edsl 0.1.31.dev4__py3-none-any.whl → 0.1.33__py3-none-any.whl

edsl/jobs/runners/JobsRunnerStatusMixin.py

@@ -1,303 +0,0 @@
-from __future__ import annotations
-from typing import List, DefaultDict
-import asyncio
-from typing import Type
-from collections import defaultdict
-
-from typing import Literal, List, Type, DefaultDict
-from collections import UserDict, defaultdict
-
-from edsl.jobs.interviews.InterviewStatusDictionary import InterviewStatusDictionary
-from edsl.jobs.tokens.InterviewTokenUsage import InterviewTokenUsage
-from edsl.jobs.tokens.TokenUsage import TokenUsage
-from edsl.enums import get_token_pricing
-from edsl.jobs.tasks.task_status_enum import TaskStatus
-
-InterviewTokenUsageMapping = DefaultDict[str, InterviewTokenUsage]
-
-from edsl.jobs.interviews.InterviewStatistic import InterviewStatistic
-from edsl.jobs.interviews.InterviewStatisticsCollection import (
-    InterviewStatisticsCollection,
-)
-from edsl.jobs.tokens.InterviewTokenUsage import InterviewTokenUsage
-
-
-#return {"cache_status": token_usage_type, "details": details, "cost": f"${token_usage.cost(prices):.5f}"}
-
-from dataclasses import dataclass, asdict
-
-from rich.text import Text
-from rich.box import SIMPLE
-from rich.table import Table
-
-@dataclass
-class ModelInfo:
-    model_name: str
-    TPM_limit_k: float
-    RPM_limit_k: float
-    num_tasks_waiting: int
-    token_usage_info: dict
-
-
-@dataclass
-class ModelTokenUsageStats:
-    token_usage_type: str
-    details: List[dict]
-    cost: str
-
-class Stats:
-
-    def elapsed_time(self):
-        InterviewStatistic(
-                "elapsed_time", value=elapsed_time, digits=1, units="sec."
-            )
-
-
-
-
-class JobsRunnerStatusMixin:
-
-    # @staticmethod
-    # def status_dict(interviews: List[Type["Interview"]]) -> List[Type[InterviewStatusDictionary]]:
-    #     """
-    #     >>> from edsl.jobs.interviews.Interview import Interview
-    #     >>> interviews = [Interview.example()]
-    #     >>> JobsRunnerStatusMixin().status_dict(interviews)
-    #     [InterviewStatusDictionary({<TaskStatus.NOT_STARTED: 1>: 0, <TaskStatus.WAITING_FOR_DEPENDENCIES: 2>: 0, <TaskStatus.CANCELLED: 3>: 0, <TaskStatus.PARENT_FAILED: 4>: 0, <TaskStatus.WAITING_FOR_REQUEST_CAPACITY: 5>: 0, <TaskStatus.WAITING_FOR_TOKEN_CAPACITY: 6>: 0, <TaskStatus.API_CALL_IN_PROGRESS: 7>: 0, <TaskStatus.SUCCESS: 8>: 0, <TaskStatus.FAILED: 9>: 0, 'number_from_cache': 0})]
-    #     """
-    #     return [interview.interview_status for interview in interviews]
-
-    def _compute_statistic(stat_name: str, completed_tasks, elapsed_time, interviews):
-
-        stat_definitions = {
-            "elapsed_time": lambda: InterviewStatistic(
-                "elapsed_time", value=elapsed_time, digits=1, units="sec."
-            ),
-            "total_interviews_requested": lambda: InterviewStatistic(
-                "total_interviews_requested", value=len(interviews), units=""
-            ),
-            "completed_interviews": lambda: InterviewStatistic(
-                "completed_interviews", value=len(completed_tasks), units=""
-            ),
-            "percent_complete": lambda: InterviewStatistic(
-                "percent_complete",
-                value=(
-                    len(completed_tasks) / len(interviews) * 100
-                    if len(interviews) > 0
-                    else "NA"
-                ),
-                digits=0,
-                units="%",
-            ),
-            "average_time_per_interview": lambda: InterviewStatistic(
-                "average_time_per_interview",
-                value=elapsed_time / len(completed_tasks) if completed_tasks else "NA",
-                digits=1,
-                units="sec.",
-            ),
-            "task_remaining": lambda: InterviewStatistic(
-                "task_remaining", value=len(interviews) - len(completed_tasks), units=""
-            ),
-            "estimated_time_remaining": lambda: InterviewStatistic(
-                "estimated_time_remaining",
-                value=(
-                    (len(interviews) - len(completed_tasks)) * (elapsed_time / len(completed_tasks))
-                    if len(completed_tasks) > 0
-                    else "NA"
-                ),
-                digits=1,
-                units="sec.",
-            )
-            }
-        if stat_name not in stat_definitions:
-            raise ValueError(f"Invalid stat_name: {stat_name}. The valid stat_names are: {list(stat_definitions.keys())}")
-        return stat_definitions[stat_name]()
-
-
-    @staticmethod
-    def _job_level_info(completed_tasks: List[Type[asyncio.Task]], 
-                        elapsed_time: float, 
-                        interviews: List[Type["Interview"]] 
-                        ) -> InterviewStatisticsCollection:
-
-        interview_statistics = InterviewStatisticsCollection()
-
-        default_statistics = ["elapsed_time", "total_interviews_requested", "completed_interviews", "percent_complete", "average_time_per_interview", "task_remaining", "estimated_time_remaining"]
-        for stat_name in default_statistics:
-            interview_statistics.add_stat(JobsRunnerStatusMixin._compute_statistic(stat_name, completed_tasks, elapsed_time, interviews))
-
-        return interview_statistics
-
-    @staticmethod
-    def _get_model_queues_info(interviews):
-
-        models_to_tokens = defaultdict(InterviewTokenUsage)
-        model_to_status = defaultdict(InterviewStatusDictionary)
-        waiting_dict = defaultdict(int)
-
-        for interview in interviews:
-            models_to_tokens[interview.model] += interview.token_usage
-            model_to_status[interview.model] += interview.interview_status
-            waiting_dict[interview.model] += interview.interview_status.waiting
-
-        for model, num_waiting in waiting_dict.items():
-            yield JobsRunnerStatusMixin._get_model_info(model, num_waiting, models_to_tokens)
-
-    @staticmethod
-    def generate_status_summary(
-        completed_tasks: List[Type[asyncio.Task]],
-        elapsed_time: float,
-        interviews: List[Type["Interview"]],
-        include_model_queues = False
-    ) -> InterviewStatisticsCollection:
-        """Generate a summary of the status of the job runner.
