judgeval 0.2.0__py3-none-any.whl → 0.3.1__py3-none-any.whl

{judgeval-0.2.0.dist-info → judgeval-0.3.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: judgeval
-Version: 0.2.0
+Version: 0.3.1
 Summary: Judgeval Package
 Project-URL: Homepage, https://github.com/JudgmentLabs/judgeval
 Project-URL: Issues, https://github.com/JudgmentLabs/judgeval/issues
@@ -14,6 +14,7 @@ Requires-Dist: anthropic
 Requires-Dist: boto3
 Requires-Dist: datamodel-code-generator>=0.31.1
 Requires-Dist: google-genai
+Requires-Dist: groq>=0.30.0
 Requires-Dist: langchain-anthropic
 Requires-Dist: langchain-core
 Requires-Dist: langchain-huggingface
@@ -22,6 +23,9 @@ Requires-Dist: litellm>=1.61.15
 Requires-Dist: matplotlib>=3.10.3
 Requires-Dist: nest-asyncio
 Requires-Dist: openai
+Requires-Dist: opentelemetry-api>=1.34.1
+Requires-Dist: opentelemetry-sdk>=1.34.1
+Requires-Dist: orjson>=3.9.0
 Requires-Dist: pandas
 Requires-Dist: python-dotenv==1.0.1
 Requires-Dist: python-slugify>=8.0.4
@@ -39,7 +43,7 @@ Description-Content-Type: text/markdown
     Enable self-learning agents with traces, evals, and environment data.
 </div>
 
-## [Docs](https://docs.judgmentlabs.ai/)  •  [Judgment Cloud](https://app.judgmentlabs.ai/register)  • [Self-Host](https://docs.judgmentlabs.ai/documentation/self-hosting/get-started)
+## [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/)
 
  [Demo](https://www.youtube.com/watch?v=1S4LixpVbcc) • [Bug Reports](https://github.com/JudgmentLabs/judgeval/issues) • [Changelog](https://docs.judgmentlabs.ai/changelog/2025-04-21)
 
@@ -139,7 +143,7 @@ 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/trace_demo.png" alt="Judgment Platform Trace Example" width="800" /></p>
+<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.
@@ -152,9 +156,9 @@ You'll see your trace exported to the Judgment Platform:
 
 |  |  |
 |:---|:---:|
-| <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/trace_screenshot.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/experiments_page.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/error_analysis_dashboard.png" alt="Monitoring Dashboard" width="1200"/></p> |
+| <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> |
 
 ## 🏢 Self-Hosting

{judgeval-0.2.0.dist-info → judgeval-0.3.1.dist-info}/RECORD

@@ -1,47 +1,45 @@
 judgeval/__init__.py,sha256=HM1M8hmqRum6G554QKkXhB4DF4f5eh_xtYo0Kf-t3kw,332
 judgeval/clients.py,sha256=JnB8n90GyXiYaGmSEYaA67mdJSnr3SIrzArao7NGebw,980
-judgeval/constants.py,sha256=rfl4gW9_4irxgamjTC-jvDj2ATSUrjEu0UAHZ4pLLtY,4081
-judgeval/evaluation_run.py,sha256=PZeoKS7JCsO2gzdo8jeq8786yn01Ccrq0xuCNUu9CPo,2797
-judgeval/judgment_client.py,sha256=tUgKS2sV8QZUxjdh3mP2PSBnC7Bci1e8ur8muvrgzBM,14011
