judgeval 0.14.1__tar.gz → 0.16.0__tar.gz

judgeval-0.16.0/CONTRIBUTING.md

@@ -0,0 +1,10 @@
+# Contribute to Judgeval
+
+There are many ways to contribute to Judgeval:
+
+- Submit [bug reports](https://github.com/JudgmentLabs/judgeval/issues) and [feature requests](https://github.com/JudgmentLabs/judgeval/issues)
+- Review the documentation and submit [Pull Requests](https://github.com/JudgmentLabs/judgeval/pulls) to improve it
+- Speaking or writing about Judgment and letting us know!
+
+<!-- Contributors collage -->
+[![Contributors](https://contributors-img.web.app/image?repo=JudgmentLabs/judgeval)](https://github.com/JudgmentLabs/judgeval/graphs/contributors)

judgeval-0.16.0/PKG-INFO

@@ -0,0 +1,266 @@
+Metadata-Version: 2.4
+Name: judgeval
+Version: 0.16.0
+Summary: Judgeval Package
+Project-URL: Homepage, https://github.com/JudgmentLabs/judgeval
+Project-URL: Issues, https://github.com/JudgmentLabs/judgeval/issues
+Author-email: Andrew Li <andrew@judgmentlabs.ai>, Alex Shan <alex@judgmentlabs.ai>, Joseph Camyre <joseph@judgmentlabs.ai>
+License-Expression: Apache-2.0
+License-File: LICENSE.md
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.10
+Requires-Dist: boto3>=1.40.11
+Requires-Dist: click<8.2.0
+Requires-Dist: dotenv
+Requires-Dist: httpx>=0.28.1
+Requires-Dist: litellm<1.75.0
+Requires-Dist: opentelemetry-exporter-otlp>=1.36.0
+Requires-Dist: opentelemetry-sdk>=1.36.0
+Requires-Dist: orjson>=3.9.0
+Requires-Dist: typer>=0.9.0
+Provides-Extra: s3
+Requires-Dist: boto3>=1.40.11; extra == 's3'
+Provides-Extra: trainer
+Requires-Dist: fireworks-ai>=0.19.18; extra == 'trainer'
+Description-Content-Type: text/markdown
+
+<div align="center">
+
+<a href="https://judgmentlabs.ai/">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="assets/logo_darkmode.svg">
+    <img src="assets/logo_lightmode.svg" alt="Judgment Logo" width="400" />
+  </picture>
+</a>
+
+<br>
+
+## Agent Behavior Monitoring (ABM)
+
+Track and judge any agent behavior in online and offline setups. Set up Sentry-style alerts and analyze agent behaviors / topic patterns at scale! 
+
+[![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.judgmentlabs.ai/documentation)
+[![Judgment Cloud](https://img.shields.io/badge/Judgment%20Cloud-brightgreen)](https://app.judgmentlabs.ai/register)
+[![Self-Host](https://img.shields.io/badge/Self--Host-orange)](https://docs.judgmentlabs.ai/documentation/self-hosting/get-started)
+
+
+[![X](https://img.shields.io/badge/-X/Twitter-000?logo=x&logoColor=white)](https://x.com/JudgmentLabs)
+[![LinkedIn](https://custom-icon-badges.demolab.com/badge/LinkedIn%20-0A66C2?logo=linkedin-white&logoColor=fff)](https://www.linkedin.com/company/judgmentlabs)
+
+</div>
+
+
+</table>
+
+## [NEW] 🎆 Agent Reinforcement Learning
+
+Train your agents with multi-turn reinforcement learning using judgeval and [Fireworks AI](https://fireworks.ai/)! Judgeval's ABM now integrates with Fireworks' Reinforcement Fine-Tuning (RFT) endpoint, supporting gpt-oss, qwen3, Kimi2, DeepSeek, and more.
+
+Judgeval's agent monitoring infra provides a simple harness for integrating GRPO into any Python agent, giving builders a quick method to **try RL with minimal code changes** to their existing agents!
+
+```python
+await trainer.train(
+    agent_function=your_agent_function,  # entry point to your agent
+    scorers=[RewardScorer()],  # Custom scorer you define based on task criteria, acts as reward
+    prompts=training_prompts,  # Tasks
+    rft_provider="fireworks"
+)
+```
+
+**That's it!** Judgeval automatically manages trajectory collection and reward tagging - your agent can learn from production data with minimal code changes. 
+
+👉 Check out the [Wikipedia Racer notebook](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/rl/WikiRacingAgent_RL.ipynb), where an agent learns to navigate Wikipedia using RL, to see Judgeval in action.
+
+
+You can view and monitor training progress for free via the [Judgment Dashboard](https://app.judgmentlabs.ai/).
