kiln-ai 0.18.0__py3-none-any.whl → 0.20.1__py3-none-any.whl

kiln_ai/adapters/__init__.py

@@ -28,12 +28,12 @@ from . import (
 )
 
 __all__ = [
-    "model_adapters",
     "chat",
     "data_gen",
+    "eval",
     "fine_tune",
     "ml_model_list",
+    "model_adapters",
     "prompt_builders",
     "repair",
-    "eval",
 ]

kiln_ai/adapters/adapter_registry.py

@@ -44,6 +44,23 @@ def adapter_for_task(
                 ),
                 base_adapter_config=base_adapter_config,
             )
+        case ModelProviderName.siliconflow_cn:
+            return LiteLlmAdapter(
+                kiln_task=kiln_task,
+                config=LiteLlmConfig(
+                    run_config_properties=run_config_properties,
+                    base_url=getenv("SILICONFLOW_BASE_URL")
+                    or "https://api.siliconflow.cn/v1",
+                    default_headers={
+                        "HTTP-Referer": "https://kiln.tech/siliconflow",
+                        "X-Title": "KilnAI",
+                    },
+                    additional_body_options={
+                        "api_key": Config.shared().siliconflow_cn_api_key,
+                    },
+                ),
+                base_adapter_config=base_adapter_config,
+            )
         case ModelProviderName.openai:
             return LiteLlmAdapter(
                 kiln_task=kiln_task,
@@ -106,6 +123,24 @@ def adapter_for_task(
                     },
                 ),
             )
+        case ModelProviderName.docker_model_runner:
+            docker_base_url = (
+                Config.shared().docker_model_runner_base_url
+                or "http://localhost:12434/engines/llama.cpp"
+            )
+            return LiteLlmAdapter(
+                kiln_task=kiln_task,
+                base_adapter_config=base_adapter_config,
+                config=LiteLlmConfig(
+                    run_config_properties=run_config_properties,
+                    # Docker Model Runner uses OpenAI-compatible API at /v1 endpoint
+                    base_url=docker_base_url + "/v1",
+                    additional_body_options={
+                        # LiteLLM errors without an api_key, even though Docker Model Runner doesn't require one.
+                        "api_key": "DMR",
+                    },
+                ),
+            )
         case ModelProviderName.fireworks_ai:
             return LiteLlmAdapter(
                 kiln_task=kiln_task,
@@ -186,6 +221,17 @@ def adapter_for_task(
                     },
                 ),
             )
+        case ModelProviderName.cerebras:
+            return LiteLlmAdapter(
+                kiln_task=kiln_task,
+                base_adapter_config=base_adapter_config,
+                config=LiteLlmConfig(
+                    run_config_properties=run_config_properties,
+                    additional_body_options={
+                        "api_key": Config.shared().cerebras_api_key,
+                    },
+                ),
+            )
         # These are virtual providers that should have mapped to an actual provider in core_provider
         case ModelProviderName.kiln_fine_tune:
             raise ValueError(

kiln_ai/adapters/chat/chat_formatter.py

@@ -106,14 +106,12 @@ class TwoMessageCotLegacyFormatter(ChatFormatter):
         if self._state == "awaiting_thinking":
             if previous_output is None:
                 raise ValueError("previous_output required for thinking step")
-            msgs = [
-                ChatMessage("assistant", previous_output),
-                ChatMessage("user", COT_FINAL_ANSWER_PROMPT),
-            ]
             self._intermediate_outputs["chain_of_thought"] = previous_output
             self._state = "awaiting_final"
-            self._messages.extend(msgs)
-            return ChatTurn(messages=msgs, final_call=True)
+            cot_message = ChatMessage("user", COT_FINAL_ANSWER_PROMPT)
+            self._messages.append(ChatMessage("assistant", previous_output))
+            self._messages.append(cot_message)
+            return ChatTurn(messages=[cot_message], final_call=True)
 
         if self._state == "awaiting_final":
             if previous_output is None:
@@ -155,14 +153,12 @@ class TwoMessageCotFormatter(ChatFormatter):
         if self._state == "awaiting_thinking":
             if previous_output is None:
                 raise ValueError("previous_output required for thinking step")
-            msgs = [
-                ChatMessage("assistant", previous_output),
-                ChatMessage("user", COT_FINAL_ANSWER_PROMPT),
-            ]
             self._intermediate_outputs["chain_of_thought"] = previous_output
             self._state = "awaiting_final"
-            self._messages.extend(msgs)
-            return ChatTurn(messages=msgs, final_call=True)
+            self._messages.append(ChatMessage("assistant", previous_output))
+            cot_message = ChatMessage("user", COT_FINAL_ANSWER_PROMPT)
+            self._messages.append(cot_message)
+            return ChatTurn(messages=[cot_message], final_call=True)
 
         if self._state == "awaiting_final":
             if previous_output is None:

kiln_ai/adapters/chat/test_chat_formatter.py

@@ -46,12 +46,14 @@ def test_chat_formatter_final_and_intermediate():
     )
 
     first = formatter.next_turn()
+    assert first is not None
     assert [m.__dict__ for m in first.messages] == expected[:3]
     assert not first.final_call
     assert formatter.intermediate_outputs() == {}
 
     second = formatter.next_turn("thinking output")
-    assert [m.__dict__ for m in second.messages] == expected[3:5]
+    assert second is not None
+    assert [m.__dict__ for m in second.messages] == expected[4:5]
     assert second.final_call
     assert formatter.intermediate_outputs() == {"chain_of_thought": "thinking output"}
 