-
-        :param completed_tasks: list of completed tasks
-        :param elapsed_time: time elapsed since the start of the job
-        :param interviews: list of interviews to be conducted
-
-        >>> from edsl.jobs.interviews.Interview import Interview
-        >>> interviews = [Interview.example()]
-        >>> completed_tasks = []
-        >>> elapsed_time = 0
-        >>> JobsRunnerStatusMixin().generate_status_summary(completed_tasks, elapsed_time, interviews)
-        {'Elapsed time': '0.0 sec.', 'Total interviews requested': '1 ', 'Completed interviews': '0 ', 'Percent complete': '0 %', 'Average time per interview': 'NA', 'Task remaining': '1 ', 'Estimated time remaining': 'NA'}
-        """
-
-        interview_status_summary: InterviewStatisticsCollection = JobsRunnerStatusMixin._job_level_info(
-            completed_tasks=completed_tasks, 
-            elapsed_time=elapsed_time, 
-            interviews=interviews
-        )
-        if include_model_queues:
-            interview_status_summary.model_queues = list(JobsRunnerStatusMixin._get_model_queues_info(interviews))
-        else:
-            interview_status_summary.model_queues = None
-
-        return interview_status_summary
-
-    @staticmethod
-    def _get_model_info(
-        model: str,
-        num_waiting: int,
-        models_to_tokens: InterviewTokenUsageMapping,
-    ) -> dict:
-        """Get the status of a model.
-
-        :param model: the model name
-        :param num_waiting: the number of tasks waiting for capacity
-        :param models_to_tokens: a mapping of models to token usage
-
-        >>> from edsl.jobs.interviews.Interview import Interview
-        >>> interviews = [Interview.example()]
-        >>> models_to_tokens = defaultdict(InterviewTokenUsage)
-        >>> model = interviews[0].model
-        >>> num_waiting = 0
-        >>> JobsRunnerStatusMixin()._get_model_info(model, num_waiting, models_to_tokens)
-        ModelInfo(model_name='gpt-4-1106-preview', TPM_limit_k=480.0, RPM_limit_k=4.0, num_tasks_waiting=0, token_usage_info=[ModelTokenUsageStats(token_usage_type='new_token_usage', details=[{'type': 'prompt_tokens', 'tokens': 0}, {'type': 'completion_tokens', 'tokens': 0}], cost='$0.00000'), ModelTokenUsageStats(token_usage_type='cached_token_usage', details=[{'type': 'prompt_tokens', 'tokens': 0}, {'type': 'completion_tokens', 'tokens': 0}], cost='$0.00000')])
-        """
-
-        ## TODO: This should probably be a coop method
-        prices = get_token_pricing(model.model)
-
-        token_usage_info = []
-        for token_usage_type in ["new_token_usage", "cached_token_usage"]:
-            token_usage_info.append(JobsRunnerStatusMixin._get_token_usage_info(token_usage_type, models_to_tokens, model, prices))
-
-        return ModelInfo(**{
-            "model_name": model.model,
-            "TPM_limit_k": model.TPM / 1000,
-            "RPM_limit_k": model.RPM / 1000,
-            "num_tasks_waiting": num_waiting,
-            "token_usage_info": token_usage_info,
-        })
-
-    @staticmethod
-    def _get_token_usage_info(
-        token_usage_type: Literal["new_token_usage", "cached_token_usage"],
-        models_to_tokens: InterviewTokenUsageMapping,
-        model: str,
-        prices: "TokenPricing",
-    ) -> ModelTokenUsageStats:
-        """Get the token usage info for a model.
