_prompt = "Hello", system_prompt = "hello", cache = Cache())
-        ({'message': '{"answer": "Hello world"}'}, False, '24ff6ac2bc2f1729f817f261e0792577')
+        >>> m._get_intended_model_call_outcome(user_prompt = "Hello", system_prompt = "hello", cache = Cache())
+        IntendedModelCallOutcome(response = {'message': '{"answer": "Hello world"}'}, cache_used = False, cache_key = '24ff6ac2bc2f1729f817f261e0792577')
         """
-        start_time = time.time()
+
+        if encoded_image:
+            # the image has is appended to the user_prompt for hash-lookup purposes
+            image_hash = hashlib.md5(encoded_image.encode()).hexdigest()
 
         cache_call_params = {
             "model": str(self.model),
             "parameters": self.parameters,
             "system_prompt": system_prompt,
-            "user_prompt": user_prompt,
+            "user_prompt": user_prompt + "" if not encoded_image else f" {image_hash}",
             "iteration": iteration,
         }
-
-        if encoded_image:
-            import hashlib
-
-            image_hash = hashlib.md5(encoded_image.encode()).hexdigest()
-            cache_call_params["user_prompt"] = f"{user_prompt} {image_hash}"
-
         cached_response, cache_key = cache.fetch(**cache_call_params)
-        if cached_response:
+    
+        if (cache_used := cached_response is not None):
             response = json.loads(cached_response)
-            cache_used = True
         else:
-            remote_call = hasattr(self, "remote") and self.remote
             f = (
                 self.remote_async_execute_model_call
-                if remote_call
+                if hasattr(self, "remote") and self.remote
                 else self.async_execute_model_call
             )
-            params = {"user_prompt": user_prompt, "system_prompt": system_prompt}
-            if encoded_image:
-                params["encoded_image"] = encoded_image
+            params = {"user_prompt": user_prompt, "system_prompt": system_prompt, 
+            **({"encoded_image": encoded_image} if encoded_image else {})
+            }
             response = await f(**params)
-            new_cache_key = cache.store(
-                user_prompt=user_prompt,
-                model=str(self.model),
-                parameters=self.parameters,
-                system_prompt=system_prompt,
-                response=response,
-                iteration=iteration,
-            )
-            assert new_cache_key == cache_key
-            cache_used = False
+            new_cache_key = cache.store(**cache_call_params, response=response) # store the response in the cache
+            assert new_cache_key == cache_key # should be the same
+     
+        return IntendedModelCallOutcome(response = response, cache_used = cache_used, cache_key = cache_key)
 
-        return response, cache_used, cache_key
+    _get_intended_model_call_outcome = sync_wrapper(_async_get_intended_model_call_outcome)
 
     get_raw_response = sync_wrapper(async_get_raw_response)
 
@@ -370,7 +437,7 @@ class LanguageModel(
         self,
         user_prompt: str,
         system_prompt: str,
-        cache: Cache,
+        cache: 'Cache',
         iteration: int = 1,
         encoded_image=None,
     ) -> dict:
@@ -388,36 +455,10 @@ class LanguageModel(
             "system_prompt": system_prompt,
             "iteration": iteration,
             "cache": cache,
-        }
-        if encoded_image:
-            params["encoded_image"] = encoded_image
-
-        raw_response, cache_used, cache_key = await self.async_get_raw_response(
-            **params
-        )
-        response = self.parse_response(raw_response)
-
-        try:
-            dict_response = json.loads(response)
-        except json.JSONDecodeError as e:
-            # TODO: Turn into logs to generate issues
-            dict_response, success = await repair(
-                bad_json=response, error_message=str(e), cache=cache
-            )
-            if not success:
-                raise Exception(
-                    f"""Even the repair failed. The error was: {e}. The response was: {response}."""
-                )
-
-        dict_response.update(
-            {
-                "cache_used": cache_used,
-                "cache_key": cache_key,
-                "usage": raw_response.get("usage", {}),
-                "raw_model_response": raw_response,
-            }
-        )
-        return dict_response
+            **({"encoded_image": encoded_image} if encoded_image else {})
+        }        
+        model_call_outcome = await self._async_get_intended_model_call_outcome(**params)
+        return await self._async_prepare_response(model_call_outcome, cache=cache)
 
     get_response = sync_wrapper(async_get_response)
 