@@ -78,12 +80,14 @@ def test_chat_formatter_two_message_cot():
     )
 
     first = formatter.next_turn()
+    assert first is not None
     assert [m.__dict__ for m in first.messages] == expected[:2]
     assert not first.final_call
     assert formatter.intermediate_outputs() == {}
 
     second = formatter.next_turn("thinking output")
-    assert [m.__dict__ for m in second.messages] == expected[2:4]
+    assert second is not None
+    assert [m.__dict__ for m in second.messages] == expected[3:4]
     assert second.final_call
     assert formatter.intermediate_outputs() == {"chain_of_thought": "thinking output"}
 

kiln_ai/adapters/data_gen/data_gen_task.py

@@ -77,7 +77,7 @@ class DataGenCategoriesTask(Task, parent_of={}):
     """
 
     def __init__(self, gen_type: Literal["training", "eval"], guidance: str | None):
-        # Keep the typechecker happy. TODO: shouldn't need this or parent_of above.
+        # Keep the typechecker happy. We should make this optional.
         tmp_project = Project(name="DataGen")
 
         instruction = generate_topic_tree_prompt(gen_type=gen_type, guidance=guidance)
@@ -181,7 +181,7 @@ class DataGenSampleTask(Task, parent_of={}):
         gen_type: Literal["training", "eval"],
         guidance: str | None,
     ):
-        # Keep the typechecker happy. TODO: shouldn't need this or parent_of above.
+        # Keep the typechecker happy. We should make this optional.
         tmp_project = Project(name="DataGenSample")
 
         instruction = generate_sample_generation_prompt(

kiln_ai/adapters/data_gen/test_data_gen_task.py

@@ -255,11 +255,13 @@ async def test_data_gen_sample_all_models_providers(
     tmp_path, model_name, provider_name, base_task
 ):
     _, provider = get_model_and_provider(model_name, provider_name)
-    if not provider.supports_data_gen:
+    if provider is None or not provider.supports_data_gen:
         # pass if the model doesn't support data gen (testing the support flag is part of this)
         return
 
-    data_gen_task = DataGenSampleTask(target_task=base_task)
+    data_gen_task = DataGenSampleTask(
+        target_task=base_task, gen_type="training", guidance=None
+    )
     data_gen_input = DataGenSampleTaskInput.from_task(
         base_task, topic=["riding horses"], num_samples=4
     )
@@ -313,7 +315,9 @@ async def test_data_gen_sample_all_models_providers_with_structured_output(
         # pass if the model doesn't support data gen (testing the support flag is part of this)
         return
 
-    data_gen_task = DataGenSampleTask(target_task=task)
+    data_gen_task = DataGenSampleTask(
+        target_task=task, gen_type="training", guidance=None
+    )
     data_gen_input = DataGenSampleTaskInput.from_task(
         task, topic=["Food"], num_samples=4
     )