+
+
+## Judgeval Overview
+
+Judgeval is an open-source framework for agent behavior monitoring. Judgeval offers a toolkit to track and judge agent behavior in online and offline setups, enabling you to convert interaction data from production/test environments into improved agents. To get started, try running one of the notebooks below or dive deeper in our [docs](https://docs.judgmentlabs.ai/documentation).
+
+Our mission is to unlock the power of production data for agent development, enabling teams to improve their apps by catching real-time failures and optimizing over their users' preferences.
+
+## 📚 Cookbooks
+
+| Try Out | Notebook | Description |
+|:---------|:-----|:------------|
+| RL | [Wikipedia Racer](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/rl/WikiRacingAgent_RL.ipynb) | Train agents with reinforcement learning |
+| Online ABM | [Research Agent](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/monitoring/Research_Agent_Online_Monitoring.ipynb) | Monitor agent behavior in production |
+| Custom Scorers | [HumanEval](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/custom_scorers/HumanEval_Custom_Scorer.ipynb) | Build custom evaluators for your agents |
+| Offline Testing | [Get Started For Free] | Compare how different prompts, models, or agent configs affect performance across ANY metric |
+
+You can access our [repo of cookbooks](https://github.com/JudgmentLabs/judgment-cookbook).
+
+You can find a list of [video tutorials for Judgeval use cases](https://www.youtube.com/@Alexshander-JL).
+
+## Why Judgeval?
+
+🤖 **Simple to run multi-turn RL**: Optimize your agents with multi-turn RL without managing compute infrastructure or data pipelines. Just add a few lines of code to your existing agent code and train!
+
+⚙️ **Custom Evaluators**: No restriction to only monitoring with prefab scorers. Judgeval provides simple abstractions for custom Python scorers, supporting any LLM-as-a-judge rubrics/models and code-based scorers that integrate to our live agent-tracking infrastructure. [Learn more](https://docs.judgmentlabs.ai/documentation/evaluation/custom-scorers)
+
+🚨 **Production Monitoring**: Run any custom scorer in a hosted, virtualized secure container to flag agent behaviors online in production. Get Slack alerts for failures and add custom hooks to address regressions before they impact users. [Learn more](https://docs.judgmentlabs.ai/documentation/performance/online-evals)
+
+📊 **Behavior/Topic Grouping**: Group agent runs by behavior type or topic for deeper analysis. Drill down into subsets of users, agents, or use cases to reveal patterns of agent behavior.
+<!-- Add link to Bucketing docs once we have it -->
+<!-- 
+TODO: Once we have trainer code docs, plug in here
+-->
+
+🧪 **Run experiments on your agents**: Compare test different prompts, models, or agent configs across customer segments. Measure which changes improve agent performance and decrease bad agent behaviors.
+
+<!-- 
+Use this once we have AI PM features:
+
+**Run experiments on your agents**: A/B test different prompts, models, or agent configs across customer segments. Measure which changes improve agent performance and decrease bad agent behaviors. [Learn more]
+
+-->
+
+## 🛠️ Quickstart
+
+Get started with Judgeval by installing our SDK using pip:
+
+```bash
+pip install judgeval
+```
+
+Ensure you have your `JUDGMENT_API_KEY` and `JUDGMENT_ORG_ID` environment variables set to connect to the [Judgment Platform](https://app.judgmentlabs.ai/).
+
+```bash
+export JUDGMENT_API_KEY=...
+export JUDGMENT_ORG_ID=...
+```
+
+**If you don't have keys, [create an account for free](https://app.judgmentlabs.ai/register) on the platform!**
+
+### Start monitoring with Judgeval
+
+```python
+from judgeval.tracer import Tracer, wrap
+from judgeval.data import Example
+from judgeval.scorers import AnswerRelevancyScorer
+from openai import OpenAI
+
+
+judgment = Tracer(project_name="default_project")