@@ -543,8 +584,3 @@ if __name__ == "__main__":
     import doctest
 
     doctest.testmod(optionflags=doctest.ELLIPSIS)
-
-    # from edsl.language_models import LanguageModel
-
-    # from edsl.language_models import LanguageModel
-    # print(LanguageModel.example())

edsl/questions/QuestionMultipleChoice.py

@@ -96,6 +96,7 @@ class QuestionMultipleChoice(QuestionBase):
             question_option_key = list(meta.find_undeclared_variables(parsed_content))[
                 0
             ]
+            #breakpoint()
             translated_options = scenario.get(question_option_key)
         else:
             translated_options = [

{edsl-0.1.31.dev1.dist-info → edsl-0.1.31.dev2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: edsl
-Version: 0.1.31.dev1
+Version: 0.1.31.dev2
 Summary: Create and analyze LLM-based surveys
 Home-page: https://www.expectedparrot.com/
 License: MIT
@@ -22,7 +22,7 @@ Requires-Dist: black[jupyter] (>=24.4.2,<25.0.0)
 Requires-Dist: jinja2 (>=3.1.2,<4.0.0)
 Requires-Dist: jupyter (>=1.0.0,<2.0.0)
 Requires-Dist: markdown2 (>=2.4.11,<3.0.0)
-Requires-Dist: matplotlib (>=3.8.4,<4.0.0)
+Requires-Dist: matplotlib (>=3.8,<3.9)
 Requires-Dist: nest-asyncio (>=1.5.9,<2.0.0)
 Requires-Dist: numpy (>=1.22,<2.0)
 Requires-Dist: openai (>=1.4.0,<2.0.0)

