judgeval 0.6.0__py3-none-any.whl → 0.7.0__py3-none-any.whl

judgeval/judgment_client.py

@@ -7,12 +7,11 @@ import os
 import importlib.util
 from pathlib import Path
 from uuid import uuid4
-from typing import Optional, List, Dict, Any, Union, Callable, TYPE_CHECKING
+from typing import Optional, List, Dict, Union
 
 from judgeval.data import (
     ScoringResult,
     Example,
-    Trace,
 )
 from judgeval.scorers import (
     APIScorerConfig,
@@ -22,19 +21,14 @@ from judgeval.data.evaluation_run import EvaluationRun
 from judgeval.run_evaluation import (
     run_eval,
     assert_test,
-    run_trace_eval,
 )
-from judgeval.data.trace_run import TraceRun
 from judgeval.common.api import JudgmentApiClient
 from judgeval.common.exceptions import JudgmentAPIError
-from judgeval.common.tracer import Tracer
 from judgeval.common.utils import validate_api_key
 from pydantic import BaseModel
 from judgeval.common.logger import judgeval_logger
 
 
-if TYPE_CHECKING:
-    from judgeval.integrations.langgraph import JudgevalCallbackHandler
 from judgeval.constants import DEFAULT_GPT_MODEL
 
 
@@ -86,47 +80,6 @@ class JudgmentClient(metaclass=SingletonMeta):
         else:
             judgeval_logger.info("Successfully initialized JudgmentClient!")
 
-    def run_trace_evaluation(
-        self,
-        scorers: List[Union[APIScorerConfig, BaseScorer]],
-        examples: Optional[List[Example]] = None,
-        function: Optional[Callable] = None,
-        tracer: Optional[Union[Tracer, JudgevalCallbackHandler]] = None,
-        traces: Optional[List[Trace]] = None,
-        tools: Optional[List[Dict[str, Any]]] = None,
-        project_name: str = "default_project",
-        eval_run_name: str = "default_eval_trace",
-        model: Optional[str] = DEFAULT_GPT_MODEL,
-    ) -> List[ScoringResult]:
-        try:
-            if examples and not function:
-                raise ValueError("Cannot pass in examples without a function")
-
-            if traces and function:
-                raise ValueError("Cannot pass in traces and function")
-
-            if examples and traces:
-                raise ValueError("Cannot pass in both examples and traces")
-
-            trace_run = TraceRun(
-                project_name=project_name,
-                eval_name=eval_run_name,
-                traces=traces,
-                scorers=scorers,
-                model=model,
-                organization_id=self.organization_id,
-                tools=tools,
-            )
-            return run_trace_eval(
-                trace_run, self.judgment_api_key, function, tracer, examples
-            )
-        except ValueError as e:
-            raise ValueError(
-                f"Please check your TraceRun object, one or more fields are invalid: \n{str(e)}"
-            )
-        except Exception as e:
-            raise Exception(f"An unexpected error occurred during evaluation: {str(e)}")
-
     def run_evaluation(
         self,
         examples: List[Example],
@@ -134,6 +87,7 @@ class JudgmentClient(metaclass=SingletonMeta):
         model: Optional[str] = DEFAULT_GPT_MODEL,
         project_name: str = "default_project",
         eval_run_name: str = "default_eval_run",
+        show_url: bool = True,
     ) -> List[ScoringResult]:
         """
         Executes an evaluation of `Example`s using one or more `Scorer`s
@@ -161,6 +115,7 @@ class JudgmentClient(metaclass=SingletonMeta):
             return run_eval(
                 eval,
                 self.judgment_api_key,
+                show_url=show_url,
             )
         except ValueError as e:
             raise ValueError(
@@ -217,57 +172,6 @@ class JudgmentClient(metaclass=SingletonMeta):
         )
         assert_test(results)
 