+judgeval/constants.py,sha256=hWed25HwGUJy-tePbtoUZ0_Zg0X_MkAH84KiH-OHHFI,4150
+judgeval/dataset.py,sha256=rjV54XNTslNNtf-Uu2ndDIh602ZwSCFhPg2NuckDJ-w,6081
+judgeval/evaluation_run.py,sha256=edNpO444Fwt2ykWsflIzlYdDJUlUfbpXHHQSKfFS4y0,2876
+judgeval/judgment_client.py,sha256=vPoxbmxAlhbG5rXXqxWjMbyEqOI044BaQanr1fev2CE,11723
 judgeval/rules.py,sha256=CoQjqmP8daEXewMkplmA-7urubDtweOr5O6z8klVwLI,20031
-judgeval/run_evaluation.py,sha256=h05MI7S5q6cmm_mFuM_nqHqNIu-IHXkisoZat4YOSDE,26405
+judgeval/run_evaluation.py,sha256=7J6FHhWhB-IDPMSOcWkrjTpSNm2v3s_KBq8Np3y2pys,27652
 judgeval/version_check.py,sha256=FoLEtpCjDw2HuDQdpw5yT29UtwumSc6ZZN6AV_c9Mnw,1057
 judgeval/common/__init__.py,sha256=KH-QJyWtQ60R6yFIBDYS3WGRiNpEu1guynpxivZvpBQ,309
 judgeval/common/exceptions.py,sha256=OkgDznu2wpBQZMXiZarLJYNk1HIcC8qYW7VypDC3Ook,556
 judgeval/common/logger.py,sha256=514eFLYWS_UL8VY-zAR2ePUlpQe4rbYlleLASFllLE4,1511
-judgeval/common/utils.py,sha256=GhCEv8i_7JK4DJeUlMmibqEUy9ZVHxJAlFO_CriAzg4,34323
+judgeval/common/utils.py,sha256=oxGDRVWOICKWeyGgsoc36_yAyHSYF4XtH842Mkznwis,34739
 judgeval/common/api/__init__.py,sha256=-E7lpZz1fG8puR_aYUMfPmQ-Vyhd0bgzoaU5EhIuFjQ,114
-judgeval/common/api/api.py,sha256=BGtAGGRDqxs8DrA0ye8BPZ6KBsgJ2C0Dca4vvA55d6g,13049
-judgeval/common/api/constants.py,sha256=azA0eyz4q33SWS795NHhaKDKNmVHBWAAGe5_sk37nDU,4297
+judgeval/common/api/api.py,sha256=wty02HYANeOYlM8fHOLc33ux5bu9Ieq7iRqCr-UP0ng,14157
+judgeval/common/api/constants.py,sha256=vAW94pbyTS6rv1TKpt7z6xxMJvTaAxFiy1D4kzuLHeg,4567
 judgeval/common/storage/__init__.py,sha256=a-PI7OL-ydyzugGUKmJKRBASnK-Q-gs82L9K9rSyJP8,90
-judgeval/common/storage/s3_storage.py,sha256=UvAKGSa0S1BnNprzDKHMAfyT-8zlMAOM5kCrXcVN0HE,3743
+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=Ij-KDD3dVXHK_6NPk-VbTH_Mo8GZq5h4Zl5ii5QMjnE,72403
+judgeval/common/tracer/core.py,sha256=6a67h8WfI4T5YV4TXqZqAAbOPptA0yaIV38pe7Urf_0,73813
 judgeval/common/tracer/otel_exporter.py,sha256=kZLlOQ6afQE4dmb9H1wgU4P3H5PG1D_zKyvnpWcT5Ak,3899
-judgeval/common/tracer/otel_span_processor.py,sha256=3cMETvrNlwrTkS_XDdTNRhjVw_6TdgnojpQhDK9sbOs,7484
+judgeval/common/tracer/otel_span_processor.py,sha256=W7SM62KnxJ48vC9WllIHRKaLlvxkCwqYoT4KqZLfGNs,6497
 judgeval/common/tracer/span_processor.py,sha256=eFjTgSWSkM6BWE94CrvgafDg_WkxLsFL_MafwBG-p9M,1145
-judgeval/common/tracer/span_transformer.py,sha256=YIHEmr35o6_uX931JbD1PFIcLIWTVumWrJ198Ys391k,7544
+judgeval/common/tracer/span_transformer.py,sha256=nCnwRC52OKfYRFnsOwGdPaqb_U17yn5S_9jfhv1GaLM,7803
 judgeval/common/tracer/trace_manager.py,sha256=7KLWBrz5GE_138DHL_eRjhx4-LNfXKz1q_XIDfg6nw8,2992
 judgeval/data/__init__.py,sha256=1QagDcSQtfnJ632t9Dnq8d7XjAqhmY4mInOWt8qH9tM,455