{edsl-0.1.31.dev1.dist-info → edsl-0.1.31.dev2.dist-info}/RECORD

@@ -1,12 +1,12 @@
 edsl/Base.py,sha256=ttNxUotSd9LSEJl2w6LdMtT78d0nMQvYDJ0q4JkqBfg,8945
 edsl/BaseDiff.py,sha256=RoVEh52UJs22yMa7k7jv8se01G62jJNWnBzaZngo-Ug,8260
 edsl/__init__.py,sha256=E6PkWI_owu8AUc4uJs2XWDVozqSbcRWzsIqf8_Kskho,1631
-edsl/__version__.py,sha256=muI5jd-fDNbXxztFFWI5wdZkX6SVhOtKL4K3XxztZsg,28
+edsl/__version__.py,sha256=BN1dLwi4HgyXIf5fxZomtYU3o3qkECZEfi25Xh6EtA4,28
 edsl/agents/Agent.py,sha256=qNJsQkN6HuTKqJrQbuUEgRX3Wo7Dwukle0oNWPi0UIE,27191
 edsl/agents/AgentList.py,sha256=_MsdeOEgaANAceLIXwuLC22mwlBn0ruGX4GEqz8_SSY,9467
 edsl/agents/Invigilator.py,sha256=WNgGT9VRKpHbk__h-vd4LASgjnlJnzepf-2FxQ3K98I,10798
 edsl/agents/InvigilatorBase.py,sha256=ncha1HF2V1Dz4f50Gekg6AzUXCD2Af82ztfSJZbgOHY,7469
-edsl/agents/PromptConstructionMixin.py,sha256=MP2Frmm9iP3J50ijXKrr6YYIjB_38UuA2J7Mysfs0ZQ,15913
+edsl/agents/PromptConstructionMixin.py,sha256=uqk5SfGbvI191eda44bUtYHL7N0xEAxx64ga59SB610,16576
 edsl/agents/__init__.py,sha256=a3H1lxDwu9HR8fwh79C5DgxPSFv_bE2rzQ6y1D8Ba5c,80
 edsl/agents/descriptors.py,sha256=m8ND3-2-JbgNX1HGakBNLIeemwsgYa1mQxYO9GW33hw,2934
 edsl/base/Base.py,sha256=DShsfI6A2ojg42muPFpVtUgTX33pnqT5vtN0SRlr-9Q,8866
@@ -58,7 +58,7 @@ edsl/inference_services/AnthropicService.py,sha256=tjYRJRIvQ7Z6uCYdqxm5ZlVjZdVZC
 edsl/inference_services/DeepInfraService.py,sha256=fpjLJl7gyUFWVdR6U7XwIspD_pH5x55f4LamKT01Et4,3853
 edsl/inference_services/GoogleService.py,sha256=IwSwXr7khvHjpDzgiW5PRVKMhI2wQ9D1_H1MRnHjefU,2732
 edsl/inference_services/InferenceServiceABC.py,sha256=H6jW2gDKTLC3xgmqiSBdX4pGY1oauEO8VqGZoB3qvnQ,1790
-edsl/inference_services/InferenceServicesCollection.py,sha256=1ulvUYs2gaJsb7t8Mkua-6_3gff6rJmH72_BbItkaCE,2274
+edsl/inference_services/InferenceServicesCollection.py,sha256=7Q04aiJUWJx3zzjSY1uH7MkhrJi41RshU3Zy-6rM6kI,2596
 edsl/inference_services/OpenAIService.py,sha256=OvczbY2wlEehZdaaMq69yeqzkjdrbbXlP8uC9WjgHq0,6021
 edsl/inference_services/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 edsl/inference_services/models_available_cache.py,sha256=ZT2pBGxJqTgwynthu-SqBjv8zl7ql44q3gA6xy7kqSU,2338
@@ -66,7 +66,7 @@ edsl/inference_services/rate_limits_cache.py,sha256=HYslviz7mxF9U4CUTPAkoyBsiXjS
 edsl/inference_services/registry.py,sha256=-Yz86do-KZraunIrziVs9b95EbY-__JUnQb5Ulni7KI,483
 edsl/inference_services/write_available.py,sha256=NNwhATlaMp8IYY635MSx-oYxt5X15acjAfaqYCo_I1Y,285
 edsl/jobs/Answers.py,sha256=z4TADN-iHIrbMtI1jVyiaetv0OkTv768dFBpREIQC6c,1799
-edsl/jobs/Jobs.py,sha256=JrJcpTjR3wejMVvuFXZr7PHqCyj6zaRwqNu9eatvy9Y,29339
+edsl/jobs/Jobs.py,sha256=rd9wlx7f7Q0aF-toV6A4ps6hd73MEmB5UlQleRBzPoE,30737
 edsl/jobs/__init__.py,sha256=aKuAyd_GoalGj-k7djOoVwEbFUE2XLPlikXaA1_8yAg,32
 edsl/jobs/buckets/BucketCollection.py,sha256=LA8DBVwMdeTFCbSDI0S2cDzfi_Qo6kRizwrG64tE8S4,1844