-    def assert_trace_test(
-        self,
-        scorers: List[Union[APIScorerConfig, BaseScorer]],
-        examples: Optional[List[Example]] = None,
-        function: Optional[Callable] = None,
-        tracer: Optional[Union[Tracer, JudgevalCallbackHandler]] = None,
-        traces: Optional[List[Trace]] = None,
-        tools: Optional[List[Dict[str, Any]]] = None,
-        model: Optional[str] = DEFAULT_GPT_MODEL,
-        project_name: str = "default_test",
-        eval_run_name: str = str(uuid4()),
-    ) -> None:
-        """
-        Asserts a test by running the evaluation and checking the results for success
-
-        Args:
-            examples (List[Example]): The examples to evaluate.
-            scorers (List[Union[APIScorerConfig, BaseScorer]]): A list of scorers to use for evaluation
-            model (str): The model used as a judge when using LLM as a Judge
-            project_name (str): The name of the project the evaluation results belong to
-            eval_run_name (str): A name for this evaluation run
-            function (Optional[Callable]): A function to use for evaluation
-            tracer (Optional[Union[Tracer, BaseCallbackHandler]]): A tracer to use for evaluation
-            tools (Optional[List[Dict[str, Any]]]): A list of tools to use for evaluation
-        """
-
-        # Check for enable_param_checking and tools
-        for scorer in scorers:
-            if hasattr(scorer, "kwargs") and scorer.kwargs is not None:
-                if scorer.kwargs.get("enable_param_checking") is True:
-                    if not tools:
-                        raise ValueError(
-                            f"You must provide the 'tools' argument to assert_test when using a scorer with enable_param_checking=True. If you do not want to do param checking, explicitly set enable_param_checking=False for the {scorer.__name__} scorer."
-                        )
-
-        results: List[ScoringResult]
-
-        results = self.run_trace_evaluation(
-            examples=examples,
-            traces=traces,
-            scorers=scorers,
-            model=model,
-            project_name=project_name,
-            eval_run_name=eval_run_name,
-            function=function,
-            tracer=tracer,
-            tools=tools,
-        )
-
-        assert_test(results)
-
     def _extract_scorer_name(self, scorer_file_path: str) -> str:
         """Extract scorer name from the scorer file by importing it."""
         try:
@@ -301,7 +205,7 @@ class JudgmentClient(metaclass=SingletonMeta):
             judgeval_logger.warning(f"Could not extract scorer name: {e}")
             return Path(scorer_file_path).stem
 
-    def save_custom_scorer(
+    def upload_custom_scorer(
         self,
         scorer_file_path: str,
         requirements_file_path: Optional[str] = None,
@@ -342,10 +246,6 @@ class JudgmentClient(metaclass=SingletonMeta):
             with open(requirements_file_path, "r") as f:
                 requirements_text = f.read()
 
-        # Upload to backend
-        judgeval_logger.info(
-            f"Uploading custom scorer: {unique_name}, this can take a couple of minutes..."
-        )
         try:
             response = self.api_client.upload_custom_scorer(
                 scorer_name=unique_name,

judgeval/run_evaluation.py

@@ -6,10 +6,10 @@ import time
 import orjson
 import sys
 import threading
-from typing import List, Dict, Union, Optional, Callable, Tuple, Any, TYPE_CHECKING
+from typing import List, Dict, Union, Tuple, Any, TYPE_CHECKING
 from rich import print as rprint
 
-from judgeval.data import ScorerData, ScoringResult, Example, Trace
+from judgeval.data import ScorerData, ScoringResult, Example
 from judgeval.scorers import BaseScorer, APIScorerConfig
 from judgeval.scorers.score import a_execute_scoring
 from judgeval.common.api import JudgmentApiClient
@@ -22,10 +22,7 @@ from judgeval.common.logger import judgeval_logger
 
 
 if TYPE_CHECKING:
-    from judgeval.common.tracer import Tracer
-    from judgeval.data.trace_run import TraceRun
     from judgeval.data.evaluation_run import EvaluationRun
-    from judgeval.integrations.langgraph import JudgevalCallbackHandler
 
 
 def safe_run_async(coro):
@@ -99,29 +96,6 @@ def execute_api_eval(evaluation_run: EvaluationRun) -> Dict:
         )
 