kiln_ai/adapters/docker_model_runner_tools.py

@@ -0,0 +1,119 @@
+from typing import List
+
+import httpx
+import openai
+from pydantic import BaseModel, Field
+
+from kiln_ai.adapters.ml_model_list import ModelProviderName, built_in_models
+from kiln_ai.utils.config import Config
+
+
+def docker_model_runner_base_url() -> str:
+    """
+    Gets the base URL for Docker Model Runner API connections.
+
+    Returns:
+        The base URL to use for Docker Model Runner API calls, using environment variable if set
+        or falling back to localhost default
+    """
+    config_base_url = Config.shared().docker_model_runner_base_url
+    if config_base_url:
+        return config_base_url
+    return "http://localhost:12434/engines/llama.cpp"
+
+
+async def docker_model_runner_online() -> bool:
+    """
+    Checks if the Docker Model Runner service is available and responding.
+
+    Returns:
+        True if Docker Model Runner is available and responding, False otherwise
+    """
+    try:
+        base_url = docker_model_runner_base_url()
+        # Docker Model Runner uses OpenAI-compatible endpoints
+        async with httpx.AsyncClient() as client:
+            response = await client.get(f"{base_url}/v1/models", timeout=5.0)
+            response.raise_for_status()
+    except httpx.RequestError:
+        return False
+    return True
+
+
+class DockerModelRunnerConnection(BaseModel):
+    message: str
+    version: str | None = None
+    supported_models: List[str]
+    untested_models: List[str] = Field(default_factory=list)
+
+    def all_models(self) -> List[str]:
+        return self.supported_models + self.untested_models
+
+
+# Parse the Docker Model Runner /v1/models response
+def parse_docker_model_runner_models(
+    models: List[openai.types.Model],
+) -> DockerModelRunnerConnection | None:
+    # Build a list of models we support for Docker Model Runner from the built-in model list
+    supported_docker_models = [
+        provider.model_id
+        for model in built_in_models
+        for provider in model.providers
+        if provider.name == ModelProviderName.docker_model_runner
+    ]
+    # Note: Docker Model Runner aliases will be added when we configure models
+
+    model_names = [model.id for model in models]
+    available_supported_models = []
+    untested_models = []
+
+    for model_name in model_names:
+        if model_name in supported_docker_models:
+            available_supported_models.append(model_name)
+        else:
+            untested_models.append(model_name)
+
+    if available_supported_models or untested_models:
+        return DockerModelRunnerConnection(
+            message="Docker Model Runner connected",
+            supported_models=available_supported_models,
+            untested_models=untested_models,
+        )
+
+    return DockerModelRunnerConnection(
+        message="Docker Model Runner is running, but no supported models are available. Ensure models like 'ai/llama3.2:3B-Q4_K_M', 'ai/qwen3:8B-Q4_K_M', or 'ai/gemma3n:4B-Q4_K_M' are loaded.",
+        supported_models=[],
+        untested_models=[],
+    )
+
+
+async def get_docker_model_runner_connection(
+    custom_url: str | None = None,
+) -> DockerModelRunnerConnection | None:
+    """
+    Gets the connection status for Docker Model Runner.
+
+    Args:
+        custom_url: Optional custom URL to use instead of the configured one
+    """
+    try:
+        base_url = custom_url or docker_model_runner_base_url()
+        # Use OpenAI client to get models list
+        client = openai.OpenAI(
+            api_key="dummy",  # Docker Model Runner doesn't require API key
+            base_url=f"{base_url}/v1",
+            max_retries=0,
+        )
+        models_response = client.models.list()
+
+    except (openai.APIConnectionError, openai.APIError, httpx.RequestError):
+        return None
+
+    return parse_docker_model_runner_models(list(models_response))
+
+
+def docker_model_runner_model_installed(
+    conn: DockerModelRunnerConnection, model_name: str
+) -> bool:
+    all_models = conn.all_models()
+    return model_name in all_models

kiln_ai/adapters/eval/base_eval.py

@@ -7,7 +7,7 @@ from kiln_ai.adapters.ml_model_list import ModelProviderName
 from kiln_ai.adapters.model_adapters.base_adapter import AdapterConfig
 from kiln_ai.datamodel.eval import Eval, EvalConfig, EvalScores
 from kiln_ai.datamodel.json_schema import validate_schema_with_value_error
-from kiln_ai.datamodel.task import RunConfig, TaskOutputRatingType, TaskRun
+from kiln_ai.datamodel.task import RunConfigProperties, TaskOutputRatingType, TaskRun
 from kiln_ai.utils.exhaustive_error import raise_exhaustive_enum_error
 
 
@@ -18,7 +18,7 @@ class BaseEval:
     Should be subclassed, and the run_eval method implemented.
     """
 
-    def __init__(self, eval_config: EvalConfig, run_config: RunConfig | None):
+    def __init__(self, eval_config: EvalConfig, run_config: RunConfigProperties | None):
         self.eval_config = eval_config
         eval = eval_config.parent_eval()
         if not eval:

kiln_ai/adapters/eval/eval_runner.py

@@ -169,7 +169,9 @@ class EvalRunner:
             # Create the evaluator for this eval config/run config pair
             evaluator = eval_adapter_from_type(job.eval_config.config_type)(
                 job.eval_config,
-                job.task_run_config.run_config() if job.task_run_config else None,
+                job.task_run_config.run_config_properties
+                if job.task_run_config
+                else None,
             )
             if not isinstance(evaluator, BaseEval):
                 raise ValueError("Not able to create evaluator from eval config")

kiln_ai/adapters/eval/g_eval.py

@@ -12,7 +12,7 @@ from kiln_ai.adapters.model_adapters.base_adapter import AdapterConfig, RunOutpu
 from kiln_ai.adapters.prompt_builders import PromptGenerators
 from kiln_ai.datamodel import Project, Task, TaskRun
 from kiln_ai.datamodel.eval import EvalConfig, EvalConfigType, EvalScores
-from kiln_ai.datamodel.task import RunConfig, RunConfigProperties, StructuredOutputMode
+from kiln_ai.datamodel.task import RunConfigProperties, StructuredOutputMode
 
 # all the tokens we score for, and their float scores.
 TOKEN_TO_SCORE_MAP: Dict[str, float] = {
@@ -89,7 +89,7 @@ class GEval(BaseEval):
     }
     """
 
-    def __init__(self, eval_config: EvalConfig, run_config: RunConfig | None):
+    def __init__(self, eval_config: EvalConfig, run_config: RunConfigProperties | None):
         if (
             eval_config.config_type != EvalConfigType.g_eval
             and eval_config.config_type != EvalConfigType.llm_as_judge

kiln_ai/adapters/eval/test_base_eval.py

@@ -380,7 +380,7 @@ async def test_run_task_and_eval():
         async def run_eval(self, task_run):
             return {"overall_rating": 5, "quality": 4}, {"thinking": "test thinking"}
 
-    evaluator = MockEval(eval_config, run_config.run_config())
+    evaluator = MockEval(eval_config, run_config.run_config_properties)
 