-
-        >>> from edsl.jobs.interviews.Interview import Interview
-        >>> interviews = [Interview.example()]
-        >>> models_to_tokens = defaultdict(InterviewTokenUsage)
-        >>> model = interviews[0].model
-        >>> prices = get_token_pricing(model.model)
-        >>> cache_status = "new_token_usage"
-        >>> JobsRunnerStatusMixin()._get_token_usage_info(cache_status, models_to_tokens, model, prices)
-        ModelTokenUsageStats(token_usage_type='new_token_usage', details=[{'type': 'prompt_tokens', 'tokens': 0}, {'type': 'completion_tokens', 'tokens': 0}], cost='$0.00000')
-
-        """
-        all_token_usage: InterviewTokenUsage = models_to_tokens[model]
-        token_usage: TokenUsage = getattr(all_token_usage, token_usage_type)    
-        
-        details = [{"type": token_type, "tokens": getattr(token_usage, token_type)}
-                   for token_type in ["prompt_tokens", "completion_tokens"]]
-        
-        return ModelTokenUsageStats(token_usage_type = token_usage_type, details = details, cost = f"${token_usage.cost(prices):.5f}")
-    
-    @staticmethod
-    def _add_statistics_to_table(table, status_summary):
-        table.add_column("Statistic", style="dim", no_wrap=True, width=50)
-        table.add_column("Value", width=10)
-
-        for key, value in status_summary.items():
-            if key != "model_queues":
-                table.add_row(key, value)
-
-    @staticmethod
-    def display_status_table(status_summary: InterviewStatisticsCollection) -> 'Table':
-
-
-        table = Table(
-            title="Job Status",
-            show_header=True,
-            header_style="bold magenta",
-            box=SIMPLE,
-        )
-
-        ### Job-level statistics
-        JobsRunnerStatusMixin._add_statistics_to_table(table, status_summary)
-
-        ## Model-level statistics
-        spacing = " "
-
-        if status_summary.model_queues is not None:
-            table.add_row(Text("Model Queues", style="bold red"), "")
-            for model_info in status_summary.model_queues:
-
-                model_name = model_info.model_name
-                tpm = f"TPM (k)={model_info.TPM_limit_k}"
-                rpm = f"RPM (k)= {model_info.RPM_limit_k}"
-                pretty_model_name = model_name + ";" + tpm + ";" + rpm
-                table.add_row(Text(pretty_model_name, style="blue"), "")
-                table.add_row("Number question tasks waiting for capacity", str(model_info.num_tasks_waiting))
-                # Token usage and cost info
-                for token_usage_info in model_info.token_usage_info:
-                    token_usage_type = token_usage_info.token_usage_type
-                    table.add_row(
-                        Text(spacing + token_usage_type.replace("_", " "), style="bold"), ""
-                    )
-                    for detail in token_usage_info.details:
-                        token_type = detail["type"]
-                        tokens = detail["tokens"]
-                        table.add_row(spacing + f"{token_type}", f"{tokens:,}")
-                    #table.add_row(spacing + "cost", cache_info["cost"])
-
-        return table
-
-    def status_table(self, completed_tasks: List[asyncio.Task], elapsed_time: float):
-        summary_data = JobsRunnerStatusMixin.generate_status_summary(