 
-def execute_api_trace_eval(trace_run: TraceRun, judgment_api_key: str) -> Dict:
-    """
-    Executes an evaluation of a list of `Trace`s using one or more `JudgmentScorer`s via the Judgment API.
-    """
-
-    try:
-        # submit API request to execute evals
-        if not judgment_api_key or not trace_run.organization_id:
-            raise ValueError("API key and organization ID are required")
-        api_client = JudgmentApiClient(judgment_api_key, trace_run.organization_id)
-        return api_client.run_trace_evaluation(trace_run.model_dump(warnings=False))
-    except Exception as e:
-        judgeval_logger.error(f"Error: {e}")
-
-        details = "An unknown error occurred."
-        if isinstance(e, JudgmentAPIException):
-            details = e.response_json.get("detail", "An unknown error occurred.")
-
-        raise JudgmentAPIError(
-            "An error occurred while executing the Judgment API request: " + details
-        )
-
-
 def check_missing_scorer_data(results: List[ScoringResult]) -> List[ScoringResult]:
     """
     Checks if any `ScoringResult` objects are missing `scorers_data`.
@@ -142,7 +116,7 @@ def check_missing_scorer_data(results: List[ScoringResult]) -> List[ScoringResul
 
 def log_evaluation_results(
     scoring_results: List[ScoringResult],
-    run: Union[EvaluationRun, TraceRun],
+    run: EvaluationRun,
     judgment_api_key: str,
 ) -> str:
     """
@@ -208,81 +182,6 @@ def check_examples(
             rprint("[green]Continuing...[/green]")
 
 
-def run_trace_eval(
-    trace_run: TraceRun,
-    judgment_api_key: str,
-    function: Optional[Callable] = None,
-    tracer: Optional[Union[Tracer, "JudgevalCallbackHandler"]] = None,
-    examples: Optional[List[Example]] = None,
-) -> List[ScoringResult]:
-    if function and tracer and examples is not None:
-        new_traces: List[Trace] = []
-
-        # Handle case where tracer is actually a callback handler
-        actual_tracer = tracer
-        if hasattr(tracer, "tracer") and hasattr(tracer.tracer, "traces"):
-            # This is a callback handler, get the underlying tracer
-            actual_tracer = tracer.tracer
-
-        if trace_run.project_name != actual_tracer.project_name:
-            raise ValueError(
-                f"Project name mismatch between run_trace_eval and tracer. "
-                f"Trace run: {trace_run.project_name}, "
-                f"Tracer: {actual_tracer.project_name}"
-            )
-
-        actual_tracer.offline_mode = True
-        actual_tracer.traces = []
-        judgeval_logger.info("Running agent function: ")
-        for example in examples:
-            if example.input:
-                if isinstance(example.input, str):
-                    function(example.input)
-                elif isinstance(example.input, dict):
-                    function(**example.input)
-                else:
-                    raise ValueError(
-                        f"Input must be string or dict, got {type(example.input)}"
-                    )
-            else:
-                function()
-
-        for i, trace in enumerate(actual_tracer.traces):
-            # We set the root-level trace span with the expected tools of the Trace
-            trace = Trace(**trace)
-            trace.trace_spans[0].expected_tools = examples[i].expected_tools
-            new_traces.append(trace)
-        trace_run.traces = new_traces
-        actual_tracer.traces = []
-
-    # Execute evaluation using Judgment API
-    try:  # execute an EvaluationRun with just JudgmentScorers
-        judgeval_logger.info("Executing Trace Evaluation... ")
-        response_data: Dict = execute_api_trace_eval(trace_run, judgment_api_key)
-        scoring_results = [
-            ScoringResult(**result) for result in response_data["results"]
-        ]
-    except JudgmentAPIError as e:
-        raise JudgmentAPIError(
-            f"An error occurred while executing the Judgment API request: {str(e)}"
-        )
-    except ValueError as e:
-        raise ValueError(
-            f"Please check your TraceRun object, one or more fields are invalid: {str(e)}"
-        )
-
-    # Convert the response data to `ScoringResult` objects
-    # TODO: allow for custom scorer on traces
-
-    url = log_evaluation_results(
-        response_data["agent_results"], trace_run, judgment_api_key
-    )
-    rprint(
-        f"\n🔍 You can view your evaluation results here: [rgb(106,0,255)][link={url}]View Results[/link]\n"
-    )
-    return scoring_results
-
-
 def _poll_evaluation_until_complete(
     experiment_run_id: str,
     project_name: str,
@@ -387,12 +286,15 @@ def progress_logger(stop_event, msg="Working...", interval=5):
 def run_eval(
     evaluation_run: EvaluationRun,
     judgment_api_key: str,
+    show_url: bool = True,
 ) -> List[ScoringResult]:
     """
     Executes an evaluation of `Example`s using one or more `Scorer`s
 
     Args:
         evaluation_run (EvaluationRun): Stores example and evaluation together for running
+        judgment_api_key (str): API key for authentication
+        show_url (bool): Whether to display the evaluation results URL. Defaults to True.
 