+client = wrap(OpenAI())  # tracks all LLM calls
+
+@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-5-mini",
+        messages=[{"role": "user", "content": task}]
+    )
+
+    judgment.async_evaluate(  # trigger online monitoring
+        scorer=AnswerRelevancyScorer(threshold=0.5),  # swap with any scorer
+        example=Example(input=task, actual_output=response),  # customize to your data
+        model="gpt-5",
+    )
+    return response.choices[0].message.content
+
+run_agent("What is the capital of the United States?")
+```
+
+Running this code will deliver monitoring results to your [free platform account](https://app.judgmentlabs.ai/register) and should look like this:
+
+![Judgment Platform Trajectory View](assets/quickstart_trajectory_ss.png)
+
+
+### Customizable Scorers Over Agent Behavior
+
+Judgeval's strongest suit is the full customization over the types of scorers you can run online monitoring with. No restrictions to only single-prompt LLM judges or prefab scorers - if you can express your scorer
+in python code, judgeval can monitor it! Under the hood, judgeval hosts your scorer in a virtualized secure container, enabling online monitoring for any scorer.
+
+
+First, create a behavior scorer in a file called `helpfulness_scorer.py`:
+
+```python
+from judgeval.data import Example
+from judgeval.scorers.example_scorer import ExampleScorer
+
+# Define custom example class
+class QuestionAnswer(Example):
+    question: str
+    answer: str
+
+# Define a server-hosted custom scorer
+class HelpfulnessScorer(ExampleScorer):
+    name: str = "Helpfulness Scorer"
+    server_hosted: bool = True  # Enable server hosting
+    async def a_score_example(self, example: QuestionAnswer):
+        # Custom scoring logic for agent behavior
+        # Can be an arbitrary combination of code and LLM calls
+        if len(example.answer) > 10 and "?" not in example.answer:
+            self.reason = "Answer is detailed and provides helpful information"
+            return 1.0
+        else:
+            self.reason = "Answer is too brief or unclear"
+            return 0.0
+```
+
+Then deploy your scorer to Judgment's infrastructure:
+
+```bash
+echo "pydantic" > requirements.txt
+uv run judgeval upload_scorer helpfulness_scorer.py requirements.txt
+```
+
+Now you can instrument your agent with monitoring and online evaluation:
+
+```python
+from judgeval.tracer import Tracer, wrap
+from helpfulness_scorer import HelpfulnessScorer, QuestionAnswer
+from openai import OpenAI
+
+judgment = Tracer(project_name="default_project")
+client = wrap(OpenAI())  # tracks all LLM calls
+
+@judgment.observe(span_type="tool")
+def format_task(question: str) -> str:  # replace with your prompt engineering
+    return f"Please answer the following question: {question}"
+
+@judgment.observe(span_type="tool")
+def answer_question(prompt: str) -> str:  # replace with your LLM system calls
+    response = client.chat.completions.create(
+        model="gpt-5-mini",
+        messages=[{"role": "user", "content": prompt}]
+    )
+    return response.choices[0].message.content
+
+@judgment.observe(span_type="function")
+def run_agent(question: str) -> str:
+    task = format_task(question)
+    answer = answer_question(task)
+
+    # Add online evaluation with server-hosted scorer
+    judgment.async_evaluate(
+        scorer=HelpfulnessScorer(),
+        example=QuestionAnswer(question=question, answer=answer),
+        sampling_rate=0.9  # Evaluate 90% of agent runs
+    )
+
+    return answer
+
+if __name__ == "__main__":
+    result = run_agent("What is the capital of the United States?")
+    print(result)
+```
+
+Congratulations! Your online eval result should look like this:
+
+![Custom Scorer Online ABM](assets/custom_scorer_online_abm.png)
+
+You can now run any online scorer in a secure Firecracker microVMs with no latency impact on your applications.
+
+---
+
+Judgeval is created and maintained by [Judgment Labs](https://judgmentlabs.ai/).