-            completed_tasks=completed_tasks,
-            elapsed_time=elapsed_time,
-            interviews=self.total_interviews,
-        )
-        return self.display_status_table(summary_data)
-
-if __name__ == "__main__":
-    import doctest
-
-    doctest.testmod(optionflags=doctest.ELLIPSIS)

edsl/utilities/gcp_bucket/simple_example.py

@@ -1,9 +0,0 @@
-from edsl.utilities.gcp_bucket.cloud_storage import CloudStorageManager
-
-manager = CloudStorageManager()
-
-# Download Process
-file_name = "GSS2022.dta"  # Name for the downloaded file
-save_name = "test.dta"
-
-manager.download_file(file_name, save_name)

edsl-0.1.31.dev4.dist-info/RECORD

@@ -1,204 +0,0 @@
-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=Fv7dR2lKexgIV_9qy1nx0-jCMCGoz6ycHt2PDdog7iY,28
-edsl/agents/Agent.py,sha256=qNJsQkN6HuTKqJrQbuUEgRX3Wo7Dwukle0oNWPi0UIE,27191
-edsl/agents/AgentList.py,sha256=_MsdeOEgaANAceLIXwuLC22mwlBn0ruGX4GEqz8_SSY,9467
-edsl/agents/Invigilator.py,sha256=1LPfSV61pK2TpNsN72nyLz7BmLBu87Nl1cYNRdgXpP0,10947
-edsl/agents/InvigilatorBase.py,sha256=ncha1HF2V1Dz4f50Gekg6AzUXCD2Af82ztfSJZbgOHY,7469
-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
-edsl/config.py,sha256=EE4NFLtBr5wbUdf6iOGFZQ1so26gzjVHUcu_IfDqjqw,5770
-edsl/conjure/AgentConstructionMixin.py,sha256=qLLYJH02HotVwBUYzaHs4QW0t5nsC3NX15qxQLzEwLI,5702
-edsl/conjure/Conjure.py,sha256=KBmF3d6EjzTI5f-j_cZBowxWQx7jZqezHgfPMkh-h8M,1884
-edsl/conjure/InputData.py,sha256=RdFgkzzayddSTd6vcwBB8LC796YBj94pciwrQx9nBtg,22003
-edsl/conjure/InputDataCSV.py,sha256=m4hHSQogxt7LNcGNxcGRkrbdGy8pIQu5KvXhIEt9i6k,1684
-edsl/conjure/InputDataMixinQuestionStats.py,sha256=Jav5pqYCLSQ1pAbGV8O9VCBu0vL8Q6pteSEhRKrONuw,6256
-edsl/conjure/InputDataPyRead.py,sha256=phGmzVi06jdbcxgngAp_lEawGkJr5dAC2B4ho5IrAy4,3064
-edsl/conjure/InputDataSPSS.py,sha256=lv7NK8lpUfjsWh8h9MpqQrCjJX6Oyg3tIOrXcQYcS_4,223
-edsl/conjure/InputDataStata.py,sha256=WbA7oUGHgHJgugKjakXzpFfzWxTI4bXGGSZLxM1-tEM,224
-edsl/conjure/QuestionOptionMixin.py,sha256=RSLZ7AmA65MfwyxKKjqprR9FdkLP6MsCcmTbJoqu-MM,2870
-edsl/conjure/QuestionTypeMixin.py,sha256=L2vU207aeezlI1OuJ4I4SdtFCWBZzE-mBk7VwnTghO8,892
-edsl/conjure/RawQuestion.py,sha256=lo8k1aln4RfnfeS6OukzwC7P_cRe2LVZxcL6uwmim6A,2116
-edsl/conjure/SurveyResponses.py,sha256=fdJNFasSXVf7S5KCsYE9WB6w17q7VRylzw0aD5zGO_M,191
-edsl/conjure/__init__.py,sha256=1lPYFjV73GzYYSXiTyxopM4nKcXVHumEEo0fe06DbMo,535
-edsl/conjure/examples/placeholder.txt,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-edsl/conjure/naming_utilities.py,sha256=8uoGaCPZQKLwz2HudtsFSovivTGumQrFYxXxck5WUZQ,4964
-edsl/conjure/utilities.py,sha256=yRdOJx9KIpWXMx41Bbfysx7Zd4v2ROwca5L4T1rmtQM,5539
-edsl/conversation/Conversation.py,sha256=NdWH62XpcF6hoaG0ScMho_c3TO7PfBnbdlppUN-j07k,7627
-edsl/conversation/car_buying.py,sha256=Quh2Q8O9YoCyTKJUy3li376QFIOcL1gX0y89w3wlSl4,1950
-edsl/conversation/mug_negotiation.py,sha256=mjvAqErD4AjN3G2za2c-X-3axOShW-zAJUeiJqTxVPA,2616
-edsl/conversation/next_speaker_utilities.py,sha256=bqr5JglCd6bdLc9IZ5zGOAsmN2F4ERiubSMYvZIG7qk,3629
-edsl/coop/__init__.py,sha256=4iZCwJSzJVyjBYk8ggGxY2kZjq9dXVT1jhyPDNyew4I,115
-edsl/coop/coop.py,sha256=p2JvhzUpjXEaiFWafCpkfsPIsH2BqV9ePAJCKsKfFOo,27138
-edsl/coop/utils.py,sha256=UZwljKYW_Yjw7RYcjOg3SW7fn1pyHQfJ1fM48TBNoss,3601
-edsl/data/Cache.py,sha256=aR9ydTFvUWiRJZd2G7SLFFtZaS2At8ArbQ1SAhYZBDs,15629