-judgeval/data/example.py,sha256=6xtPTwWUsZ0HdErU-g954nCv64fsbnS1I5xuEvs14EA,2027
-judgeval/data/judgment_types.py,sha256=s1oea01AEBQBdqQntXhTbMiuDGAxvs2iGoxrR2uLnUw,9538
-judgeval/data/result.py,sha256=hHKiMMEl9Qv3EvK5UH8Y5YDu8VyvrHzNqlKatrq4UUY,2450
+judgeval/data/example.py,sha256=kRskIgsjwcvv2Y8jaPwV-PND7zlmMbFsvRVQ_b7SZY0,914
+judgeval/data/judgment_types.py,sha256=KE1HrFLfSxiu1zutaiZ7B7La9PGXIAsoWpo_5iy645c,8336
+judgeval/data/result.py,sha256=OtSnBUrdQpjyAqxXRLTW3wC9v9lOm_GqzL14ccRQxrg,2124
 judgeval/data/scorer_data.py,sha256=5QBHtvOIWOq0Rn9_uPJzAMRYMlWxMB-rXnG_6kV4Z4Y,2955
 judgeval/data/tool.py,sha256=iWQSdy5uNbIeACu3gQy1DC2oGYxRVYNfkkczWdQMAiA,99
-judgeval/data/trace.py,sha256=_cyCsyg2gwG7lyyv186xo4OvGH2QlJDuyIg-qh-CZNA,6994
+judgeval/data/trace.py,sha256=tDOuYFPUssQInjsmwyxcXq-W3IB29Vq340VzqafuKJc,6942
 judgeval/data/trace_run.py,sha256=c6pRSv09Vj016hxM49I3kMftCwWg8hhkfT_1kBXluSI,1600
-judgeval/data/datasets/__init__.py,sha256=IdNKhQv9yYZ_op0rdBacrFaFVmiiYQ3JTzXzxOTsEVQ,176
-judgeval/data/datasets/dataset.py,sha256=dDmTYSBRj4YEUhgYOebAcDm4N14nj3tcCqHj9y2Z1z0,12725
-judgeval/data/datasets/eval_dataset_client.py,sha256=8tiuwRC3oebc19KY-5b99Cxj0qq6ADW1NMDd1R1RhLc,7258
 judgeval/data/scripts/fix_default_factory.py,sha256=lvp2JwYZqz-XpD9LZNa3mANZVP-jJSZoNzolI6JWERM,591
-judgeval/data/scripts/openapi_transform.py,sha256=Rye-fErFtENAq3KKBKRUVR_oJdjYZtNzKRBKFkYS0XQ,3857
+judgeval/data/scripts/openapi_transform.py,sha256=Sm04JClzyP1ga8KA3gkIdsae8Hlx-XU7-x0gHCQYOhg,3877
 judgeval/integrations/langgraph.py,sha256=kJXLsgBY7DgsUTZyVQ47deDgHm887brFHfyIbuyerGw,29986
 judgeval/judges/__init__.py,sha256=6X7VSwrwsdxGBNxCyapVRWGghhKOy3MVxFNMQ62kCXM,308
 judgeval/judges/base_judge.py,sha256=_dz0qWsKRxzXxpRY9l6mrxTRYPSF2FE4ZXkrzhZ4gbY,986
-judgeval/judges/litellm_judge.py,sha256=LX4_KXb1Jp8IXif3vvOiKfRYH7ZkbQLs9AtWPGmj544,2483
-judgeval/judges/mixture_of_judges.py,sha256=wcHwLi9zU0uwKMqRVhcPdjiYKgWflX4dpUbU2kS9yg0,14825
-judgeval/judges/together_judge.py,sha256=r5k8ZcC6lnsFttGHhrocFtmglx2Cb3G-4ORKAeK-Nmw,2253
+judgeval/judges/litellm_judge.py,sha256=yt6QvwKMmxZcrUtjbn3EiO5aVg7CHM2YZkBCSQLS8jk,2509
+judgeval/judges/mixture_of_judges.py,sha256=cecQ8mRmz2-dDoZl2MGsrhZICkpIvRovGPK3su0kc8s,14889
+judgeval/judges/together_judge.py,sha256=5FADUhs6-FN1ZVV_1D3-8_gu9mPbZiG0PYTpme41SfM,2336
 judgeval/judges/utils.py,sha256=0CF9qtIUQUL3-W-qTGpmTjZbkUUBAM6TslDsrCHnTBU,2725
 judgeval/scorers/__init__.py,sha256=4H_cinTQ4EogZv59YEV-3U9EOTLppNwgAPTi1-jI9Fw,746
 judgeval/scorers/agent_scorer.py,sha256=TjwD_YglSywr3EowEojiCyg5qDgCRa5LRGc5nFdmIBc,703
@@ -49,8 +47,8 @@ judgeval/scorers/api_scorer.py,sha256=xlhqkeMUBFxl8daSXOTWOYwZjBAz7o6b4sVD5f8cIH