 edsl/jobs/buckets/ModelBuckets.py,sha256=hxw_tzc0V42CiB7mh5jIxlgwDVJ-zFZhlLtKrHEg8ho,2419
@@ -93,7 +93,7 @@ edsl/jobs/tasks/task_management.py,sha256=KMToZuXzMlnHRHUF_VHL0-lHMTGhklf2GHVuwE
 edsl/jobs/tasks/task_status_enum.py,sha256=DOyrz61YlIS8R1W7izJNphcLrJ7I_ReUlfdRmk23h0Q,5333
 edsl/jobs/tokens/InterviewTokenUsage.py,sha256=u_6-IHpGFwZ6qMEXr24-jyLVUSSp4dSs_4iAZsBv7O4,1100
 edsl/jobs/tokens/TokenUsage.py,sha256=odj2-wDNEbHl9noyFAQ0DSKV0D9cv3aDOpmXufKZ8O4,1323
-edsl/language_models/LanguageModel.py,sha256=cou6R-oNYk-_C8vfCQMkaeUbbAFEtBcG4d5lTZKN0YI,19082
+edsl/language_models/LanguageModel.py,sha256=2TYZl1LM8kSrkf7wRvGy-OF8WIJHIOTlswdOM_ESkC4,20940
 edsl/language_models/ModelList.py,sha256=G8tzHqzz4exc28BGvGgVRk1Xwu8EDCiVWxMC5l8VnvI,2862
 edsl/language_models/RegisterLanguageModelsMeta.py,sha256=2bvWrVau2BRo-Bb1aO-QATH8xxuW_tF7NmqBMGDOfSg,8191
 edsl/language_models/__init__.py,sha256=bvY7Gy6VkX1gSbNkRbGPS-M1kUnb0EohL0FSagaEaTs,109
@@ -126,7 +126,7 @@ edsl/questions/QuestionExtract.py,sha256=fjnsNLS2fNW6dfFuRyc2EgKEHx8ujjONmg2nSRy
 edsl/questions/QuestionFreeText.py,sha256=ASj1s0EQYcZerJp476fscu_xEME8mKzVK3sPL6egiuU,3289
 edsl/questions/QuestionFunctional.py,sha256=jlC1eNE-kpp9o5CXKo-c3Re4PIq1_WmdJ66u9nD-W7w,4967
 edsl/questions/QuestionList.py,sha256=Wf7xDXJsQBsAD_yOrzZ_GstKGT7aZjimTkU6qyqOhhM,4051
-edsl/questions/QuestionMultipleChoice.py,sha256=C6FjGZxLESvpq76PjxbSR_yrrExJpEvF31JSbY1luuQ,6605
+edsl/questions/QuestionMultipleChoice.py,sha256=P1GR5Ml7ppk-xeJnlS7ZWctj5poR9NHZ3MPKrlKSync,6631
 edsl/questions/QuestionNumerical.py,sha256=QArFDhP9Adb4l6y-udnUqPNk2Q6vT4pGsY13TkHsLGs,3631
 edsl/questions/QuestionRank.py,sha256=NEAwDt1at0zEM2S-E7jXMjglnlB0WhUlxSVJkzH4xSs,5876
 edsl/questions/RegisterQuestionsMeta.py,sha256=unON0CKpW-mveyhg9V3_BF_GYYwytMYP9h2ZZPetVNM,1994
@@ -197,7 +197,7 @@ edsl/utilities/interface.py,sha256=AaKpWiwWBwP2swNXmnFlIf3ZFsjfsR5bjXQAW47tD-8,1
 edsl/utilities/repair_functions.py,sha256=tftmklAqam6LOQQu_-9U44N-llycffhW8LfO63vBmNw,929
 edsl/utilities/restricted_python.py,sha256=5-_zUhrNbos7pLhDl9nr8d24auRlquR6w-vKkmNjPiA,2060
 edsl/utilities/utilities.py,sha256=oU5Gg6szTGqsJ2yBOS0aC3XooezLE8By3SdrQLLpqvA,10107
-edsl-0.1.31.dev1.dist-info/LICENSE,sha256=_qszBDs8KHShVYcYzdMz3HNMtH-fKN_p5zjoVAVumFc,1111
-edsl-0.1.31.dev1.dist-info/METADATA,sha256=tsrurkFgZhvJzc-CO2ZiYEAoBmVHYyYgULThTH8kcWQ,4137
-edsl-0.1.31.dev1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-edsl-0.1.31.dev1.dist-info/RECORD,,
+edsl-0.1.31.dev2.dist-info/LICENSE,sha256=_qszBDs8KHShVYcYzdMz3HNMtH-fKN_p5zjoVAVumFc,1111
+edsl-0.1.31.dev2.dist-info/METADATA,sha256=gQlFRVjdYP2rKQ4GQvub6WC5FdqTorn0IwT_l3_WSrk,4133
+edsl-0.1.31.dev2.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+edsl-0.1.31.dev2.dist-info/RECORD,,