judgeval 0.0.41__py3-none-any.whl → 0.0.43__py3-none-any.whl

judgeval/run_evaluation.py

@@ -100,9 +100,9 @@ def execute_api_eval(evaluation_run: EvaluationRun) -> List[Dict]:
         raise JudgmentAPIError(error_message)
     return response_data
 
-def execute_api_trace_eval(trace_run: TraceRun) -> List[Dict]:
+def execute_api_trace_eval(trace_run: TraceRun) -> Dict:
     """
-    Executes an evaluation of a list of `Example`s using one or more `JudgmentScorer`s via the Judgment API.
+    Executes an evaluation of a list of `Trace`s using one or more `JudgmentScorer`s via the Judgment API.
     """
         
     try:
@@ -146,46 +146,47 @@ def merge_results(api_results: List[ScoringResult], local_results: List[ScoringR
     """
     # No merge required
     if not local_results and api_results:
-        return api_results
+        return [result.model_copy() for result in api_results]
     if not api_results and local_results:
-        return local_results
+        return [result.model_copy() for result in local_results]
 
     if len(api_results) != len(local_results):
         # Results should be of same length because each ScoringResult is a 1-1 mapping to an Example
         raise ValueError(f"The number of API and local results do not match: {len(api_results)} vs {len(local_results)}")
     
+    # Create a copy of api_results to avoid modifying the input
+    merged_results = [result.model_copy() for result in api_results]
+    
     # Each ScoringResult in api and local have all the same fields besides `scorers_data`
-    for api_result, local_result in zip(api_results, local_results):
-        if not (api_result.data_object and local_result.data_object):
+    for merged_result, local_result in zip(merged_results, local_results):
+        if not (merged_result.data_object and local_result.data_object):
             raise ValueError("Data object is None in one of the results.")
-        if api_result.data_object.input != local_result.data_object.input:
+        if merged_result.data_object.input != local_result.data_object.input:
             raise ValueError("The API and local results are not aligned.")
-        if api_result.data_object.actual_output != local_result.data_object.actual_output:
+        if merged_result.data_object.actual_output != local_result.data_object.actual_output:
             raise ValueError("The API and local results are not aligned.")
-        if api_result.data_object.expected_output != local_result.data_object.expected_output:
+        if merged_result.data_object.expected_output != local_result.data_object.expected_output:
             raise ValueError("The API and local results are not aligned.")
-        if api_result.data_object.context != local_result.data_object.context:
+        if merged_result.data_object.context != local_result.data_object.context:
             raise ValueError("The API and local results are not aligned.")
-        if api_result.data_object.retrieval_context != local_result.data_object.retrieval_context:
+        if merged_result.data_object.retrieval_context != local_result.data_object.retrieval_context:
             raise ValueError("The API and local results are not aligned.")
-        if api_result.data_object.additional_metadata != local_result.data_object.additional_metadata:
+        if merged_result.data_object.additional_metadata != local_result.data_object.additional_metadata:
             raise ValueError("The API and local results are not aligned.")
-        if api_result.data_object.tools_called != local_result.data_object.tools_called:
+        if merged_result.data_object.tools_called != local_result.data_object.tools_called:
             raise ValueError("The API and local results are not aligned.")
-        if api_result.data_object.expected_tools != local_result.data_object.expected_tools:
+        if merged_result.data_object.expected_tools != local_result.data_object.expected_tools:
             raise ValueError("The API and local results are not aligned.")
         
-        
         # Merge ScorerData from the API and local scorers together
-        api_scorer_data = api_result.scorers_data
+        api_scorer_data = merged_result.scorers_data
         local_scorer_data = local_result.scorers_data
         if api_scorer_data is None and local_scorer_data is not None:
-            api_result.scorers_data = local_scorer_data
-
-        if api_scorer_data is not None and local_scorer_data is not None:
-            api_result.scorers_data = api_scorer_data + local_scorer_data
+            merged_result.scorers_data = local_scorer_data
+        elif api_scorer_data is not None and local_scorer_data is not None:
+            merged_result.scorers_data = api_scorer_data + local_scorer_data
     