 judgeval/scorers/base_scorer.py,sha256=eDfQk8N8TQfM1ayJDWr0NTdSQxcbk9-VZHd0Igb9EbI,2878
 judgeval/scorers/example_scorer.py,sha256=2n45y3LMV1Q-ARyXLHqvVWETlnY1DqS7OLzPu9IBGz8,716
 judgeval/scorers/exceptions.py,sha256=ACDHK5-TWiF3NTk-wycaedpbrdobm-CvvC1JA_iP-Mk,179
-judgeval/scorers/score.py,sha256=t9prkpDapcOAyuOXtDHMmwrqVGW0C_Hvx1UIEGyafmI,6610
-judgeval/scorers/utils.py,sha256=WM7mTCQSa2Z_rJ-0Iv9dhuBmtkTfV0pFN7XEhxHdzsM,3959
+judgeval/scorers/score.py,sha256=2-M_AmOjIQR2c0qvuB4WIIQD-7zSNdzsWC8ttqltw2g,6601
+judgeval/scorers/utils.py,sha256=HQOYTJtNnsi_aPfMssePAaBbXpAv7LXgwUlWlDFuN2g,3965
 judgeval/scorers/judgeval_scorers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 judgeval/scorers/judgeval_scorers/api_scorers/__init__.py,sha256=GX4KkwPR2p-c0Y5mZingJa8EUfjAbMGhrmRBDBunOGw,1484
 judgeval/scorers/judgeval_scorers/api_scorers/answer_correctness.py,sha256=zJsU0VrUmRhY9qav48c6jTyDqUwI3JzhV9ajtlJCe0M,544
@@ -65,9 +63,9 @@ judgeval/scorers/judgeval_scorers/api_scorers/tool_dependency.py,sha256=Mcp1CjMN
 judgeval/scorers/judgeval_scorers/api_scorers/tool_order.py,sha256=Z2FLGBC7m_CLx-CMgXVuTvYvN0vY5yOcWA0ImBkeBfY,787
 judgeval/tracer/__init__.py,sha256=wkuXtOGDCrwgPPXlh_sSJmvGuWaAMHyNzk1TzB5f9aI,148
 judgeval/utils/alerts.py,sha256=3w_AjQrgfmOZvfqCridW8WAnHVxHHXokX9jNzVFyGjA,3297
-judgeval/utils/file_utils.py,sha256=wIEn8kjM0WrP216RGU_yhZhFOMWIS5ckigyHbzFSOMk,1774
+judgeval/utils/file_utils.py,sha256=PWHRs8dUr8iDwpglSSk4Yjd7C6ZhDzUaO-jV3m7riHM,1987
 judgeval/utils/requests.py,sha256=K3gUKrwL6TvwYKVYO5OeLWdUHn9NiUPmnIXhZEiEaHU,1534
-judgeval-0.2.0.dist-info/METADATA,sha256=1AYfJLsYTlofcz1PDkd9Np71U_NvOSWKG_T387xdQ-0,10188
-judgeval-0.2.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-judgeval-0.2.0.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
-judgeval-0.2.0.dist-info/RECORD,,
+judgeval-0.3.1.dist-info/METADATA,sha256=rMctXqjJ8pY2MEfeXMA9Ot_8GQiZUDZwErzCZ6rommQ,10348
+judgeval-0.3.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+judgeval-0.3.1.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
+judgeval-0.3.1.dist-info/RECORD,,

judgeval/data/datasets/__init__.py

@@ -1,4 +0,0 @@
-from judgeval.data.datasets.dataset import EvalDataset
-from judgeval.data.datasets.eval_dataset_client import EvalDatasetClient
-
-__all__ = ["EvalDataset", "EvalDatasetClient"]

judgeval/data/datasets/dataset.py

@@ -1,341 +0,0 @@
-import ast
-import csv
-import datetime
-import json
-import os
-import yaml
-from dataclasses import dataclass, field
-from typing import List, Union, Literal, Optional
-
-from judgeval.data import Example, Trace
-from judgeval.common.logger import judgeval_logger
-from judgeval.utils.file_utils import get_examples_from_yaml
-
-
-@dataclass