     Returns:
         List[ScoringResult]: A list of ScoringResult objects
@@ -481,9 +383,10 @@ def run_eval(
             scoring_result.model_dump(warnings=False) for scoring_result in results
         ]
         url = log_evaluation_results(send_results, evaluation_run, judgment_api_key)
-    rprint(
-        f"\n🔍 You can view your evaluation results here: [rgb(106,0,255)][link={url}]View Results[/link]\n"
-    )
+    if show_url:
+        rprint(
+            f"\n🔍 You can view your evaluation results here: [rgb(106,0,255)][link={url}]View Results[/link]\n"
+        )
     return results
 
 

{judgeval-0.6.0.dist-info → judgeval-0.7.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: judgeval
-Version: 0.6.0
+Version: 0.7.0
 Summary: Judgeval Package
 Project-URL: Homepage, https://github.com/JudgmentLabs/judgeval
 Project-URL: Issues, https://github.com/JudgmentLabs/judgeval/issues
@@ -12,6 +12,7 @@ Classifier: Programming Language :: Python :: 3
 Requires-Python: >=3.11
 Requires-Dist: boto3
 Requires-Dist: click<8.2.0
+Requires-Dist: fireworks-ai>=0.19.18
 Requires-Dist: langchain-anthropic
 Requires-Dist: langchain-core
 Requires-Dist: langchain-huggingface
@@ -39,7 +40,7 @@ Description-Content-Type: text/markdown
 
 <br>
 <div style="font-size: 1.5em;">
-    Enable self-learning agents with traces, evals, and environment data.
+    Enable self-learning agents with environment data and evals.
 </div>
 
 ## [Docs](https://docs.judgmentlabs.ai/)  •  [Judgment Cloud](https://app.judgmentlabs.ai/register)  • [Self-Host](https://docs.judgmentlabs.ai/documentation/self-hosting/get-started)  • [Landing Page](https://judgmentlabs.ai/)
@@ -56,11 +57,11 @@ We're hiring! Join us in our mission to enable self-learning agents by providing
 
 </div>
 
-Judgeval offers **open-source tooling** for tracing and evaluating autonomous, stateful agents. It **provides runtime data from agent-environment interactions** for continuous learning and self-improvement.
+Judgeval offers **open-source tooling** for evaluating autonomous, stateful agents. It **provides runtime data from agent-environment interactions** for continuous learning and self-improvement.
 
 ## 🎬 See Judgeval in Action
 
-**[Multi-Agent System](https://github.com/JudgmentLabs/judgment-cookbook/tree/main/cookbooks/agents/multi-agent) with complete observability:** (1) A multi-agent system spawns agents to research topics on the internet. (2) With just **3 lines of code**, Judgeval traces every input/output + environment response across all agent tool calls for debugging. (3) After completion, (4) export all interaction data to enable further environment-specific learning and optimization.
+**[Multi-Agent System](https://github.com/JudgmentLabs/judgment-cookbook/tree/main/cookbooks/agents/multi-agent) with complete observability:** (1) A multi-agent system spawns agents to research topics on the internet. (2) With just **3 lines of code**, Judgeval captures all environment responses across all agent tool calls for monitoring. (3) After completion, (4) export all interaction data to enable further environment-specific learning and optimization.
 
 <table style="width: 100%; max-width: 800px; table-layout: fixed;">
 <tr>
@@ -69,8 +70,8 @@ Judgeval offers **open-source tooling** for tracing and evaluating autonomous, s
   <br><strong>🤖 Agents Running</strong>
 </td>
 <td align="center" style="padding: 8px; width: 50%;">
-  <img src="assets/trace.gif" alt="Trace Demo" style="width: 100%; max-width: 350px; height: auto;" />
-  <br><strong>📊 Real-time Tracing</strong>
+  <img src="assets/trace.gif" alt="Capturing Environment Data Demo" style="width: 100%; max-width: 350px; height: auto;" />
+  <br><strong>📊 Capturing Environment Data </strong>
 </td>
 </tr>
 <tr>
@@ -111,54 +112,14 @@ export JUDGMENT_ORG_ID=...
 