-    return api_results
+    return merged_results
 
 
 def check_missing_scorer_data(results: List[ScoringResult]) -> List[ScoringResult]:
@@ -405,8 +406,15 @@ def run_trace_eval(trace_run: TraceRun, override: bool = False, ignore_errors: b
         )
     if function and tracer:
         new_traces: List[Trace] = []
-        tracer.offline_mode = True
-        tracer.traces = []
+        
+        # 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
+        
+        actual_tracer.offline_mode = True
+        actual_tracer.traces = []
         for example in examples:
             if example.input:
                 if isinstance(example.input, str):
@@ -417,19 +425,21 @@ def run_trace_eval(trace_run: TraceRun, override: bool = False, ignore_errors: b
                     raise ValueError(f"Input must be string or dict, got {type(example.input)}")
             else:
                 result = run_with_spinner("Running agent function: ", function)
-        for i, trace in enumerate(tracer.traces):
+        
+        
+        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
-        tracer.traces = []
+        actual_tracer.traces = []
         
     # Execute evaluation using Judgment API
     info("Starting API evaluation")
     try:  # execute an EvaluationRun with just JudgmentScorers
         debug("Sending request to Judgment API")    
-        response_data: List[Dict] = run_with_spinner("Running Trace Evaluation: ", execute_api_trace_eval, trace_run)
+        response_data: Dict = run_with_spinner("Running Trace Evaluation: ", execute_api_trace_eval, trace_run)
         scoring_results = [ScoringResult(**result) for result in response_data["results"]]
         info(f"Received {len(scoring_results)} results from API")
     except JudgmentAPIError as e:

judgeval/utils/alerts.py

@@ -20,12 +20,20 @@ class AlertResult(BaseModel):
         status: Status of the alert (triggered or not)
         conditions_result: List of condition evaluation results
         metadata: Dictionary containing example_id, timestamp, and other metadata
+        notification: Optional notification configuration for triggered alerts
+        combine_type: The combination type used ("all" or "any")
+        project_id: Optional project identifier
+        trace_span_id: Optional trace span identifier
     """
     rule_name: str
     rule_id: Optional[str] = None  # The unique identifier of the rule
     status: AlertStatus
     conditions_result: List[Dict[str, Any]] = []
     metadata: Dict[str, Any] = {}
+    notification: Optional[Any] = None  # NotificationConfig when triggered, None otherwise
+    combine_type: Optional[str] = None  # "all" or "any"
+    project_id: Optional[str] = None  # Project identifier
+    trace_span_id: Optional[str] = None  # Trace span identifier
     
     @property
     def example_id(self) -> Optional[str]:

{judgeval-0.0.41.dist-info → judgeval-0.0.43.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: judgeval
-Version: 0.0.41
+Version: 0.0.43
 Summary: Judgeval Package
 Project-URL: Homepage, https://github.com/JudgmentLabs/judgeval
 Project-URL: Issues, https://github.com/JudgmentLabs/judgeval/issues
@@ -18,6 +18,7 @@ Requires-Dist: langchain-core
 Requires-Dist: langchain-huggingface
 Requires-Dist: langchain-openai
 Requires-Dist: litellm==1.61.15
+Requires-Dist: matplotlib>=3.10.3
 Requires-Dist: nest-asyncio
 Requires-Dist: openai
 Requires-Dist: pandas
@@ -31,37 +32,37 @@ Description-Content-Type: text/markdown
 <img src="assets/new_lightmode.svg#gh-light-mode-only" alt="Judgment Logo" width="400" />
 <img src="assets/new_darkmode.svg#gh-dark-mode-only" alt="Judgment Logo" width="400" />
 
-**Build monitoring & evaluation pipelines for complex agents**
+<br>
+<div style="font-size: 1.5em;">
+  Open source tracing, evals, and metrics to debug, test, and monitor LLM agents.
+</div>
 
-<img src="assets/experiments_pagev2.png" alt="Judgment Platform Experiments Page" width="800" />
+## [Judgment Cloud](https://app.judgmentlabs.ai/register)  • [Self-Host](https://docs.judgmentlabs.ai/self-hosting/get_started) • [Demo](https://www.youtube.com/watch?v=1S4LixpVbcc) 
 
-<br>
+[Docs](https://docs.judgmentlabs.ai/introduction) • [Bug Reports](https://github.com/JudgmentLabs/judgeval/issues) • [Changelog](https://docs.judgmentlabs.ai/changelog/2025-04-21)
 
-## [🌐 Landing Page](https://www.judgmentlabs.ai/)  • [📚 Docs](https://docs.judgmentlabs.ai/introduction) • [🚀 Demos](https://www.youtube.com/@AlexShan-j3o) 
+We're hiring! Join us in our mission to unleash optimized agents.
 