-edsl/data/CacheEntry.py,sha256=_5UiFaJQu_U-Z1_lEPt-h6Gaidp2Eunk02wOd3Ni3MQ,7252
-edsl/data/CacheHandler.py,sha256=DTr8nJnbl_SidhsDetqbshu1DV-njPFiPPosUWTIBok,4789
-edsl/data/SQLiteDict.py,sha256=V5Nfnxctgh4Iblqcw1KmbnkjtfmWrrombROSQ3mvg6A,8979
-edsl/data/__init__.py,sha256=KBNGGEuGHq--D-TlpAQmvv_If906dJc1Gsy028zOx78,170
-edsl/data/orm.py,sha256=Jz6rvw5SrlxwysTL0QI9r68EflKxeEBmf6j6himHDS8,238
-edsl/data_transfer_models.py,sha256=ORcI-g_oUE8EofLvHQKnWC5ar-IgZiXGY2bIpTGAZyQ,1157
-edsl/enums.py,sha256=fxb0obXB-71alkx7IPosXLMAv32Ln0-ljL30dhwtK9M,4946
-edsl/exceptions/__init__.py,sha256=HVg-U-rJ0fRoG9Rws6gnK5S9B68SkPWDPsoD6KpMZ-A,1370
-edsl/exceptions/agents.py,sha256=3SORFwFbMGrF6-vAL2GrKEVdPcXo7md_k2oYufnVXHA,673
-edsl/exceptions/configuration.py,sha256=qH2sInNTndKlCLAaNgaXHyRFdKQHL7-dElB_j8wz9g4,351
-edsl/exceptions/coop.py,sha256=xDr7k_Tir6L5AxO6GMmoFyUjZ3DIenPQflpUkaTqJl0,38
-edsl/exceptions/data.py,sha256=K24CjgwFiMWxrF1Z2dF6F7Vfrge_y9kMK_wsYYSaroU,209
-edsl/exceptions/general.py,sha256=ksuqTmy-7kP9H34Cu5fSKC3Q2cZIY4qJ7J9JZGdJLCE,1011
-edsl/exceptions/jobs.py,sha256=sSUATmzBIN1oINWuwPExxPqIWmfCo0XYj_yR4dJzVjo,803
-edsl/exceptions/language_models.py,sha256=KDChmr2rVGa1lj57i9-QGSLYTOeguRYyF2z8FyXEplA,1017
-edsl/exceptions/prompts.py,sha256=vD_reI-RVKWYHYozenEmhmB7Rb1sIiXghgNUtbVGBUo,247
-edsl/exceptions/questions.py,sha256=9z6RI7HRH-UMrnIlt28VTj9deCSbD1Frmpqi0H6YtF0,534
-edsl/exceptions/results.py,sha256=cn6Zb86Y648ulN3RYXb52HGv1NT3ykBfE6g2Xu8TeIw,325
-edsl/exceptions/surveys.py,sha256=lADtr-tvPmUYSfRy3TdkTV5SzZfShlMgCzm-ZGYRlGk,557
-edsl/inference_services/AnthropicService.py,sha256=tjYRJRIvQ7Z6uCYdqxm5ZlVjZdVZCnHtQ6QGHT59PXs,2822
-edsl/inference_services/DeepInfraService.py,sha256=swZYN1mSjhu-raXTp3PdkeajcAov01b4W0XIYf27rDk,514
-edsl/inference_services/GoogleService.py,sha256=IwSwXr7khvHjpDzgiW5PRVKMhI2wQ9D1_H1MRnHjefU,2732
-edsl/inference_services/GroqService.py,sha256=Bs3f5VyTiDl6ujBZqYMQIM6LMwyYLppuphIGl-1KT6w,436
-edsl/inference_services/InferenceServiceABC.py,sha256=H6jW2gDKTLC3xgmqiSBdX4pGY1oauEO8VqGZoB3qvnQ,1790
-edsl/inference_services/InferenceServicesCollection.py,sha256=7Q04aiJUWJx3zzjSY1uH7MkhrJi41RshU3Zy-6rM6kI,2596
-edsl/inference_services/OpenAIService.py,sha256=h8m_GKZxrNdHA0B4x0dcOu15ZoOc6Vp-N2gmzWMIY9s,7529
-edsl/inference_services/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-edsl/inference_services/models_available_cache.py,sha256=ZT2pBGxJqTgwynthu-SqBjv8zl7ql44q3gA6xy7kqSU,2338
-edsl/inference_services/rate_limits_cache.py,sha256=HYslviz7mxF9U4CUTPAkoyBsiXjSju-YCp4HHir6e34,1398
-edsl/inference_services/registry.py,sha256=RzmOjDjq7361v2aUCeR8MIJw8qxWqKs_697ZnQrbbmM,556
-edsl/inference_services/write_available.py,sha256=NNwhATlaMp8IYY635MSx-oYxt5X15acjAfaqYCo_I1Y,285
-edsl/jobs/Answers.py,sha256=z4TADN-iHIrbMtI1jVyiaetv0OkTv768dFBpREIQC6c,1799
-edsl/jobs/Jobs.py,sha256=jSi4lbSDlJGaCHCPcbkwxepFlz008vynPTZVRABdBWM,30777
-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
-edsl/jobs/buckets/TokenBucket.py,sha256=2K9MV-8QRODK83jFNuD55kfEKhWGqk9ipC4IkMCh2gg,6008
-edsl/jobs/interviews/Interview.py,sha256=gmSYBXQbFpE8X6dNaAYkLaWu0Zb_gJZsab5ydRD2JBg,11388
-edsl/jobs/interviews/InterviewStatistic.py,sha256=hY5d2EkIJ96NilPpZAvZZzZoxLXM7ss3xx5MIcKtTPs,1856
-edsl/jobs/interviews/InterviewStatisticsCollection.py,sha256=_ZZ0fnZBQiIywP9Q_wWjpWhlfcPe2cn32GKut10t5RI,788