judgeval-0.16.0/README.md

@@ -0,0 +1,239 @@
+<div align="center">
+
+<a href="https://judgmentlabs.ai/">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="assets/logo_darkmode.svg">
+    <img src="assets/logo_lightmode.svg" alt="Judgment Logo" width="400" />
+  </picture>
+</a>
+
+<br>
+
+## Agent Behavior Monitoring (ABM)
+
+Track and judge any agent behavior in online and offline setups. Set up Sentry-style alerts and analyze agent behaviors / topic patterns at scale! 
+
+[![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.judgmentlabs.ai/documentation)
+[![Judgment Cloud](https://img.shields.io/badge/Judgment%20Cloud-brightgreen)](https://app.judgmentlabs.ai/register)
+[![Self-Host](https://img.shields.io/badge/Self--Host-orange)](https://docs.judgmentlabs.ai/documentation/self-hosting/get-started)
+
+
+[![X](https://img.shields.io/badge/-X/Twitter-000?logo=x&logoColor=white)](https://x.com/JudgmentLabs)
+[![LinkedIn](https://custom-icon-badges.demolab.com/badge/LinkedIn%20-0A66C2?logo=linkedin-white&logoColor=fff)](https://www.linkedin.com/company/judgmentlabs)
+
+</div>
+
+
+</table>
+
+## [NEW] 🎆 Agent Reinforcement Learning
+
+Train your agents with multi-turn reinforcement learning using judgeval and [Fireworks AI](https://fireworks.ai/)! Judgeval's ABM now integrates with Fireworks' Reinforcement Fine-Tuning (RFT) endpoint, supporting gpt-oss, qwen3, Kimi2, DeepSeek, and more.
+
+Judgeval's agent monitoring infra provides a simple harness for integrating GRPO into any Python agent, giving builders a quick method to **try RL with minimal code changes** to their existing agents!
+
+```python
+await trainer.train(
+    agent_function=your_agent_function,  # entry point to your agent
+    scorers=[RewardScorer()],  # Custom scorer you define based on task criteria, acts as reward
+    prompts=training_prompts,  # Tasks
+    rft_provider="fireworks"
+)
+```
+
+**That's it!** Judgeval automatically manages trajectory collection and reward tagging - your agent can learn from production data with minimal code changes. 
+
+👉 Check out the [Wikipedia Racer notebook](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/rl/WikiRacingAgent_RL.ipynb), where an agent learns to navigate Wikipedia using RL, to see Judgeval in action.
+
+
+You can view and monitor training progress for free via the [Judgment Dashboard](https://app.judgmentlabs.ai/).
+
+
+## Judgeval Overview
+
+Judgeval is an open-source framework for agent behavior monitoring. Judgeval offers a toolkit to track and judge agent behavior in online and offline setups, enabling you to convert interaction data from production/test environments into improved agents. To get started, try running one of the notebooks below or dive deeper in our [docs](https://docs.judgmentlabs.ai/documentation).
+
+Our mission is to unlock the power of production data for agent development, enabling teams to improve their apps by catching real-time failures and optimizing over their users' preferences.
+
+## 📚 Cookbooks
+
+| Try Out | Notebook | Description |
+|:---------|:-----|:------------|
+| RL | [Wikipedia Racer](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/rl/WikiRacingAgent_RL.ipynb) | Train agents with reinforcement learning |
+| Online ABM | [Research Agent](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/monitoring/Research_Agent_Online_Monitoring.ipynb) | Monitor agent behavior in production |