 [![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)
 [![Discord](https://img.shields.io/badge/-Discord-5865F2?logo=discord&logoColor=white)](https://discord.gg/ZCnSXYug)
 
-</div>
+<img src="assets/experiments_pagev2.png" alt="Judgment Platform Experiments Page" width="800" />
 
-## Judgeval: open-source testing, monitoring, and optimization for AI agents
+</div>
 
-Judgeval offers robust tooling for evaluating and tracing LLM agent systems. It is dev-friendly and open-source (licensed under Apache 2.0). 
 
-Judgeval gets you started in five minutes, after which you'll be ready to use all of its features as your agent becomes more complex. Judgeval is natively connected to the [Judgment Platform](https://www.judgmentlabs.ai/) for free and you can export your data and self-host at any time.
+Judgeval offers **robust open-source tooling** for tracing, evaluating, and monitoring LLM agents. It helps AI teams effectively **test and monitor** agents in development and production, **closing the agent feedback loop**. 
 
-We support tracing agents built with LangGraph, OpenAI SDK, Anthropic, ... and allow custom eval integrations for any use case. Check out our quickstarts below or our [setup guide](https://docs.judgmentlabs.ai/getting-started) to get started.
+Judgeval can be set up **(cloud-hosted or self-hosted) in 5 minutes**!
+> 🎁 Generous monthly [free tier](https://judgmentlabs.ai/pricing) (10k traces, 1k evals) - No credit card required!
 
 Judgeval is created and maintained by [Judgment Labs](https://judgmentlabs.ai/).
 
 ## 📋 Table of Contents
-- [🌐 Landing Page  • 📚 Docs • 🚀 Demos](#-landing-page----docs---demos)
-- [Judgeval: open-source testing, monitoring, and optimization for AI agents](#judgeval-open-source-testing-monitoring-and-optimization-for-ai-agents)
-- [📋 Table of Contents](#-table-of-contents)
 - [✨ Features](#-features)
 - [🛠️ Installation](#️-installation)
-- [🏁 Get Started](#-get-started)
+- [🏁 Quickstarts](#-quickstarts)
   - [🛰️ Tracing](#️-tracing)
   - [📝 Offline Evaluations](#-offline-evaluations)
   - [📡 Online Evaluations](#-online-evaluations)
@@ -69,12 +70,6 @@ Judgeval is created and maintained by [Judgment Labs](https://judgmentlabs.ai/).
   - [Key Features](#key-features)
   - [Getting Started](#getting-started)
 - [📚 Cookbooks](#-cookbooks)
-  - [Sample Agents](#sample-agents)
-    - [💰 LangGraph Financial QA Agent](#-langgraph-financial-qa-agent)
-    - [✈️ OpenAI Travel Agent](#️-openai-travel-agent)
-  - [Custom Evaluators](#custom-evaluators)
-    - [🔍 PII Detection](#-pii-detection)
-    - [📧 Cold Email Generation](#-cold-email-generation)
 - [💻 Development with Cursor](#-development-with-cursor)
 - [⭐ Star Us on GitHub](#-star-us-on-github)
 - [❤️ Contributors](#️-contributors)
@@ -86,11 +81,10 @@ Judgeval is created and maintained by [Judgment Labs](https://judgmentlabs.ai/).
 