     # Mock dependencies
     mock_adapter = AsyncMock()

kiln_ai/adapters/eval/test_eval_runner.py

@@ -485,18 +485,17 @@ async def test_run_job_success_task_run_eval(
     )
 
     # Mock the evaluator
-    mock_result_run = TaskRun(
-        input="test input",
-        input_source=data_source,
-        output=TaskOutput(output="evaluated output"),
-        intermediate_outputs={"intermediate_output": "intermediate output"},
-    )
     mock_scores = {"accuracy": 0.95}
 
     class MockEvaluator(BaseEval):
         async def run_task_and_eval(self, input_text):
             return (
-                mock_result_run,
+                TaskRun(
+                    input="test input",
+                    input_source=data_source,
+                    output=TaskOutput(output="evaluated output"),
+                    intermediate_outputs={"intermediate_output": "intermediate output"},
+                ),
                 mock_scores,
                 {"intermediate_output": "intermediate output"},
             )
@@ -546,11 +545,6 @@ async def test_run_job_success_eval_config_eval(
     )
 
     # Mock the evaluator
-    mock_result_run = TaskRun(
-        input="test input",
-        input_source=data_source,
-        output=TaskOutput(output="evaluated output"),
-    )
     mock_scores: EvalScores = {"accuracy": 0.95}
 
     class MockEvaluator(BaseEval):

kiln_ai/adapters/eval/test_g_eval.py

@@ -19,7 +19,7 @@ from kiln_ai.datamodel import (
     TaskRun,
 )
 from kiln_ai.datamodel.eval import Eval, EvalConfig, EvalConfigType, EvalOutputScore
-from kiln_ai.datamodel.task import RunConfig
+from kiln_ai.datamodel.task import RunConfigProperties
 
 
 @pytest.fixture
@@ -93,11 +93,10 @@ def test_eval_config(test_task):
 
 
 @pytest.fixture
-def test_run_config(test_task):
-    return RunConfig(
+def test_run_config():
+    return RunConfigProperties(
         model_name="llama_3_1_8b",
         model_provider_name="groq",
-        task=test_task,
         prompt_id="simple_prompt_builder",
         structured_output_mode="json_schema",
     )