+| Custom Scorers | [HumanEval](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/custom_scorers/HumanEval_Custom_Scorer.ipynb) | Build custom evaluators for your agents |
+| Offline Testing | [Get Started For Free] | Compare how different prompts, models, or agent configs affect performance across ANY metric |
+
+You can access our [repo of cookbooks](https://github.com/JudgmentLabs/judgment-cookbook).
+
+You can find a list of [video tutorials for Judgeval use cases](https://www.youtube.com/@Alexshander-JL).
+
+## Why Judgeval?
+
+🤖 **Simple to run multi-turn RL**: Optimize your agents with multi-turn RL without managing compute infrastructure or data pipelines. Just add a few lines of code to your existing agent code and train!
+
+⚙️ **Custom Evaluators**: No restriction to only monitoring with prefab scorers. Judgeval provides simple abstractions for custom Python scorers, supporting any LLM-as-a-judge rubrics/models and code-based scorers that integrate to our live agent-tracking infrastructure. [Learn more](https://docs.judgmentlabs.ai/documentation/evaluation/custom-scorers)
+
+🚨 **Production Monitoring**: Run any custom scorer in a hosted, virtualized secure container to flag agent behaviors online in production. Get Slack alerts for failures and add custom hooks to address regressions before they impact users. [Learn more](https://docs.judgmentlabs.ai/documentation/performance/online-evals)
+
+📊 **Behavior/Topic Grouping**: Group agent runs by behavior type or topic for deeper analysis. Drill down into subsets of users, agents, or use cases to reveal patterns of agent behavior.
+<!-- Add link to Bucketing docs once we have it -->
+<!-- 
+TODO: Once we have trainer code docs, plug in here
+-->
+
+🧪 **Run experiments on your agents**: Compare test different prompts, models, or agent configs across customer segments. Measure which changes improve agent performance and decrease bad agent behaviors.
+
+<!-- 
+Use this once we have AI PM features:
+
+**Run experiments on your agents**: A/B test different prompts, models, or agent configs across customer segments. Measure which changes improve agent performance and decrease bad agent behaviors. [Learn more]
+
+-->
+
+## 🛠️ Quickstart
+
+Get started with Judgeval by installing our SDK using pip:
+
+```bash
+pip install judgeval
+```
+
+Ensure you have your `JUDGMENT_API_KEY` and `JUDGMENT_ORG_ID` environment variables set to connect to the [Judgment Platform](https://app.judgmentlabs.ai/).
+
+```bash
+export JUDGMENT_API_KEY=...
+export JUDGMENT_ORG_ID=...
+```
+
+**If you don't have keys, [create an account for free](https://app.judgmentlabs.ai/register) on the platform!**
+
+### Start monitoring with Judgeval
+
+```python
+from judgeval.tracer import Tracer, wrap
+from judgeval.data import Example
+from judgeval.scorers import AnswerRelevancyScorer
+from openai import OpenAI
+
+
+judgment = Tracer(project_name="default_project")
+client = wrap(OpenAI())  # tracks all LLM calls
+
+@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-5-mini",
+        messages=[{"role": "user", "content": task}]
+    )
+
+    judgment.async_evaluate(  # trigger online monitoring
+        scorer=AnswerRelevancyScorer(threshold=0.5),  # swap with any scorer
+        example=Example(input=task, actual_output=response),  # customize to your data
+        model="gpt-5",
+    )
+    return response.choices[0].message.content
+
+run_agent("What is the capital of the United States?")
+```
+