-edsl/jobs/interviews/InterviewStatusDictionary.py,sha256=MSyys4hOWe1d8gfsUvAPbcKrs8YiPnz8jpufBSJL7SU,2485
-edsl/jobs/interviews/InterviewStatusLog.py,sha256=6u0F8gf5tha39VQL-IK_QPkCsQAYVOx_IesX7TDDX_A,3252
-edsl/jobs/interviews/InterviewStatusMixin.py,sha256=VV0Pel-crUsLoGpTifeIIkXsLGj0bfuO--UtpRnH-dU,1251
-edsl/jobs/interviews/InterviewTaskBuildingMixin.py,sha256=qa3WzogBOSf7HmB-o9dzUrG4GSETcPTM0e4JHHtUkTM,11168
-edsl/jobs/interviews/ReportErrors.py,sha256=RSzDU2rWwtjfztj7sqaMab0quCiY-X2bG3AEOxhTim8,1745
-edsl/jobs/interviews/interview_exception_tracking.py,sha256=tIcX92udnkE5fcM5_WXjRF9xgTq2P0uaDXxZf3NQGG0,3271
-edsl/jobs/interviews/interview_status_enum.py,sha256=KJ-1yLAHdX-p8TiFnM0M3v1tnBwkq4aMCuBX6-ytrI8,229
-edsl/jobs/interviews/retry_management.py,sha256=9Efn4B3aV45vbocnF6J5WQt88i2FgFjoi5ALzGUukEE,1375
-edsl/jobs/runners/JobsRunnerAsyncio.py,sha256=P2fx187rP9WeA3m9FovKS1VGOtvlai1AYPJaSC6-Un4,12185
-edsl/jobs/runners/JobsRunnerStatusData.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-edsl/jobs/runners/JobsRunnerStatusMixin.py,sha256=YWHdn_01RuHzCUCl5nvWgIOMtljiLfX4nUB8kPvOlgQ,12913
-edsl/jobs/tasks/QuestionTaskCreator.py,sha256=f-hF7TMdMMjQ5AQMpMJXrFdBUNSLrLHHl1sun774f_U,10394
-edsl/jobs/tasks/TaskCreators.py,sha256=WUSs-KFpwbm_MB3jlDQm1SJLNWTxP-jKjisealIm36U,2702
-edsl/jobs/tasks/TaskHistory.py,sha256=ZVellGW1cvwqdHt98dYPl0FYhk3VqRGHAZETDOxEkqg,10939
-edsl/jobs/tasks/TaskStatusLog.py,sha256=bqH36a32F12fjX-M-4lNOhHaK2-WLFzKE-r0PxZPRjI,546
-edsl/jobs/tasks/task_management.py,sha256=KMToZuXzMlnHRHUF_VHL0-lHMTGhklf2GHVuwEEHtzA,301
-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=SYIEaHwQgHquREzIRsy4--F0T2yp3sA2hxW5AnVX2qo,21212
-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
-edsl/language_models/registry.py,sha256=T7KmAZoNAWHRmvH5yRBlMOKJ2XVUIdZ7Wu0EZVPxgxg,3743
-edsl/language_models/repair.py,sha256=xaNunBRpMWgceSPOzk-ugp5WXtgLuuhj23TgXUeOobw,5963
-edsl/language_models/unused/ReplicateBase.py,sha256=J1oqf7mEyyKhRwNUomnptVqAsVFYCbS3iTW0EXpKtXo,3331
-edsl/notebooks/Notebook.py,sha256=qwDqUN2Gujr7WUneRrshzRBjHvcPpOIBRyqcrAOc90Q,7341
-edsl/notebooks/__init__.py,sha256=VNUA3nNq04slWNbYaNrzOhQJu3AZANpvBniyCJSzJ7U,45
-edsl/prompts/Prompt.py,sha256=12cbeQTKqfVQGpd1urqKZeXiDtKz2RAJqftoXS3q-DE,10070
-edsl/prompts/QuestionInstructionsBase.py,sha256=xico6ob4cqWsHl-txj2RbY_4Ny5u9UqvIjmoTVgjUhk,348
-edsl/prompts/__init__.py,sha256=Z0ywyJfnV0i-sR1SCdK4mHhgECT5cXpHVA-pKuBTifc,85
-edsl/prompts/library/agent_instructions.py,sha256=_2kCDYvh3ZOF72VvcIH5jhmHjM6AAgQdkWrHvR52Yhg,1100
-edsl/prompts/library/agent_persona.py,sha256=jEl1LjlOP67vOPiRW0S_-TRMz3n6Tp3mPRvltM2r2_k,516
-edsl/prompts/library/question_budget.py,sha256=RAc7pmQRbs_-xksU52yYl8iqJ7HejPY4sQOlCSQLGWs,1190
-edsl/prompts/library/question_checkbox.py,sha256=NIGcdnfkJ8_XbGsdq9toeWA_phQVx5FIBOAe0mReXJw,1462
-edsl/prompts/library/question_extract.py,sha256=QxNiNBjUk25Ss_Pax0iDgmgTYXEycpWJk2z0evmqsP0,775
-edsl/prompts/library/question_freetext.py,sha256=_I7hcniRfVwmZr2wXAasfbZ0GTu41ZIKfcoixGhzZUI,510
-edsl/prompts/library/question_linear_scale.py,sha256=sQpgjSvqJU-uQti-DCxOzLzj05ENkpyxmH-qTFq39x0,778
-edsl/prompts/library/question_list.py,sha256=KYi3gtcWyDzRLyAb2-k7C-QJ9TAfbLGPkWVvVmdT6xg,731
-edsl/prompts/library/question_multiple_choice.py,sha256=_2LUM9bOInODoFyaTrKfMkcb5Z7RDj_odq5iAnD7KVQ,1617
-edsl/prompts/library/question_numerical.py,sha256=ZdWnDbTU0gQdMMqcWHw_eIHEZkJ_kuE-XWrnCYFR07w,1456