-class EvalDataset:
-    examples: List[Example]
-    traces: List[Trace]
-    _alias: Union[str, None] = field(default=None)
-    _id: Union[str, None] = field(default=None)
-    judgment_api_key: str = field(default="")
-    organization_id: str = field(default="")
-
-    def __init__(
-        self,
-        judgment_api_key: str = os.getenv("JUDGMENT_API_KEY", ""),
-        organization_id: str = os.getenv("JUDGMENT_ORG_ID", ""),
-        examples: Optional[List[Example]] = None,
-        traces: Optional[List[Trace]] = None,
-    ):
-        if not judgment_api_key:
-            judgeval_logger.error("No judgment_api_key provided")
-        self.examples = examples or []
-        self.traces = traces or []
-        self._alias = None
-        self._id = None
-        self.judgment_api_key = judgment_api_key
-        self.organization_id = organization_id
-
-    def add_from_json(self, file_path: str) -> None:
-        """
-        Adds examples from a JSON file.
-
-        The format of the JSON file is expected to be a dictionary with one key: "examples".
-        The value of the key is a list of dictionaries, where each dictionary represents an example.
-
-        The JSON file is expected to have the following format:
-        {
-        "examples": [
-            {
-                "input": "test input",
-                "actual_output": "test output",
-                "expected_output": "expected output",
-                "context": [
-                    "context1",
-                    "context2"
-                ],
-                "retrieval_context": [
-                    "retrieval1"
-                ],
-                "additional_metadata": {
-                    "key": "value"
-                },
-                "tools_called": [
-                    "tool1"
-                ],
-                "expected_tools": [
-                    "tool1",
-                    "tool2"
-                ],
-                "name": "test example",
-                "example_id": null,
-                "timestamp": "20241230_160117",
-                "trace_id": "123"
-            }
-            ]
-        }
-        """
-        try:
-            with open(file_path, "r") as file:
-                payload = json.load(file)
-                examples = payload.get("examples", [])
-        except FileNotFoundError:
-            judgeval_logger.error(f"JSON file not found: {file_path}")
-            raise FileNotFoundError(f"The file {file_path} was not found.")
-        except json.JSONDecodeError:
-            judgeval_logger.error(f"Invalid JSON file: {file_path}")
-            raise ValueError(f"The file {file_path} is not a valid JSON file.")