+Running this code will deliver monitoring results to your [free platform account](https://app.judgmentlabs.ai/register) and should look like this:
+
+![Judgment Platform Trajectory View](assets/quickstart_trajectory_ss.png)
+
+
+### Customizable Scorers Over Agent Behavior
+
+Judgeval's strongest suit is the full customization over the types of scorers you can run online monitoring with. No restrictions to only single-prompt LLM judges or prefab scorers - if you can express your scorer
+in python code, judgeval can monitor it! Under the hood, judgeval hosts your scorer in a virtualized secure container, enabling online monitoring for any scorer.
+
+
+First, create a behavior scorer in a file called `helpfulness_scorer.py`:
+
+```python
+from judgeval.data import Example
+from judgeval.scorers.example_scorer import ExampleScorer
+
+# Define custom example class
+class QuestionAnswer(Example):
+    question: str
+    answer: str
+
+# Define a server-hosted custom scorer
+class HelpfulnessScorer(ExampleScorer):
+    name: str = "Helpfulness Scorer"
+    server_hosted: bool = True  # Enable server hosting
+    async def a_score_example(self, example: QuestionAnswer):
+        # Custom scoring logic for agent behavior
+        # Can be an arbitrary combination of code and LLM calls
+        if len(example.answer) > 10 and "?" not in example.answer:
+            self.reason = "Answer is detailed and provides helpful information"
+            return 1.0
+        else:
+            self.reason = "Answer is too brief or unclear"
+            return 0.0
+```
+
+Then deploy your scorer to Judgment's infrastructure:
+
+```bash
+echo "pydantic" > requirements.txt
+uv run judgeval upload_scorer helpfulness_scorer.py requirements.txt
+```
+
+Now you can instrument your agent with monitoring and online evaluation:
+
+```python
+from judgeval.tracer import Tracer, wrap
+from helpfulness_scorer import HelpfulnessScorer, QuestionAnswer
+from openai import OpenAI
+
+judgment = Tracer(project_name="default_project")
+client = wrap(OpenAI())  # tracks all LLM calls
+
+@judgment.observe(span_type="tool")
+def format_task(question: str) -> str:  # replace with your prompt engineering
+    return f"Please answer the following question: {question}"
+
+@judgment.observe(span_type="tool")
+def answer_question(prompt: str) -> str:  # replace with your LLM system calls
+    response = client.chat.completions.create(
+        model="gpt-5-mini",
+        messages=[{"role": "user", "content": prompt}]
+    )
+    return response.choices[0].message.content
+
+@judgment.observe(span_type="function")
+def run_agent(question: str) -> str:
+    task = format_task(question)
+    answer = answer_question(task)
+
+    # Add online evaluation with server-hosted scorer
+    judgment.async_evaluate(
+        scorer=HelpfulnessScorer(),
+        example=QuestionAnswer(question=question, answer=answer),
+        sampling_rate=0.9  # Evaluate 90% of agent runs
+    )
+
+    return answer
+
+if __name__ == "__main__":
+    result = run_agent("What is the capital of the United States?")
+    print(result)
+```
+
+Congratulations! Your online eval result should look like this:
+
+![Custom Scorer Online ABM](assets/custom_scorer_online_abm.png)
+
+You can now run any online scorer in a secure Firecracker microVMs with no latency impact on your applications.
+
+---
+
+Judgeval is created and maintained by [Judgment Labs](https://judgmentlabs.ai/).