kiln_ai/adapters/eval/test_g_eval_data.py

@@ -1,4 +1,4 @@
 # Saved a real RunOutput, with real logprobs via:
 # po = pickle.dumps(result)
-# print(f"\n\nPickled result: \n{po}\n\n")
+# Example inspection of the pickled result can be done with a print statement.
 serialized_run_output = b"\x80\x04\x95\xe8:\x00\x00\x00\x00\x00\x00\x8c\x1bkiln_ai.adapters.run_output\x94\x8c\tRunOutput\x94\x93\x94)\x81\x94}\x94(\x8c\x06output\x94}\x94(\x8c\x0ftopic_alignment\x94K\x05\x8c\x0fappropriateness\x94\x8c\x04pass\x94\x8c\x0eoverall_rating\x94K\x04u\x8c\x14intermediate_outputs\x94}\x94\x8c\x10chain_of_thought\x94X\x08\x06\x00\x001) **Is the joke funny?**\n   The joke \"Why did the chicken cross the road? To get to the other side!\" is a classic joke that many consider to be humorous due to its simplicity and unexpected nature. However, as it's a very well-known punchline, some may find it less amusing for being overly familiar. Overall, it can elicit a chuckle, but it may not be considered original or particularly funny by everyone.\n\n2) **Is the content appropriate for all audiences?**\n   Yes, the joke is appropriate for all audiences. It does not contain any offensive language or themes, making it suitable for children and adults alike.\n\n3) **Is the joke culturally sensitive?**\n   Yes, the joke is culturally sensitive. It does not touch on any potentially sensitive topics or stereotypes. It\xe2\x80\x99s a universal humor that transcends cultural boundaries.\n\n4) **Is the joke politically correct?**\n   Yes, the joke is politically correct. It does not make any political statements or discriminatory remarks. It simply presents a light-hearted situation involving a chicken, which is neutral and inoffensive.\n\n5) **Is the joke aligned with the provided topic?**\n   Yes, the joke is aligned with the provided topic of a \"chicken joke.\" It directly references a chicken and is structured as a joke, fulfilling the prompt's requirements.\n\nIn summary, while the joke may lack originality, it is appropriate, sensitive, politically correct, and aligns well with the topic. The humor level can vary depending on personal taste, but overall, it meets the evaluation criteria.\x94s\x8c\x0foutput_logprobs\x94\x8c!openai.types.chat.chat_completion\x94\x8c\x0eChoiceLogprobs\x94\x93\x94)\x81\x94}\x94(\x8c\x08__dict__\x94}\x94(\x8c\x07content\x94]\x94(\x8c/openai.types.chat.chat_completion_token_logprob\x94\x8c\x1aChatCompletionTokenLogprob\x94\x93\x94)\x81\x94}\x94(h\x15}\x94(\x8c\x05token\x94\x8c\x02{\"\x94\x8c\x05bytes\x94]\x94(K{K\"e\x8c\x07logprob\x94G\xbf5\xfe.\xba\x97\xb1\xde\x8c\x0ctop_logprobs\x94]\x94(h\x19\x8c\nTopLogprob\x94\x93\x94)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02{\"\x94h!]\x94(K{K\"eh#G\xbf5\xfe.\xba\x97\xb1\xdeu\x8c\x12__pydantic_extra__\x94}\x94\x8c\x17__pydantic_fields_set__\x94\x8f\x94(h\x1fh#h!\x90\x8c\x14__pydantic_private__\x94Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02{\n\x94h!]\x94(K{K\neh#G\xc0 \x00,\nJ\x05\xdeuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x01{\x94h!]\x94K{ah#G\xc0/\x80,\nJ\x05\xdeuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03{\r\n\x94h!]\x94(K{K\rK\neh#G\xc01@\x16\x05%\x02\xefuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03{\n\n\x94h!]\x94(K{K\nK\neh#G\xc03\xc0\x16\x05%\x02\xefuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03 {\"\x94h!]\x94(K K{K\"eh#G\xc05\x00\x16\x05%\x02\xefuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03 {\n\x94h!]\x94(K K{K\neh#G\xc06\xe0\x16\x05%\x02\xefuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x01\n\x94h!]\x94K\nah#G\xc07\xe0\x16\x05%\x02\xefuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02{}\x94h!]\x94(K{K}eh#G\xc08 \x16\x05%\x02\xefuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05topic\x94h!]\x94(KtKoKpKiKceh#G\xbfS\x8a+<\x99\xb9Oh$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05topic\x94h!]\x94(KtKoKpKiKceh#G\xbfS\x8a+<\x99\xb9Ouh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07overall\x94h!]\x94(KoKvKeKrKaKlKleh#G\xc0\x1b\x818\xa2\x07\xfd%uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04type\x94h!]\x94(KtKyKpKeeh#G\xc0!\x80\x9c^o\xf7\xe0uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03top\x94h!]\x94(KtKoKpeh#G\xc0-\x00\x9c^o\xf7\xe0uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05theme\x94h!]\x94(KtKhKeKmKeeh#G\xc0.\x00\x9c^o\xf7\xe0uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05total\x94h!]\x94(KtKoKtKaKleh#G\xc00\x00N\x1eq\x04Ouh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06 topic\x94h!]\x94(K KtKoKpKiKceh#G\xc00@N\x1eq\x04Ouh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05Topic\x94h!]\x94(KTKoKpKiKceh#G\xc00\xa0N\x1eq\x04Ouh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x0bappropriate\x94h!]\x94(KaKpKpKrKoKpKrKiKaKtKeeh#G\xc00\xa0N\x1eq\x04Ouh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05title\x94h!]\x94(KtKiKtKlKeeh#G\xc00\xc0N\x1eq\x04Ouh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\n_alignment\x94h!]\x94(K_KaKlKiKgKnKmKeKnKteh#G\xbe\xc1\x9f\x96D1\x8b\xf2h$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\n_alignment\x94h!]\x94(K_KaKlKiKgKnKmKeKnKteh#G\xbe\xc1\x9f\x96D1\x8b\xf2uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\n alignment\x94h!]\x94(K KaKlKiKgKnKmKeKnKteh#G\xc0+\x00\x00C\x1b\xde\x83uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06_align\x94h!]\x94(K_KaKlKiKgKneh#G\xc0.@\x00C\x1b\xde\x83uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\n_ALIGNMENT\x94h!]\x94(K_KAKLKIKGKNKMKEKNKTeh#G\xc0.