-edsl/prompts/library/question_rank.py,sha256=WDgXyph0EKWJrSgsW2eqcx3xdU-WA1LEvB2jvQFOQ8s,882
-edsl/prompts/prompt_config.py,sha256=O3Y5EvBsCeKs9m9IjXiRXOcHWlWvQV0yqsNb2oSR1ow,974
-edsl/prompts/registry.py,sha256=XOsqGsvNOmIG83jqoszqI72yNZkkszKR4FrEhwSzj_Q,8093
-edsl/questions/AnswerValidatorMixin.py,sha256=U5i79HoEHpSoevgtx68TSg8a9tELq3R8xMtYyK1L7DQ,12106
-edsl/questions/QuestionBase.py,sha256=L0-IMnSGiUh5Uw7kFDsPV057mR9tL9aMwHUtxjLlKsg,19017
-edsl/questions/QuestionBudget.py,sha256=K8cc1YOfoLWRoZBAkWO7WsMDZne0a5oAJMSxv2Jzd1E,6143
-edsl/questions/QuestionCheckBox.py,sha256=YHS-LEvR_1CWyg4usOlWfj9Gb_cCQlfIWIWhYRWn7Wo,6129
-edsl/questions/QuestionExtract.py,sha256=fjnsNLS2fNW6dfFuRyc2EgKEHx8ujjONmg2nSRynje4,3988
-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=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
-edsl/questions/SimpleAskMixin.py,sha256=YRLiHA6TPMKyLWvdAi7Mfnxcqtw7Kem6tH28YNb8n4U,2227
-edsl/questions/__init__.py,sha256=U7t2dk_dHSaFRciHETXaGaJRnCobaik3mIKCpGRUuJo,1160
-edsl/questions/compose_questions.py,sha256=ZcLkwNaofk-o0-skGXEDGZAj6DumOhVhyIUjqEnKrbg,3380
-edsl/questions/derived/QuestionLikertFive.py,sha256=zKkjKI3HSt9ZGyBBNgXNsfXZ7gOoOknidLDPgMN_PcI,2475
-edsl/questions/derived/QuestionLinearScale.py,sha256=7tybIaMaDTMkTFC6CymusW69so-zf5jUn8Aqf5pw__Y,2673
-edsl/questions/derived/QuestionTopK.py,sha256=TouXKZt_h6Jd-2rAjkEOCJOzzei4Wa-3hjYq9CLxWws,2744
-edsl/questions/derived/QuestionYesNo.py,sha256=KtMGuAPYWv-7-9WGa0fIS2UBxf6KKjFpuTk_h8FPZbg,2076
-edsl/questions/derived/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-edsl/questions/descriptors.py,sha256=W0_mGZKKiXv2E2BKIy8-4n_QDILh9sun85Oev1YRoLs,14791
-edsl/questions/question_registry.py,sha256=ZD7Y_towDdlnnmLq12vVewgQ3fEk9Ur0tCTWK8-WqeQ,5241
-edsl/questions/settings.py,sha256=er_z0ZW_dgmC5CHLWkaqBJiuWgAYzIund85M5YZFQAI,291
-edsl/results/Dataset.py,sha256=DZgb3vIj69ON7APQ6DimjBwAS1xZvZiXOg68CjW9E3I,8662
-edsl/results/DatasetExportMixin.py,sha256=Iq3Kzdoc6HmjihdsFzj_mhmRpoeBwF8AREVK8FZmlaI,25047
-edsl/results/Result.py,sha256=53lz1mGqmnt2wHl-Ccimbla7cNlg_mLUgOBQa6Qd19k,14433
-edsl/results/Results.py,sha256=IUHfmcBVtZ3me4VvVBQsdKKtuMXaZtLkzIrH5US7aUY,38155
-edsl/results/ResultsDBMixin.py,sha256=Vs95zbSB4G7ENY4lU7OBdekg9evwTrtPH0IIL2NAFTk,7936
-edsl/results/ResultsExportMixin.py,sha256=XizBsPNxziyffirMA4kS7UHpYM1WIE4s1K-B7TqTfDw,1266
-edsl/results/ResultsFetchMixin.py,sha256=VEa0TKDcXbnTinSKs9YaE4WjOSLmlp9Po1_9kklFvSo,848
-edsl/results/ResultsGGMixin.py,sha256=SAYz8p4wb1g8x6KhBVz9NHOGib2c2XsqtTclpADrFeM,4344
-edsl/results/ResultsToolsMixin.py,sha256=mseEFxJCf9sjXdIxpjITt_UZBwdXxw2o2VLg5jMrALA,3017
-edsl/results/__init__.py,sha256=2YcyiVtXi-3vIV0ZzOy1PqBLm2gaziufJVi4fdNrAt8,80
-edsl/scenarios/FileStore.py,sha256=AevvU1qdLSmL4Q7cb1PhUiaJk1i5T0sgkTKBYf0KDN4,8722
-edsl/scenarios/Scenario.py,sha256=eQRMV6JD6mrlIMXc7-NK0I-LK5px2oC6rAR_w-qJPnE,14829
-edsl/scenarios/ScenarioHtmlMixin.py,sha256=EmugmbPJYW5eZS30rM6pDMDQD9yrrvHjmgZWB1qBfq4,1882
-edsl/scenarios/ScenarioImageMixin.py,sha256=VJ5FqyPrL5-ieORlWMpnjmOAFIau8QFZCIZyEBKgb6I,3530
-edsl/scenarios/ScenarioList.py,sha256=lFdhlVG9NMAuZ4MBzz7VoIMT3NVWaNUjEHhGOQm1Hn8,19631
-edsl/scenarios/ScenarioListExportMixin.py,sha256=4fAcz_nfGrGZbzH_ZCWyf6CZoWxFvMM6xRJDWnYlevY,995
-edsl/scenarios/ScenarioListPdfMixin.py,sha256=sRCHVG7z4u4ST4ce-I_Y4md8ZzC9-tj4an9PMouaHVg,3765