judgeval-0.16.0/assets/logo_darkmode.svg

@@ -0,0 +1,7 @@
+<svg width="544" height="91" viewBox="0 0 544 91" fill="none" xmlns="http://www.w3.org/2000/svg">
+<path d="M31.2246 18H39.5512V51.3061L31.2246 59.6327V18Z" fill="#FF4B2E"/>
+<path d="M0 59.6328H31.2245L21.8571 69.0002H0V59.6328Z" fill="#FF4B2E"/>
+<path d="M52.041 18H43.7145V51.3061L52.041 59.6327V18Z" fill="#FF4B2E"/>
+<path d="M83.2656 59.6328H52.0411L62.4493 69.0002H83.2656V59.6328Z" fill="#FF4B2E"/>
+<path d="M111.45 61.3V54.37H116.63V59.55L121.39 64.24H133.36L137.35 60.32V20H142.67V62L135.67 69H119.15L111.45 61.3ZM147.896 62.56V34.14H153.076V60.95L156.576 64.38H163.576L172.256 55.7V34.14H177.436V69H172.396V61.58L164.976 69H154.336L147.896 62.56ZM182.363 62.56V40.58L188.803 34.14H202.243L207.983 39.18V19.02H213.163V69H208.123V62.63L201.753 69H188.803L182.363 62.56ZM200.633 64.38L207.983 57.03V44.64L201.263 38.76H191.043L187.543 42.19V60.95L191.043 64.38H200.633ZM248.869 34.14V77.89L242.499 84.26H225.209L219.819 78.87V74.6H224.999V77.19L227.449 79.64H240.189L243.689 76.21V63.19L237.249 69H224.509L218.069 62.56V40.58L224.509 34.14H237.739L243.829 40.23V34.14H248.869ZM243.689 46.11L236.339 38.76H226.749L223.249 42.19V60.95L226.749 64.38H236.409L243.689 57.59V46.11ZM254.474 34.14H259.514V40.86L266.234 34.14H274.564L280.024 39.6L285.484 34.14H296.474L302.914 40.58V69H297.734V42.19L294.234 38.76H286.534L281.634 43.66V69H276.594V42.19L273.094 38.76H267.214L259.654 46.32V69H254.474V34.14ZM307.458 62.56V40.58L313.898 34.14H331.468L337.978 40.58V53.11H312.638V60.95L316.138 64.38H329.228L332.728 60.95V58.29H337.908V62.56L331.468 69H313.898L307.458 62.56ZM332.798 48.63V42.19L329.298 38.76H316.138L312.638 42.19V48.63H332.798ZM342.496 34.14H347.536V41.56L354.956 34.14H365.666L372.106 40.58V69H366.926V42.19L363.426 38.76H356.356L347.676 47.44V69H342.496V34.14ZM379.848 62.56V38.69H373.548V34.14H379.988V22.8H385.028V34.14H395.948V38.69H385.028V60.95L388.528 64.45H395.948V69H386.288L379.848 62.56ZM411.613 20H416.933V64.31H441.853V69H411.613V20ZM442.227 63.26V54.37L447.967 48.7H466.587V42.05L463.087 38.62H451.187L447.687 42.05V44.92H442.507V40.58L448.947 34.14H465.257L471.697 40.58V69H466.727V62.84L460.287 69H447.967L442.227 63.26ZM459.237 64.52L466.587 57.45V53.18H450.207L447.407 55.91V61.79L450.207 64.52H459.237ZM476.932 62.56V19.02H482.112V40.93L488.902 34.14H501.152L507.592 40.58V62.56L501.152 69H483.372L476.932 62.56ZM498.912 64.38L502.412 60.95V42.19L498.912 38.76H490.372L482.112 47.02V60.95L485.612 64.38H498.912ZM510.751 63.26V58.92H515.931V61.79L518.731 64.52H531.611L534.411 61.79V56.4L531.611 53.6H516.561L511.031 48.07V39.88L516.771 34.14H533.151L538.891 39.88V44.22H533.711V41.35L530.911 38.62H519.011L516.211 41.35V46.46L519.011 49.26H533.851L539.591 55V63.26L533.851 69H516.491L510.751 63.26Z" fill="#F4F4F5"/>
+</svg>