\x80\x00C\x1b\xde\x83uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\tAlignment\x94h!]\x94(KAKlKiKgKnKmKeKnKteh#G\xc00\xc0\x00!\x8d\xefAuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x0b_assignment\x94h!]\x94(K_KaKsKsKiKgKnKmKeKnKteh#G\xc01@\x00!\x8d\xefAuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\n Alignment\x94h!]\x94(K KAKlKiKgKnKmKeKnKteh#G\xc01@\x00!\x8d\xefAuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03_al\x94h!]\x94(K_KaKleh#G\xc01\xa0\x00!\x8d\xefAuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x0b_similarity\x94h!]\x94(K_KsKiKmKiKlKaKrKiKtKyeh#G\xc01\xe0\x00!\x8d\xefAuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07_rating\x94h!]\x94(K_KrKaKtKiKnKgeh#G\xc02 \x00!\x8d\xefAuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02\":\x94h!]\x94(K\"K:eh#G\x00\x00\x00\x00\x00\x00\x00\x00h$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02\":\x94h!]\x94(K\"K:eh#G\x00\x00\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04\xe2\x80\x9d:\x94h!]\x94(K\xe2K\x80K\x9dK:eh#G\xc02@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03\\\":\x94h!]\x94(K\\K\"K:eh#G\xc03\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02':\x94h!]\x94(K'K:eh#G\xc04 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03\":\"\x94h!]\x94(K\"K:K\"eh#G\xc04\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02`:\x94h!]\x94(K`K:eh#G\xc05\xa0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06\xe2\x80\x9d\xef\xbc\x9a\x94h!]\x94(K\xe2K\x80K\x9dK\xefK\xbcK\x9aeh#G\xc06`\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03\xc2\xbb:\x94h!]\x94(K\xc2K\xbbK:eh#G\xc07 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03+\":\x94h!]\x94(K+K\"K:eh#G\xc07@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03\":[\x94h!]\x94(K\"K:K[eh#G\xc07\x80\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x015\x94h!]\x94K5ah#G\xbe\xf1\x93\xc3:x\xd77h$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1fjY\x01\x00\x00h!]\x94K5ah#G\xbe\xf1\x93\xc3:x\xd77uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x014\x94h!]\x94K4ah#G\xc0&\x00\x02:l\xe3Xuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x01 \x94h!]\x94K ah#G\xc01\xc0\x01\x1d6q\xacuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x013\x94h!]\x94K3ah#G\xc07\xc0\x01\x1d6q\xacuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02  \x94h!]\x94(K K eh#G\xc08\xa0\x01\x1d6q\xacuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x01-\x94h!]\x94K-ah#G\xc0; \x01\x1d6q\xacuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x01f\x94h!]\x94Kfah#G\xc0;0\x01\x1d6q\xacuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x01\t\x94h!]\x94K\tah#G\xc0;0\x01\x1d6q\xacuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03   \x94h!]\x94(K K K eh#G\xc0;@\x01\x1d6q\xacuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x01\"\x94h!]\x94K\"ah#G\xc0;p\x01\x1d6q\xacuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02,\"\x94h!]\x94(K,K\"eh#G\x00\x00\x00\x00\x00\x00\x00\x00h$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02,\"\x94h!]\x94(K,K\"eh#G\x00\x00\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x01,\x94h!]\x94K,ah#G\xc05\x80\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03 ,\"\x94h!]\x94(K K,K\"eh#G\xc06`\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03,\"\\\x94h!]\x94(K,K\"K\\eh#G\xc07`\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03,\"%\x94h!]\x94(K,K\"K%eh#G\xc07\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03,\",\x94h!]\x94(K,K\"K,eh#G\xc0:\x80\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02,\n\x94h!]\x94(K,K\neh#G\xc0:\x90\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03,\r\n\x94h!]\x94(K,K\rK\neh#G\xc0< \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1fj\x8f\x01\x00\x00h!]\x94K\tah#G\xc0=p\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x01.\x94h!]\x94K.ah#G\xc0>@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07appropr\x94h!]\x94(KaKpKpKrKoKpKreh#G\xbf\x1d\x1c\xa4[(\x97\x91h$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07appropr\x94h!]\x94(KaKpKpKrKoKpKreh#G\xbf\x1d\x1c\xa4[(\x97\x91uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05appro\x94h!]\x94(KaKpKpKrKoeh#G\xc0\"\x80\x0e\x8c\x8a\xbd^uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x0bappropriate\x94h!]\x94(KaKpKpKrKoKpKrKiKaKtKeeh#G\xc0&\x80\x0e\x8c\x8a\xbd^uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\t appropri\x94h!]\x94(K KaKpKpKrKoKpKrKieh#G\xc0*\x80\x0e\x8c\x8a\xbd^uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02in\x94h!]\x94(KiKneh#G\xc00\xe0\x075~g\x0euh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05Appro\x94h!]\x94(KAKpKpKrKoeh#G\xc02\x80\x075~g\x0euh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06 Appro\x94h!]\x94(K KAKpKpKrKoeh#G\xc02\xa0\x075~g\x0euh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07overall\x94h!]\x94(KoKvKeKrKaKlKleh#G\xc02\xe0\x075~g\x0euh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04apro\x94h!]\x94(KaKpKrKoeh#G\xc03\xe0\x075~g\x0euh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\rapproximately\x94h!]\x94(KaKpKpKrKoKxKiKmKaKtKeKlKyeh#G\xc04@\x075~g\x0euh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x01i\x94h!]\x94Kiah#G\xbe\xaa~\xe0\xee\xab\x86\xb2h$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1fjA\x02\x00\x00h!]\x94Kiah#G\xbe\xaa~\xe0\xee\xab\x86\xb2uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06iation\x94h!]\x94(KiKaKtKiKoKneh#G\xc0.\xc0\x00!\x8d\xefAuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03iat\x94h!]