 |  |  |
 |:---|:---:|
-| <h3>🔍 Tracing</h3>Automatic agent tracing integrated with common frameworks (LangGraph, OpenAI, Anthropic): **tracking inputs/outputs, latency, and cost** at every step.<br><br>Online evals can be applied to traces to measure quality on production data in real-time.<br><br>Export trace data to the Judgment Platform or your own S3 buckets, {Parquet, JSON, YAML} files, or data warehouse.<br><br>**Useful for:**<br>• 🐛 Debugging agent runs <br>• 👤 Tracking user activity <br>• 🔬 Pinpointing performance bottlenecks| <p align="center"><img src="assets/trace_screenshot.png" alt="Tracing visualization" width="1200"/></p> |
-| <h3>🧪 Evals</h3>15+ research-backed metrics including tool call accuracy, hallucinations, instruction adherence, and retrieval context recall.<br><br>Build custom evaluators that connect with our metric-tracking infrastructure. <br><br>**Useful for:**<br>• ⚠️ Unit-testing <br>• 🔬 Experimental prompt testing<br>• 🛡️ Online guardrails <br><br> | <p align="center"><img src="assets/experiments_page.png" alt="Evaluation metrics" width="800"/></p> |
-| <h3>📡 Monitoring</h3>Real-time performance tracking of your agents in production environments. **Track all your metrics in one place.**<br><br>Set up **Slack/email alerts** for critical metrics and receive notifications when thresholds are exceeded.<br><br> **Useful for:** <br>•📉 Identifying degradation early <br>•📈 Visualizing performance trends across versions and time | <p align="center"><img src="assets/monitoring_screenshot.png" alt="Monitoring Dashboard" width="1200"/></p> |
-| <h3>📊 Datasets</h3>Export trace data or import external testcases to datasets hosted on Judgment's Platform. Move datasets to/from Parquet, S3, etc. <br><br>Run evals on datasets as unit tests or to A/B test different agent configurations. <br><br> **Useful for:**<br>• 🔄 Scaled analysis for A/B tests <br>• 🗃️ Filtered collections of agent runtime data| <p align="center"><img src="assets/datasets_preview_screenshot.png" alt="Dataset management" width="1200"/></p> |
-| <h3>💡 Insights</h3>Cluster on your data to reveal common use cases and failure modes.<br><br>Trace failures to their exact source with Judgment's Osiris agent, which localizes errors to specific components for precise fixes.<br><br> **Useful for:**<br>•🔮 Surfacing common inputs that lead to error<br>•🤖 Investigating agent/user behavior for optimization <br>| <p align="center"><img src="assets/dataset_clustering_screenshot_dm.png" alt="Insights dashboard" width="1200"/></p> |
+| <h3>🔍 Tracing</h3>Automatic agent tracing integrated with common frameworks (LangGraph, OpenAI, Anthropic): **tracking inputs/outputs, agent tool calls, latency, and cost** at every step.<br><br>Online evals can be applied to traces to measure quality on production data in real-time.<br><br>Export trace data to the Judgment Platform or your own S3 buckets, {Parquet, JSON, YAML} files, or data warehouse.<br><br>**Useful for:**<br>• 🐛 Debugging agent runs <br>• 👤 Tracking user activity <br>• 🔬 Pinpointing performance bottlenecks| <p align="center"><img src="assets/trace_screenshot.png" alt="Tracing visualization" width="1200"/></p> |
+| <h3>🧪 Evals</h3>Evals are the key to regression testing for agents. Judgeval provides 15+ research-backed metrics including tool call accuracy, hallucinations, instruction adherence, and retrieval context recall.<br><br>Judgeval supports LLM-as-a-judge, manual labeling, and custom evaluators that connect with our metric-tracking infrastructure. <br><br>**Useful for:**<br>• ⚠️ Unit-testing <br>• 🔬 Experimental prompt testing<br>• 🛡️ Online guardrails | <p align="center"><img src="assets/experiments_page.png" alt="Evaluation metrics" width="800"/></p> |
+| <h3>📡 Monitoring</h3>Track all your agent metrics in production. **Catch production regressions early.**<br><br>Configure alerts to trigger automated actions when metric thresholds are exceeded (add agent trace to review queue/dataset, Slack notification, etc.).<br><br> **Useful for:** <br>• 📉 Identifying degradation early <br>• 📈 Visualizing performance trends across agent versions and time | <p align="center"><img src="assets/monitoring_screenshot.png" alt="Monitoring Dashboard" width="1200"/></p> |
+| <h3>📊 Datasets</h3>Export trace data or import external testcases to datasets for scaled unit testing and structured experiments. Move datasets to/from Parquet, S3, etc. <br><br>Run evals on datasets as unit tests or to A/B test different agent configurations. <br><br> **Useful for:**<br>• 🗃️ Filtered agent runtime data for fine tuning<br>• 🔄 Scaled analysis for A/B tests | <p align="center"><img src="assets/datasets_preview_screenshot.png" alt="Dataset management" width="1200"/></p> |
 