 **If you don't have keys, [create an account](https://app.judgmentlabs.ai/register) on the platform!**
 
-## 🏁 Quickstarts
-
-### 🛰️ Tracing
-
-Create a file named `agent.py` with the following code:
-
-```python
-from judgeval.tracer import Tracer, wrap
-from openai import OpenAI
-
-client = wrap(OpenAI())  # tracks all LLM calls
-judgment = Tracer(project_name="my_project")
-
-@judgment.observe(span_type="tool")
-def format_question(question: str) -> str:
-    # dummy tool
-    return f"Question : {question}"
-
-@judgment.observe(span_type="function")
-def run_agent(prompt: str) -> str:
-    task = format_question(prompt)
-    response = client.chat.completions.create(
-        model="gpt-4.1",
-        messages=[{"role": "user", "content": task}]
-    )
-    return response.choices[0].message.content
-    
-run_agent("What is the capital of the United States?")
-```
-You'll see your trace exported to the Judgment Platform:
-
-<p align="center"><img src="assets/online_eval.png" alt="Judgment Platform Trace Example" width="1500" /></p>
-
-
-[Click here](https://docs.judgmentlabs.ai/documentation/tracing/introduction) for a more detailed explanation.
-
-
-<!-- Created by https://github.com/ekalinin/github-markdown-toc -->
-
 
 ## ✨ Features
 
 |  |  |
 |:---|:---:|
-| <h3>🔍 Tracing</h3>Automatic agent tracing integrated with common frameworks (LangGraph, OpenAI, Anthropic). **Tracks inputs/outputs, agent tool calls, latency, cost, and custom metadata** at every step.<br><br>**Useful for:**<br>• 🐛 Debugging agent runs <br>• 📋 Collecting agent environment data <br>• 🔬 Pinpointing performance bottlenecks| <p align="center"><img src="assets/agent_trace_example.png" alt="Tracing visualization" width="1200"/></p> |
 | <h3>🧪 Evals</h3>Build custom evaluators on top of your agents. Judgeval supports LLM-as-a-judge, manual labeling, and code-based evaluators that connect with our metric-tracking infrastructure. <br><br>**Useful for:**<br>• ⚠️ Unit-testing <br>• 🔬 A/B testing <br>• 🛡️ Online guardrails | <p align="center"><img src="assets/test.png" alt="Evaluation metrics" width="800"/></p> |
 | <h3>📡 Monitoring</h3>Get Slack alerts for agent failures in production. Add custom hooks to address production regressions.<br><br> **Useful for:** <br>• 📉 Identifying degradation early <br>• 📈 Visualizing performance trends across agent versions and time | <p align="center"><img src="assets/errors.png" alt="Monitoring Dashboard" width="1200"/></p> |
-| <h3>📊 Datasets</h3>Export traces and test cases to datasets for scaled analysis and optimization. Move datasets to/from Parquet, S3, etc. <br><br>Run evals on datasets as unit tests or to A/B test different agent configurations, enabling continuous learning from production interactions. <br><br> **Useful for:**<br>• 🗃️ Agent environment interaction data for optimization<br>• 🔄 Scaled analysis for A/B tests | <p align="center"><img src="assets/datasets_preview_screenshot.png" alt="Dataset management" width="1200"/></p> |
+| <h3>📊 Datasets</h3>Export environment interactions and test cases to datasets for scaled analysis and optimization. Move datasets to/from Parquet, S3, etc. <br><br>Run evals on datasets as unit tests or to A/B test different agent configurations, enabling continuous learning from production interactions. <br><br> **Useful for:**<br>• 🗃️ Agent environment interaction data for optimization<br>• 🔄 Scaled analysis for A/B tests | <p align="center"><img src="assets/datasets_preview_screenshot.png" alt="Dataset management" width="1200"/></p> |
 