\x94(KiKaKteh#G\xc0.\xc0\x00!\x8d\xefAuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07ateness\x94h!]\x94(KaKtKeKnKeKsKseh#G\xc00 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04iten\x94h!]\x94(KiKtKeKneh#G\xc00`\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04iann\x94h!]\x94(KiKaKnKneh#G\xc01\x80\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\t appropri\x94h!]\x94(K KaKpKpKrKoKpKrKieh#G\xc01\xa0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02ri\x94h!]\x94(KrKieh#G\xc01\xc0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06iately\x94h!]\x94(KiKaKtKeKlKyeh#G\xc01\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05laten\x94h!]\x94(KlKaKtKeKneh#G\xc01\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07ateness\x94h!]\x94(KaKtKeKnKeKsKseh#G\xbe\x89\xfcz\xe12u\x9dh$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07ateness\x94h!]\x94(KaKtKeKnKeKsKseh#G\xbe\x89\xfcz\xe12u\x9duh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04aten\x94h!]\x94(KaKtKeKneh#G\xc0/@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05ensen\x94h!]\x94(KeKnKsKeKneh#G\xc05@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04ated\x94h!]\x94(KaKtKeKdeh#G\xc06 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06teness\x94h!]\x94(KtKeKnKeKsKseh#G\xc06@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04ates\x94h!]\x94(KaKtKeKseh#G\xc06`\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05eness\x94h!]\x94(KeKnKeKsKseh#G\xc06\xa0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04onen\x94h!]\x94(KoKnKeKneh#G\xc06\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04uten\x94h!]\x94(KuKtKeKneh#G\xc07\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06enness\x94h!]\x94(KeKnKnKeKsKseh#G\xc07\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03\":\"\x94h!]\x94(K\"K:K\"eh#G\x00\x00\x00\x00\x00\x00\x00\x00h$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03\":\"\x94h!]\x94(K\"K:K\"eh#G\x00\x00\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04\":\"'\x94h!]\x94(K\"K:K\"K'eh#G\xc02\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04 \":\"\x94h!]\x94(K K\"K:K\"eh#G\xc04 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06\":\"\",\"\x94h!]\x94(K\"K:K\"K\"K,K\"eh#G\xc04\x80\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04\":[\"\x94h!]\x94(K\"K:K[K\"eh#G\xc05\xc0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07<|end|>\x94h!Nh#G\xc05\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04\":\"+\x94h!]\x94(K\"K:K\"K+eh#G\xc05\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04\":{\"\x94h!]\x94(K\"K:K{K\"eh#G\xc06@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03':'\x94h!]\x94(K'K:K'eh#G\xc06\xf0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02\":\x94h!]\x94(K\"K:eh#G\xc07\xf0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04pass\x94h!]\x94(KpKaKsKseh#G\x00\x00\x00\x00\x00\x00\x00\x00h$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04pass\x94h!]\x94(KpKaKsKseh#G\x00\x00\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05 pass\x94h!]\x94(K KpKaKsKseh#G\xc03 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04fail\x94h!]\x94(KfKaKiKleh#G\xc07\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03pas\x94h!]\x94(KpKaKseh#G\xc08\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05.pass\x94h!]\x94(K.KpKaKsKseh#G\xc08\xa0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04Pass\x94h!]\x94(KPKaKsKseh#G\xc09\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04PASS\x94h!]\x94(KPKAKSKSeh#G\xc09 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06passed\x94h!]\x94(KpKaKsKsKeKdeh#G\xc09\xc0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05-pass\x94h!]\x94(K-KpKaKsKseh#G\xc09\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06passes\x94h!]\x94(KpKaKsKsKeKseh#G\xc0: \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03\",\"\x94h!]\x94(K\"K,K\"eh#G\x00\x00\x00\x00\x00\x00\x00\x00h$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03\",\"\x94h!]\x94(K\"K,K\"eh#G\x00\x00\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04 \",\"\x94h!]\x94(K K\"K,K\"eh#G\xc02\xc0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02,\"\x94h!]\x94(K,K\"eh#G\xc04\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04.\",\"\x94h!]\x94(K.K\"K,K\"eh#G\xc04@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07<|end|>\x94h!Nh#G\xc05\xa0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03','\x94h!]\x94(K'K,K'eh#G\xc06 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04\",\"#\x94h!]\x94(K\"K,K\"K#eh#G\xc07 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04\",\"+\x94h!]\x94(K\"K,K\"K+eh#G\xc07\xf0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05\\\",\\\"\x94h!]\x94(K\\K\"K,K\\K\"eh#G\xc08@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04\",\"\\\x94h!]\x94(K\"K,K\"K\\eh#G\xc08\x90\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07overall\x94h!]\x94(KoKvKeKrKaKlKleh#G\xbe\x89\xfcz\xe12u\x9dh$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07overall\x94h!]\x94(KoKvKeKrKaKlKleh#G\xbe\x89\xfcz\xe12u\x9duh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07Overall\x94h!]\x94(KOKvKeKrKaKlKleh#G\xc00\xa0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x08 overall\x94h!]\x94(K KoKvKeKrKaKlKleh#G\xc02@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x01c\x94h!]\x94Kcah#G\xc06\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x08overview\x94h!]\x94(KoKvKeKrKvKiKeKweh#G\xc08\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05total\x94h!]