 ## 🛠️ Installation
 
@@ -100,17 +94,19 @@ Get started with Judgeval by installing our SDK using pip:
 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/). 
+Ensure you have your `JUDGMENT_API_KEY` and `JUDGMENT_ORG_ID` environment variables set to connect to the [Judgment platform](https://app.judgmentlabs.ai/).
 
-**If you don't have keys, [create an account](https://app.judgmentlabs.ai/register) on the platform!**
+```bash
+export JUDGMENT_API_KEY=...
+export JUDGMENT_ORG_ID=...
+```
 
-## 🏁 Get Started
+**If you don't have keys, [create an account](https://app.judgmentlabs.ai/register) on the platform!**
 
-Here's how you can quickly start using Judgeval:
+## 🏁 Quickstarts
 
 ### 🛰️ Tracing
 
-Track your agent execution with full observability with just a few lines of code.
 Create a file named `traces.py` with the following code:
 
 ```python
@@ -135,12 +131,15 @@ def main():
 
 main()
 ```
+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>
+
 
 [Click here](https://docs.judgmentlabs.ai/getting-started#create-your-first-trace) for a more detailed explanation.
 
 ### 📝 Offline Evaluations
 
-You can evaluate your agent's execution to measure quality metrics such as hallucination.
 Create a file named `evaluate.py` with the following code:
 
 ```python evaluate.py
@@ -156,7 +155,7 @@ example = Example(
     retrieval_context=["All customers are eligible for a 30 day full refund at no extra cost."],
 )
 
-scorer = FaithfulnessScorer(threshold=0.5)
+scorer = FaithfulnessScorer(threshold=0.5)  # Hallucination detector
 results = client.run_evaluation(
     examples=[example],
     scorers=[scorer],
@@ -205,6 +204,8 @@ def main():
 main()
 ```
 
+You should see an evaluation attached to your trace on the Judgment Platform.
+
 [Click here](https://docs.judgmentlabs.ai/getting-started#create-your-first-online-evaluation) for a more detailed explanation.
 
 ## 🏢 Self-Hosting
@@ -229,20 +230,8 @@ You can access our repo of cookbooks [here](https://github.com/JudgmentLabs/judg
 
 ### Sample Agents
 
-#### 💰 [LangGraph Financial QA Agent](https://github.com/JudgmentLabs/judgment-cookbook/blob/main/cookbooks/financial_agent/demo.py)
-A LangGraph-based agent for financial queries, featuring RAG capabilities with a vector database for contextual data retrieval and evaluation of its reasoning and data accuracy.
-
-#### ✈️ [OpenAI Travel Agent](https://github.com/JudgmentLabs/judgment-cookbook/blob/main/cookbooks/openai_travel_agent/agent.py)
-A travel planning agent using OpenAI API calls, custom tool functions, and RAG with a vector database for up-to-date and contextual travel information. Evaluated for itinerary quality and information relevance.
-
-### Custom Evaluators
-
-#### 🔍 [PII Detection](https://github.com/JudgmentLabs/judgment-cookbook/blob/main/cookbooks/classifier_scorer/pii_checker.py)
-Detecting and evaluating Personal Identifiable Information (PII) leakage.
-
-#### 📧 [Cold Email Generation](https://github.com/JudgmentLabs/judgment-cookbook/blob/main/cookbooks/custom_scorers/cold_email_scorer.py)
-
-Evaluates if a cold email generator properly utilizes all relevant information about the target recipient.
+#### [Multi-Agent System](https://github.com/JudgmentLabs/judgment-cookbook/tree/main/cookbooks/agents/multi-agent)
+A multi-agent system augmented with tool calls designed for general purpose tasks like financial research and math. Traced and evaluated on Faithfulness (factual adherence to retrieval context).
 