-edsl/scenarios/__init__.py,sha256=KRwZCLf2R0qyJvv1NGbd8M51Bt6Ia6Iylg-Xq_2Fa6M,98
-edsl/shared.py,sha256=lgLa-mCk2flIhxXarXLtfXZjXG_6XHhC2A3O8yRTjXc,20
-edsl/study/ObjectEntry.py,sha256=e3xRPH8wCN8Pum5HZsQRYgnSoauSvjXunIEH79wu5A8,5788
-edsl/study/ProofOfWork.py,sha256=FaqYtLgeiTEQXWKukPgPUTWMcIN5t1FR7h7Re8QEtgc,3433
-edsl/study/SnapShot.py,sha256=-5zoP4uTvnqtu3zRNMD-fKsNAVYX9psoKRADfotsF9E,2439
-edsl/study/Study.py,sha256=zLy2mMvsX_QgZ6D4dcgYJoEacyajkRnARYjIFvyCO1o,16939
-edsl/study/__init__.py,sha256=YAvPLTPG3hK_eN9Ar3d1_d-E3laXpSya879A25-JAxU,170
-edsl/surveys/DAG.py,sha256=ozQuHo9ZQ8Eet5nDXtp7rFpiSocvvfxIHtyTnztvodg,2380
-edsl/surveys/Memory.py,sha256=-ikOtkkQldGB_BkPCW3o7AYwV5B_pIwlREw7aVCSHaQ,1113
-edsl/surveys/MemoryPlan.py,sha256=BeLuqS5Q8G2jSluHYFCAxVmj7cNPK-rDQ3mUsuDjikQ,7979
-edsl/surveys/Rule.py,sha256=ddZyZSObs4gsKtFSmcXkPigXDX8rrh1NFvAplP02TcA,11092
-edsl/surveys/RuleCollection.py,sha256=sN7aYDQJG3HmE-WxohgpctcQbHewjwE6NAqEVTxvFP8,13359
-edsl/surveys/Survey.py,sha256=eB8S3KQ0d7nyJ0RqhCimmOXcO-d2_GquxvHMR0g6t90,48567
-edsl/surveys/SurveyCSS.py,sha256=NjJezs2sTlgFprN6IukjGKwNYmNdXnLjzV2w5K4z4RI,8415
-edsl/surveys/SurveyExportMixin.py,sha256=vj9bZReHx0wBK9sVuS0alzPIUDdg6AFFMd7bl1RKWKI,6555
-edsl/surveys/SurveyFlowVisualizationMixin.py,sha256=Z-YqeedMqWOtCFy003YJ9aneJ1n4bn70lDoILwLtTc0,3966
-edsl/surveys/__init__.py,sha256=vjMYVlP95fHVqqw2FfKXRuYbTArZkZr1nK4FnXzZWzs,129
-edsl/surveys/base.py,sha256=n5PBx0BF0powzBXCsufpUekfNK_9huf3rohtU1mMCq0,1001
-edsl/surveys/descriptors.py,sha256=3B-hBVvGpLlVBCyOnPuxkLjesvpr0QIuATbggp_MJ7o,2076
-edsl/tools/__init__.py,sha256=4iRiX1K0Yh8RGwlUBuzipvFfRrofKqCRQ0SzNK_2oiQ,41
-edsl/tools/clusters.py,sha256=uvDN76bfHIHS-ykB2iioXu0gKeP_UyD7Q9ee67w_fV4,6132
-edsl/tools/embeddings.py,sha256=-mHqApiFbGzj_2Cr_VVl_7XiBBDyPB5-6ZO7IsXvaig,677
-edsl/tools/embeddings_plotting.py,sha256=fznAqLnjF_K8PkJy1C4hBRObm3f8ebDIxQzrqRXlEJM,3564
-edsl/tools/plotting.py,sha256=DbVNlm8rNCnWHXi5wDPnOviZ1Qxz-rHvtQM1zHWw1f8,3120
-edsl/tools/summarize.py,sha256=YcdB0IjZn92qv2zVJuxsHfXou810APWYKeaHknsATqM,656
-edsl/utilities/SystemInfo.py,sha256=qTP_aKwECPxtTnbEjJ7F1QqKU9U3rcEEbppg2ilQGuY,792
-edsl/utilities/__init__.py,sha256=oUWx_h-8OFb1Of2SgIQZuIu7hX_bhDuwCSwksKGWZ6k,544
-edsl/utilities/ast_utilities.py,sha256=49KDDu-PHYpzDN5cCaDf-ReQH-1dzjT5EG3WVSa8THk,868
-edsl/utilities/data/Registry.py,sha256=q2DKc7CpG_7l47MxxsSi6DJOs4p1Z3qNx7PV-v8CUOE,176
-edsl/utilities/data/__init__.py,sha256=pDjGnzC11q4Za8qX5zcg6plcQ_8Qjpb-sAKPwOlKmCY,62
-edsl/utilities/data/scooter_results.json,sha256=tRtVAI5haLMh_-wjz9it_uk_I1bGe5qdFHsIRQMi_ks,250944
-edsl/utilities/decorators.py,sha256=rlTSMItwmWUxHQBIEUDxX3lFzgtiT8PnfNavakuf-2M,2319
-edsl/utilities/gcp_bucket/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-edsl/utilities/gcp_bucket/cloud_storage.py,sha256=dStHsG181YP9ALW-bkyO-sgMWuLV5aaLsnsCOVD8jJw,3472
-edsl/utilities/gcp_bucket/simple_example.py,sha256=pR_IH_Y640_-YnEyNpE7V_1MtBFC9nD3dg2NdSVcuXY,251
-edsl/utilities/interface.py,sha256=AaKpWiwWBwP2swNXmnFlIf3ZFsjfsR5bjXQAW47tD-8,19656
-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.dev4.dist-info/LICENSE,sha256=_qszBDs8KHShVYcYzdMz3HNMtH-fKN_p5zjoVAVumFc,1111
-edsl-0.1.31.dev4.dist-info/METADATA,sha256=d5d3UglIezwp0eb3EhsGPw1VnJFyr_G_m8-AuArA124,4171
-edsl-0.1.31.dev4.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-edsl-0.1.31.dev4.dist-info/RECORD,,