judgeval-0.16.0/assets/logo_lightmode.svg

@@ -0,0 +1,7 @@
+<svg width="544" height="91" viewBox="0 0 544 91" fill="none" xmlns="http://www.w3.org/2000/svg">
+<path d="M31.2246 18H39.5512V51.3061L31.2246 59.6327V18Z" fill="#FF4B2E"/>
+<path d="M0 59.6328H31.2245L21.8571 69.0002H0V59.6328Z" fill="#FF4B2E"/>
+<path d="M52.041 18H43.7145V51.3061L52.041 59.6327V18Z" fill="#FF4B2E"/>
+<path d="M83.2656 59.6328H52.0411L62.4493 69.0002H83.2656V59.6328Z" fill="#FF4B2E"/>
+<path d="M111.45 61.3V54.37H116.63V59.55L121.39 64.24H133.36L137.35 60.32V20H142.67V62L135.67 69H119.15L111.45 61.3ZM147.896 62.56V34.14H153.076V60.95L156.576 64.38H163.576L172.256 55.7V34.14H177.436V69H172.396V61.58L164.976 69H154.336L147.896 62.56ZM182.363 62.56V40.58L188.803 34.14H202.243L207.983 39.18V19.02H213.163V69H208.123V62.63L201.753 69H188.803L182.363 62.56ZM200.633 64.38L207.983 57.03V44.64L201.263 38.76H191.043L187.543 42.19V60.95L191.043 64.38H200.633ZM248.869 34.14V77.89L242.499 84.26H225.209L219.819 78.87V74.6H224.999V77.19L227.449 79.64H240.189L243.689 76.21V63.19L237.249 69H224.509L218.069 62.56V40.58L224.509 34.14H237.739L243.829 40.23V34.14H248.869ZM243.689 46.11L236.339 38.76H226.749L223.249 42.19V60.95L226.749 64.38H236.409L243.689 57.59V46.11ZM254.474 34.14H259.514V40.86L266.234 34.14H274.564L280.024 39.6L285.484 34.14H296.474L302.914 40.58V69H297.734V42.19L294.234 38.76H286.534L281.634 43.66V69H276.594V42.19L273.094 38.76H267.214L259.654 46.32V69H254.474V34.14ZM307.458 62.56V40.58L313.898 34.14H331.468L337.978 40.58V53.11H312.638V60.95L316.138 64.38H329.228L332.728 60.95V58.29H337.908V62.56L331.468 69H313.898L307.458 62.56ZM332.798 48.63V42.19L329.298 38.76H316.138L312.638 42.19V48.63H332.798ZM342.496 34.14H347.536V41.56L354.956 34.14H365.666L372.106 40.58V69H366.926V42.19L363.426 38.76H356.356L347.676 47.44V69H342.496V34.14ZM379.848 62.56V38.69H373.548V34.14H379.988V22.8H385.028V34.14H395.948V38.69H385.028V60.95L388.528 64.45H395.948V69H386.288L379.848 62.56ZM411.613 20H416.933V64.31H441.853V69H411.613V20ZM442.227 63.26V54.37L447.967 48.7H466.587V42.05L463.087 38.62H451.187L447.687 42.05V44.92H442.507V40.58L448.947 34.14H465.257L471.697 40.58V69H466.727V62.84L460.287 69H447.967L442.227 63.26ZM459.237 64.52L466.587 57.45V53.18H450.207L447.407 55.91V61.79L450.207 64.52H459.237ZM476.932 62.56V19.02H482.112V40.93L488.902 34.14H501.152L507.592 40.58V62.56L501.152 69H483.372L476.932 62.56ZM498.912 64.38L502.412 60.95V42.19L498.912 38.76H490.372L482.112 47.02V60.95L485.612 64.38H498.912ZM510.751 63.26V58.92H515.931V61.79L518.731 64.52H531.611L534.411 61.79V56.4L531.611 53.6H516.561L511.031 48.07V39.88L516.771 34.14H533.151L538.891 39.88V44.22H533.711V41.35L530.911 38.62H519.011L516.211 41.35V46.46L519.011 49.26H533.851L539.591 55V63.26L533.851 69H516.491L510.751 63.26Z" fill="black"/>
+</svg>

{judgeval-0.14.1 → judgeval-0.16.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "judgeval"
-version = "0.14.1"
+version = "0.16.0"
 authors = [
     { name = "Andrew Li", email = "andrew@judgmentlabs.ai" },
     { name = "Alex Shan", email = "alex@judgmentlabs.ai" },
@@ -58,7 +58,7 @@ dev = [
     "langchain-core>=0.3.72",
     "langgraph>=0.6.4",
     "mypy>=1.17.1",
-    "openai>=1.78.1",
+    "openai>=1.92.0",
     "opentelemetry-instrumentation-openai>=0.44.1",
     "ruff>=0.9.1,<0.10.0",
     "together>=1.5.21",
@@ -73,6 +73,7 @@ dev = [
     "langchain-tavily>=0.2.11",
     "streamlit>=1.49.1",
     "langchain-community>=0.3.29",
+    "openlit>=1.35.5",
 ]
 
 

{judgeval-0.14.1 → judgeval-0.16.0}/scripts/api_generator.py

@@ -31,7 +31,6 @@ JUDGEVAL_PATHS: List[str] = [
     "/fetch_experiment_run/",
     "/add_to_run_eval_queue/examples",
     "/add_to_run_eval_queue/traces",
-    "/get_evaluation_status/",
     "/save_scorer/",
     "/fetch_scorers/",
     "/scorer_exists/",

{judgeval-0.14.1 → judgeval-0.16.0}/scripts/openapi_transform.py

@@ -30,7 +30,6 @@ JUDGEVAL_PATHS: List[str] = [
     "/fetch_experiment_run/",
     "/add_to_run_eval_queue/examples",
     "/add_to_run_eval_queue/traces",
-    "/get_evaluation_status/",
     "/save_scorer/",
     "/fetch_scorers/",
     "/scorer_exists/",