-
-        new_examples = [Example(**e) for e in examples]
-        for e in new_examples:
-            self.add_example(e)
-
-    def add_from_csv(
-        self,
-        file_path: str,
-        header_mapping: dict,
-        primary_delimiter: str = ",",
-        secondary_delimiter: str = ";",
-    ) -> None:
-        """
-        Add Examples from a CSV file.
-
-        Args:
-            file_path (str): Path to the CSV file
-            header_mapping (dict): Dictionary mapping Example headers to custom headers
-            primary_delimiter (str, optional): Main delimiter used in CSV file. Defaults to ","
-            secondary_delimiter (str, optional): Secondary delimiter for list fields. Defaults to ";"
-        """
-        try:
-            import pandas as pd
-        except ModuleNotFoundError:
-            raise ModuleNotFoundError(
-                "Please install pandas to use this method. 'pip install pandas'"
-            )
-
-        # Pandas naturally reads numbers in data files as ints, not strings (can lead to unexpected behavior)
-        df = pd.read_csv(file_path, dtype={"trace_id": str}, sep=primary_delimiter)
-        """
-        The user should pass in a dict mapping from Judgment Example headers to their custom defined headers.
-        Available headers for Example objects are as follows:
-
-        "input", "actual_output", "expected_output", "context", \
-        "retrieval_context", "additional_metadata", "tools_called", \
-        "expected_tools", "name", "comments", "source_file", "example", \
-        "trace_id"
-
-        We want to collect the examples separately which can
-        be determined by the "example" column. If the value is True, then it is an
-        example, and we expect the `input` and `actual_output` fields to be non-null.
-
-        We also assume that if there are multiple retrieval contexts, contexts, or tools called, they are separated by semicolons.
-        This can be adjusted using the `secondary_delimiter` parameter.
-        """
-        examples = []
-
-        def process_csv_row(value, header):
-            """
-            Maps a singular value in the CSV file to the appropriate type based on the header.
-            If value exists and can be split into type List[*], we will split upon the user's provided secondary delimiter.
-            """
-            # check that the CSV value is not null for entry
-            null_replacement = dict() if header == "additional_metadata" else None
-            if pd.isna(value) or value == "":
-                return null_replacement
-            try:
-                value = (
-                    ast.literal_eval(value)
-                    if header == "additional_metadata"
-                    else str(value)
-                )
-            except (ValueError, SyntaxError):
-                value = str(value)
-            if header in [
-                "context",
-                "retrieval_context",
-                "tools_called",
-                "expected_tools",
-            ]:
-                # attempt to split the value by the secondary delimiter
-                value = value.split(secondary_delimiter)
-
-            return value
-
-        for _, row in df.iterrows():
-            data = {
-                header: process_csv_row(row[header_mapping[header]], header)
-                for header in header_mapping
-            }
-            if "example" in header_mapping and row[header_mapping["example"]]:
-                if "name" in header_mapping:
-                    data["name"] = (
-                        row[header_mapping["name"]]
-                        if pd.notna(row[header_mapping["name"]])
-                        else None
-                    )
-                # every Example has `input` and `actual_output` fields
-                if data["input"] is not None and data["actual_output"] is not None:
-                    e = Example(**data)
-                    examples.append(e)
-                else:
-                    raise ValueError(
-                        "Every example must have an 'input' and 'actual_output' field."
-                    )
-
-        for e in examples:
-            self.add_example(e)
-
-    def add_from_yaml(self, file_path: str) -> None:
-        """
-        Adds examples from a YAML file.
-
-        The format of the YAML file is expected to be a dictionary with one key: "examples".
-        The value of the key is a list of dictionaries, where each dictionary represents an example.