 ## 💻 Development with Cursor
 When building agents and LLM workflows in Cursor, providing proper context to your coding assistant helps ensure seamless integration with Judgment. This rule file supplies the essential context your coding assistant needs for successful implementation.

{judgeval-0.0.41.dist-info → judgeval-0.0.43.dist-info}/RECORD

@@ -1,29 +1,29 @@
 judgeval/__init__.py,sha256=x9HWt4waJwJMAqTuJSg2MezF9Zg-macEjeU-ajbly-8,330
 judgeval/clients.py,sha256=EiTmvvWksTPyWIuMC9jz06SPY2vFzokIJUIGoScpisA,989
-judgeval/constants.py,sha256=xuO-Und5c0-K3yTRn2fAkwyY2uTf8b7dGd39CPVqkSQ,5661
+judgeval/constants.py,sha256=MmkgNXdwQOyYSVJc_I8EjX12OWZdFEzjaqXduRowuU4,6033
 judgeval/evaluation_run.py,sha256=KNGtaGAwD18pDNOKF7PCMlLnQe9SpRLTs0XWFMrCiLc,6684
 judgeval/judgment_client.py,sha256=JO3AkU-disPHQVK5g1SM-bs_EUSy8QZ3AaAj_Q2ag6s,24968
-judgeval/rules.py,sha256=jkh1cXXcUf8oRY7xJUZfcQBYWn_rjUW4GvrhRt15PeU,20265
-judgeval/run_evaluation.py,sha256=MshtOGvWm_eGj2JamEtiMWvPjdCwrKTp9WcAUrBm2Fs,49673
+judgeval/rules.py,sha256=LLojqmiKzQ90jAczccfaOoc3b9LBJCWX0hZ7p439no8,21110
+judgeval/run_evaluation.py,sha256=JI-BCyEVKW61JJ4qxFMk1ww4tams-1g_0aaCE4cHrU8,50252
 judgeval/version_check.py,sha256=bvJEidB7rAeXozoUbN9Yb97QOR_s2hgvpvj74jJ5HlY,943
 judgeval/common/__init__.py,sha256=7d24BRxtncpMj3AAJCj8RS7TqgjXmW777HVZH6-3sBs,289
 judgeval/common/exceptions.py,sha256=U-TxHLn7oVMezsMuoYouNDb2XuS8RCggfntYf5_6u4E,565
 judgeval/common/logger.py,sha256=KO75wWXCxhUHUMvLaTU31ZzOk6tkZBa7heQ7y0f-zFE,6062
-judgeval/common/s3_storage.py,sha256=W8wq9S7qJZdqdBR4sk3aEZ4K3-pz40DOoolOJrWs9Vo,3768
-judgeval/common/tracer.py,sha256=rYNmyB3Z955xfnKmlase6gub8Xf5xz6nQefONs_Td5U,90870
-judgeval/common/utils.py,sha256=sWdHfqgiF6AnKTQNmeUBfoEsddXgInI5M24t2-QYexk,34271
+judgeval/common/s3_storage.py,sha256=UZZzQ8CP9_42SKDoKpPncJx8CL5Dchh4jFlKxDKi-cs,3938
+judgeval/common/tracer.py,sha256=jbXtgBgrfGH-zxW6Kf4VDpq8ot-yb0ggaC5isCQFGvw,128882
+judgeval/common/utils.py,sha256=l2nvm3-LeeScZ02H9TB2AcJh1gJSK1lNdi1Tu0p_fNQ,34276
 judgeval/data/__init__.py,sha256=GX_GloDtBB35mv3INWbSTP2r9cwCU2IeIYjzRT0SAd8,530
 judgeval/data/custom_example.py,sha256=QRBqiRiZS8UgVeTRHY0r1Jzm6yAYsyg6zmHxQGxdiQs,739
 judgeval/data/example.py,sha256=jcK78ff-TKNl9Qtxvbd1g61crpo-s4fWHaqyMIbQNq0,6877
 judgeval/data/result.py,sha256=KfU9lhAKG_Xo2eGDm2uKVVRZpf177IDASg1cIwedJwE,3184