 ## 🏢 Self-Hosting
 

{judgeval-0.6.0.dist-info → judgeval-0.7.0.dist-info}/RECORD

@@ -1,12 +1,12 @@
 judgeval/__init__.py,sha256=5Lm1JMYFREJGN_8X-Wpruu_ovwGLJ08gCzNAt-u-pQE,419
-judgeval/cli.py,sha256=IcL4_bGr9CtEeea1-AFqM_TEV_VomDlArlxh4IomiSQ,1754
+judgeval/cli.py,sha256=WTFTJKQ6LZI7K9o9KnCfTzsTEJnKfPuSURUpRFLiHp8,1756
 judgeval/clients.py,sha256=HHul68PV1om0dxsVZZu90TtCiy5zaqAwph16jXTQzQo,989
 judgeval/constants.py,sha256=UNoTLHgbpZHRInPM2ZaI3m0XokPkee5ILlg20reqhzo,4180
 judgeval/dataset.py,sha256=vOrDKam2I-K1WcVF5IBkQruCDvXTc8PRaFm4-dV0lXs,6220
-judgeval/judgment_client.py,sha256=-7xcBFowzXKedMINwfZCOL4FKucECWPNEY9QVMo_cys,13644
+judgeval/judgment_client.py,sha256=KxQP-EmhZUJOIFM2Zf_OJbxrgDpN1dRwxo4iVI9zLdA,9390
 judgeval/local_eval_queue.py,sha256=GmlXeZt7bfAJe1hPUjDg_irth4RkNqL2Zdi7VzboBzI,6984
 judgeval/rules.py,sha256=CoQjqmP8daEXewMkplmA-7urubDtweOr5O6z8klVwLI,20031
-judgeval/run_evaluation.py,sha256=gs-_v_i95LKlJj95G2RmQXvIyBfoldnd1pWCNO4UqsM,21985
+judgeval/run_evaluation.py,sha256=ETAP7srohMBAsRqvxHQHKsR5zt3Rzns_kNM_2ulxVdU,18084
 judgeval/version_check.py,sha256=FoLEtpCjDw2HuDQdpw5yT29UtwumSc6ZZN6AV_c9Mnw,1057
 judgeval/common/__init__.py,sha256=KH-QJyWtQ60R6yFIBDYS3WGRiNpEu1guynpxivZvpBQ,309
 judgeval/common/exceptions.py,sha256=OkgDznu2wpBQZMXiZarLJYNk1HIcC8qYW7VypDC3Ook,556
@@ -14,19 +14,24 @@ judgeval/common/logger.py,sha256=514eFLYWS_UL8VY-zAR2ePUlpQe4rbYlleLASFllLE4,151
 judgeval/common/utils.py,sha256=oxGDRVWOICKWeyGgsoc36_yAyHSYF4XtH842Mkznwis,34739
 judgeval/common/api/__init__.py,sha256=-E7lpZz1fG8puR_aYUMfPmQ-Vyhd0bgzoaU5EhIuFjQ,114
 judgeval/common/api/api.py,sha256=fWtMNln0o1wOhJ9wangWpyY_j3WF7P3at_LYPJEicP0,13670
-judgeval/common/api/constants.py,sha256=y0BDcQqHBZ7MwLd4gT5hLUF8UMs_GVwsJGC-ibfxCAw,4698
+judgeval/common/api/constants.py,sha256=N6rQZqMhFv2U8tOw-6pMH0uV7aGT9m8sw57ZkfDW97c,4689
 judgeval/common/api/json_encoder.py,sha256=QQgCe2FBmW1uWKx8yvuhr4U7_b4D0sG97GZtXHKnBdk,5881
 judgeval/common/storage/__init__.py,sha256=a-PI7OL-ydyzugGUKmJKRBASnK-Q-gs82L9K9rSyJP8,90
 judgeval/common/storage/s3_storage.py,sha256=0-bNKheqJJyBZ92KGrzQtd1zocIRWBlfn_58L4a-Ay0,3719
 judgeval/common/tracer/__init__.py,sha256=tJCJsmVmrL89Phv88gNCJ-j0ITPez6lh8vhMAAlLNSc,795
 judgeval/common/tracer/constants.py,sha256=yu5y8gMe5yb1AaBkPtAH-BNwIaAR3NwYCRoSf45wp5U,621
-judgeval/common/tracer/core.py,sha256=TQ80NODaJx7gzmntevDLA3evVJ3m2Zy2s0Pwd7APG9Y,84867
+judgeval/common/tracer/core.py,sha256=Vhh2LRgLdxa_yxUfMunv7l83tksuztm7F_oSwD92EXs,91681