\x94(KtKoKtKaKleh#G\xc08@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04over\x94h!]\x94(KoKvKeKreh#G\xc08\xa0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x08 Overall\x94h!]\x94(K KOKvKeKrKaKlKleh#G\xc09 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06\xe6\x95\xb4\xe4\xbd\x93\x94h!]\x94(K\xe6K\x95K\xb4K\xe4K\xbdK\x93eh#G\xc09`\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05polit\x94h!]\x94(KpKoKlKiKteh#G\xc0:\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07_rating\x94h!]\x94(K_KrKaKtKiKnKgeh#G\xbe\x94\xfe$\xc4\xceLIh$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07_rating\x94h!]\x94(K_KrKaKtKiKnKgeh#G\xbe\x94\xfe$\xc4\xceLIuh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07 rating\x94h!]\x94(K KrKaKtKiKnKgeh#G\xc0/@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06rating\x94h!]\x94(KrKaKtKiKnKgeh#G\xc01\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07 Rating\x94h!]\x94(K KRKaKtKiKnKgeh#G\xc01\xa0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06Rating\x94h!]\x94(KRKaKtKiKnKgeh#G\xc01\xc0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07-rating\x94h!]\x94(K-KrKaKtKiKnKgeh#G\xc01\xc0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07.rating\x94h!]\x94(K.KrKaKtKiKnKgeh#G\xc02\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05_rate\x94h!]\x94(K_KrKaKtKeeh#G\xc03\x80\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\t_rotation\x94h!]\x94(K_KrKoKtKaKtKiKoKneh#G\xc04 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02_r\x94h!]\x94(K_Kreh#G\xc04 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02\":\x94h!]\x94(K\"K:eh#G\x00\x00\x00\x00\x00\x00\x00\x00h$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02\":\x94h!]\x94(K\"K:eh#G\x00\x00\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04\xe2\x80\x9d:\x94h!]\x94(K\xe2K\x80K\x9dK:eh#G\xc04\xc0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03\\\":\x94h!]\x94(K\\K\"K:eh#G\xc04\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02':\x94h!]\x94(K'K:eh#G\xc05@\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03\":\"\x94h!]\x94(K\"K:K\"eh#G\xc06\xa0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07<|end|>\x94h!Nh#G\xc06\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x06\xe2\x80\x9d\xef\xbc\x9a\x94h!]\x94(K\xe2K\x80K\x9dK\xefK\xbcK\x9aeh#G\xc07\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02`:\x94h!]\x94(K`K:eh#G\xc07\x90\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03\":[\x94h!]\x94(K\"K:K[eh#G\xc08\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03 \":\x94h!]\x94(K K\"K:eh#G\xc08 \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1fje\x01\x00\x00h!]\x94K4ah#G\xbfdI\x15\x1e\x7f\x84\xe1h$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1fje\x01\x00\x00h!]\x94K4ah#G\xbfdI\x15\x1e\x7f\x84\xe1uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1fjs\x01\x00\x00h!]\x94K3ah#G\xc0\x18\x02\x89\x11\x8c\x19~uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1fjY\x01\x00\x00h!]\x94K5ah#G\xc0,\x81D\xaaS\xfc\x01uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1fjl\x01\x00\x00h!]\x94K ah#G\xc05\x10\xa2Dc\x06`uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x012\x94h!]\x94K2ah#G\xc070\xa2Dc\x06`uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1fj\x81\x01\x00\x00h!]\x94K-ah#G\xc08\xd0\xa2Dc\x06`uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02\n\n\x94h!]\x94(K\nK\neh#G\xc09\x80\xa2Dc\x06`uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1fh_h!]\x94K\nah#G\xc09\xc0\xa2Dc\x06`uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02  \x94h!]\x94(K K eh#G\xc09\xf0\xa2Dc\x06`uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1fj\x88\x01\x00\x00h!]\x94Kfah#G\xc0:0\xa2Dc\x06`uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nubh\x1b)\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x01}\x94h!]\x94K}ah#G\x00\x00\x00\x00\x00\x00\x00\x00h$]\x94(h')\x81\x94}\x94(h\x15}\x94(h\x1fj\xf3\x04\x00\x00h!]\x94K}ah#G\x00\x00\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02 }\x94h!]\x94(K K}eh#G\xc01\xe0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02,\"\x94h!]\x94(K,K\"eh#G\xc05`\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x02}\n\x94h!]\x94(K}K\neh#G\xc07\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03}\n\n\x94h!]\x94(K}K\nK\neh#G\xc08\xc0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1fj\xea\x01\x00\x00h!]\x94K.ah#G\xc0:\x90\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x03}\r\n\x94h!]\x94(K}K\rK\neh#G\xc0; \x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x05}\r\n\r\n\x94h!]\x94(K}K\rK\nK\rK\neh#G\xc0=\x90\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x04}\n\n\n\x94h!]\x94(K}K\nK\nK\neh#G\xc0=\xa0\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubh')\x81\x94}\x94(h\x15}\x94(h\x1f\x8c\x07}\n\n\n\n\n\n\x94h!]\x94(K}K\nK\nK\nK\nK\nK\neh#G\xc0>\x00\x00\x00\x00\x00\x00uh-}\x94h/\x8f\x94(h\x1fh#h!\x90h1Nubeuh-}\x94h/\x8f\x94(h\x1fh#h!h$\x90h1Nube\x8c\x07refusal\x94Nuh-}\x94h/\x8f\x94(h\x17j<\x05\x00\x00\x90h1Nubub."

kiln_ai/adapters/fine_tune/__init__.py

@@ -8,7 +8,7 @@ from . import base_finetune, dataset_formatter, finetune_registry, openai_finetu
 
 __all__ = [
     "base_finetune",
-    "openai_finetune",
     "dataset_formatter",
     "finetune_registry",
+    "openai_finetune",
 ]

kiln_ai/adapters/fine_tune/base_finetune.py

@@ -16,6 +16,7 @@ class FineTuneStatus(BaseModel):
 
     status: FineTuneStatusType
     message: str | None = None
+    error_details: str | None = None
 
 
 class FineTuneParameter(BaseModel):