-
-        The YAML file is expected to have the following format:
-        examples:
-          - input: "test input"
-            actual_output: "test output"
-            expected_output: "expected output"
-            context:
-              - "context1"
-              - "context2"
-            retrieval_context:
-              - "retrieval1"
-            additional_metadata:
-              key: "value"
-            tools_called:
-              - "tool1"
-            expected_tools:
-              - "tool1"
-              - "tool2"
-            name: "test example"
-            example_id: null
-            timestamp: "20241230_160117"
-            trace_id: "123"
-        """
-        examples = get_examples_from_yaml(file_path)
-
-        for e in examples:
-            self.add_example(e)
-
-    def add_example(self, e: Example) -> None:
-        self.examples.append(e)
-        # TODO if we need to add rank, then we need to do it here
-
-    def add_trace(self, t: Trace) -> None:
-        self.traces.append(t)
-
-    def save_as(
-        self,
-        file_type: Literal["json", "csv", "yaml"],
-        dir_path: str,
-        save_name: str | None = None,
-    ) -> None:
-        """
-        Saves the dataset as a file. Save only the examples.
-
-        Args:
-            file_type (Literal["json", "csv"]): The file type to save the dataset as.
-            dir_path (str): The directory path to save the file to.
-            save_name (str, optional): The name of the file to save. Defaults to None.
-        """
-        if not os.path.exists(dir_path):
-            os.makedirs(dir_path)
-        file_name = (
-            datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
-            if save_name is None
-            else save_name
-        )
-        complete_path = os.path.join(dir_path, f"{file_name}.{file_type}")
-        if file_type == "json":
-            with open(complete_path, "w") as file:
-                json.dump(
-                    {
-                        "examples": [e.to_dict() for e in self.examples],
-                    },
-                    file,
-                    indent=4,
-                )
-        elif file_type == "csv":
-            with open(complete_path, "w", newline="") as file:
-                writer = csv.writer(file)
-                writer.writerow(
-                    [
-                        "input",
-                        "actual_output",
-                        "expected_output",
-                        "context",
-                        "retrieval_context",
-                        "additional_metadata",
-                        "tools_called",
-                        "expected_tools",
-                        "name",
-                        "comments",
-                        "source_file",
-                        "example",
-                        "trace_id",
-                    ]
-                )
-                for e in self.examples:
-                    writer.writerow(
-                        [
-                            e.input,
-                            e.actual_output,
-                            e.expected_output,
-                            ";".join(e.context),
-                            ";".join(e.retrieval_context),
-                            e.additional_metadata,
-                            ";".join(e.tools_called),
-                            ";".join(e.expected_tools),
-                            e.name,
-                            None,  # Example does not have comments
-                            None,  # Example does not have source file
-                            True,  # Adding an Example
-                        ]
-                    )
-
-        elif file_type == "yaml":
-            with open(complete_path, "w") as file:
-                yaml_data = {
-                    "examples": [
-                        {
-                            "input": e.input,
-                            "actual_output": e.actual_output,
-                            "expected_output": e.expected_output,
-                            "context": e.context,
-                            "retrieval_context": e.retrieval_context,
-                            "additional_metadata": e.additional_metadata,
-                            "tools_called": e.tools_called,
-                            "expected_tools": e.expected_tools,
-                            "name": e.name,
-                            "comments": None,  # Example does not have comments
-                            "source_file": None,  # Example does not have source file
-                            "example": True,  # Adding an Example
-                        }
-                        for e in self.examples
-                    ],
-                }
-                yaml.dump(yaml_data, file, default_flow_style=False)
-        else:
-            ACCEPTABLE_FILE_TYPES = ["json", "csv", "yaml"]
-            raise TypeError(
-                f"Invalid file type: {file_type}. Please choose from {ACCEPTABLE_FILE_TYPES}"
-            )
-
-    def __iter__(self):
-        return iter(self.examples)
-
-    def __len__(self):
-        return len(self.examples)
-
-    def __str__(self):
-        return (
-            f"{self.__class__.__name__}("
-            f"examples={self.examples}, "
-            f"traces={self.traces}, "
-            f"_alias={self._alias}, "
-            f"_id={self._id}"
-            f")"
-        )