 judgeval/data/scorer_data.py,sha256=JVlaTx1EP2jw2gh3Vgx1CSEsvIFABAN26IquKyxwiJQ,3273
 judgeval/data/tool.py,sha256=eEEvGDNNYWhcQiI6cjDv3rO1VoOJJS5LWGS76Gb_gtY,1813
-judgeval/data/trace.py,sha256=S9IQunatke-Kcxi2-qXg3CtbmxBk8VGBDJzWshx7zJg,4798
+judgeval/data/trace.py,sha256=5HSJbCMvNTF4O8D_364dGv2cs-0oa4rCQcYR_hS5FG4,4881
 judgeval/data/trace_run.py,sha256=fiB5Z5il9U9XqvksdA2DbLNd96U_Wrz8K00RuFJBy38,2324
 judgeval/data/datasets/__init__.py,sha256=IdNKhQv9yYZ_op0rdBacrFaFVmiiYQ3JTzXzxOTsEVQ,176
 judgeval/data/datasets/dataset.py,sha256=pq9-A1mg2Brpjg1TufDU_eLo9sQhX0nw-UTGaf3jCXA,12952
 judgeval/data/datasets/eval_dataset_client.py,sha256=LJ1bf1sZAC4ZBCRTQ1Y4VrJuNSslYBQ1y9YKuhYxwqY,15176
-judgeval/integrations/langgraph.py,sha256=L9zPPWVLGL2HWuwHPqM5Kic4S7EfQ_Y1Y3YKBJNfGCA,23004
+judgeval/integrations/langgraph.py,sha256=Ogk3MFE116WfRV4w_2c6mp3d27Uea7vmLstltML8VBM,31963
 judgeval/judges/__init__.py,sha256=6X7VSwrwsdxGBNxCyapVRWGghhKOy3MVxFNMQ62kCXM,308
 judgeval/judges/base_judge.py,sha256=ch_S7uBB7lyv44Lf1d7mIGFpveOO58zOkkpImKgd9_4,994
 judgeval/judges/litellm_judge.py,sha256=DhB6px9ELZL3gbMb2w4FkBliuTlaCVIcjE8v149G6NM,2425
@@ -60,9 +60,9 @@ judgeval/scorers/judgeval_scorers/classifiers/__init__.py,sha256=Qt81W5ZCwMvBAne
 judgeval/scorers/judgeval_scorers/classifiers/text2sql/__init__.py,sha256=8iTzMvou1Dr8pybul6lZHKjc9Ye2-0_racRGYkhEdTY,74
 judgeval/scorers/judgeval_scorers/classifiers/text2sql/text2sql_scorer.py,sha256=O9xq2Cxcg16pFNZwHTb_MDJ5ehFab6oDiiNtC47AnY4,2584
 judgeval/tracer/__init__.py,sha256=wy3DYpH8U_z0GO_K_gOSkK0tTTD-u5eLDo0T5xIBoAc,147
-judgeval/utils/alerts.py,sha256=O19Xj7DA0YVjl8PWiuH4zfdZeu3yiLVvHfY8ah2wG0g,2759
+judgeval/utils/alerts.py,sha256=7HO42fEskQpwocUU-lq6EX4LGPzpxbIhaiJ5pkH31-I,3278
 judgeval/utils/data_utils.py,sha256=pB4GBWi8XoM2zSR2NlLXH5kqcQ029BVhDxaVKkdmiBY,1860
-judgeval-0.0.41.dist-info/METADATA,sha256=-sO68MUEmN3s4ji7Vf1gTuPv60R7Ny6bMcuuKlFSSI8,57358
-judgeval-0.0.41.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-judgeval-0.0.41.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
-judgeval-0.0.41.dist-info/RECORD,,
+judgeval-0.0.43.dist-info/METADATA,sha256=nA8kVqJDfwTJTzV31R3dbgkt4VTbcWTc_WRxyuWZZtQ,55748
+judgeval-0.0.43.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+judgeval-0.0.43.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
+judgeval-0.0.43.dist-info/RECORD,,