 judgeval/common/tracer/otel_exporter.py,sha256=kZLlOQ6afQE4dmb9H1wgU4P3H5PG1D_zKyvnpWcT5Ak,3899
 judgeval/common/tracer/otel_span_processor.py,sha256=BD-FKXaZft5_3zqy1Qe_tpkudVOLop9AGhBjZUgp-Z8,6502
 judgeval/common/tracer/providers.py,sha256=3c3YOtKuoBjlTL0rc2HAGnUpppqvsyzrN5H6EKCqEi0,2733
 judgeval/common/tracer/span_processor.py,sha256=1NQxNSVWcb8qCFLmslSVMnaWdkOZmiFJnxeeN0i6vnU,1150
 judgeval/common/tracer/span_transformer.py,sha256=cfzz6RpTCOG9Io9knNlwtAW34p3wyK-u8jSNMu24p1w,7382
-judgeval/common/tracer/trace_manager.py,sha256=ltiXcWC-68DRc8uSa28qHiWRSIBf6NpYOPkZYooR8tg,3086
+judgeval/common/tracer/trace_manager.py,sha256=FAlkTNomb_TzSSnF7DnmP5nImBgHaA_SFNW1INzE1aI,3178
+judgeval/common/trainer/__init__.py,sha256=fkaBjtAynh1GZbvK2xbNTjuLFSDpPzj7u4Chf4vZsfs,209
+judgeval/common/trainer/config.py,sha256=kaWz0ni4ijtXpu8SF2jLEnw5yA2HqaUbvjiyqEnSrXE,4195
+judgeval/common/trainer/console.py,sha256=sZCoJqI6ZRArbJpxl3ZwNb9taYoEkgCpz9PF4IUbGjE,4818
+judgeval/common/trainer/trainable_model.py,sha256=tnhFH2Mp5hVht3utHVFPs2BxKoBQgRJrAzgzE5IfKEU,8842
+judgeval/common/trainer/trainer.py,sha256=dE-sOU26dNaWxPaN88XuN3f3XCizdHrRPNylrspCWQc,11815
 judgeval/data/__init__.py,sha256=1QagDcSQtfnJ632t9Dnq8d7XjAqhmY4mInOWt8qH9tM,455
 judgeval/data/evaluation_run.py,sha256=IirmYZ1_9N99eep7DDuoyshwjmpNK9bQCxCWXnnhhuI,4053
 judgeval/data/example.py,sha256=kRskIgsjwcvv2Y8jaPwV-PND7zlmMbFsvRVQ_b7SZY0,914
@@ -70,8 +75,8 @@ judgeval/utils/alerts.py,sha256=3w_AjQrgfmOZvfqCridW8WAnHVxHHXokX9jNzVFyGjA,3297
 judgeval/utils/async_utils.py,sha256=uNx1SopEc0quSjc8GBQqyba0SmCMAzv2NKIq6xYwttc,989
 judgeval/utils/file_utils.py,sha256=PWHRs8dUr8iDwpglSSk4Yjd7C6ZhDzUaO-jV3m7riHM,1987
 judgeval/utils/requests.py,sha256=K3gUKrwL6TvwYKVYO5OeLWdUHn9NiUPmnIXhZEiEaHU,1534
-judgeval-0.6.0.dist-info/METADATA,sha256=CulXMs0v5YrHjR3ntVX8xWKcZyxwEpo_nOYs_hkaeN8,10403
-judgeval-0.6.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-judgeval-0.6.0.dist-info/entry_points.txt,sha256=-eoeD-oDLn4A7MSgeBS9Akwanf3_0r0cgEleBcIOjg0,46
-judgeval-0.6.0.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
-judgeval-0.6.0.dist-info/RECORD,,
+judgeval-0.7.0.dist-info/METADATA,sha256=WvjnS9cY6RvmrLdtpJbNJN3AssRmIWp61dYr2ZUn0Bo,8877
+judgeval-0.7.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+judgeval-0.7.0.dist-info/entry_points.txt,sha256=-eoeD-oDLn4A7MSgeBS9Akwanf3_0r0cgEleBcIOjg0,46
+judgeval-0.7.0.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
+judgeval-0.7.0.dist-info/RECORD,,