judgeval 0.0.39__py3-none-any.whl → 0.0.40__py3-none-any.whl

{judgeval-0.0.39.dist-info → judgeval-0.0.40.dist-info}/RECORD

@@ -1,25 +1,25 @@
 judgeval/__init__.py,sha256=x9HWt4waJwJMAqTuJSg2MezF9Zg-macEjeU-ajbly-8,330
-judgeval/clients.py,sha256=6VQmEqmfCngUdS2MuPBIpHvtDFqOENm8-_BmMvjLyRQ,944
-judgeval/constants.py,sha256=aDEy51CUbzp_CWARFmw3Fie5fZ-2pkaYPc_gUEbvT4Y,5591
-judgeval/evaluation_run.py,sha256=V9xMyiJ7e9lqHRblaeeMh6oyx1MEtGwfSxYtbi-EeXY,6746
-judgeval/judgment_client.py,sha256=eQQ6J3iUPHfBu9v83-8F-yNMqf015b1NoGsbLOzy2s4,23375
+judgeval/clients.py,sha256=EiTmvvWksTPyWIuMC9jz06SPY2vFzokIJUIGoScpisA,989
+judgeval/constants.py,sha256=xuO-Und5c0-K3yTRn2fAkwyY2uTf8b7dGd39CPVqkSQ,5661
+judgeval/evaluation_run.py,sha256=KNGtaGAwD18pDNOKF7PCMlLnQe9SpRLTs0XWFMrCiLc,6684
+judgeval/judgment_client.py,sha256=TkYNCzuy5toIqvsgCSGO4WyKfUSgEM_gX2pbQqWCFJo,24481
 judgeval/rules.py,sha256=jkh1cXXcUf8oRY7xJUZfcQBYWn_rjUW4GvrhRt15PeU,20265
-judgeval/run_evaluation.py,sha256=bYNbMubqOOUNlsplY5Iw9IpUxuuqsJHIs-RweWC45E4,47474
+judgeval/run_evaluation.py,sha256=Kg2iFrpVq-rGMfQokM5s_LJ4BSqGNxjQUxnxfaiTOZ4,49135
 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=EkWkg2AsS5FIj2ffh912qZZ9ew5h3hu2rynPBDsMszw,80463
+judgeval/common/tracer.py,sha256=0HwWwbvnT9Z686q9ppqUB54xR-GKqlBnkXf29c76eow,84425
 judgeval/common/utils.py,sha256=w1SjpDtB1DTJapFSAvLzr_a3gGI45iacEoxIUnQXx4Q,34087
-judgeval/data/__init__.py,sha256=Q4WiIva20U_NgxGr-MU-9FWN_eFzUZBVgCsBmoo7IM8,501
+judgeval/data/__init__.py,sha256=GX_GloDtBB35mv3INWbSTP2r9cwCU2IeIYjzRT0SAd8,530
 judgeval/data/custom_example.py,sha256=QRBqiRiZS8UgVeTRHY0r1Jzm6yAYsyg6zmHxQGxdiQs,739
-judgeval/data/example.py,sha256=XptCg2dLMS46SfDYa4kLgq1zXnlDnhOmR15Ci_08p90,6882
+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=x6YsdTTfeIwSn5f1xIDU3j1xJgSCzho0FW1ojR-L0Ac,612
-judgeval/data/trace.py,sha256=euYIbwYsGqATWIeOZwBzNWS3hh3wefVzMJ7v5rHvG6c,5069
-judgeval/data/trace_run.py,sha256=G_OsHNK_nZzJKhtdiyWp7GFyyns5AOJZ956GM_4jXM0,2192
+judgeval/data/tool.py,sha256=eEEvGDNNYWhcQiI6cjDv3rO1VoOJJS5LWGS76Gb_gtY,1813
+judgeval/data/trace.py,sha256=ETZEb_MJfv4vWr2y_uZ7FfIua7GrV6jgSUVjjURAdlQ,4602
+judgeval/data/trace_run.py,sha256=fiB5Z5il9U9XqvksdA2DbLNd96U_Wrz8K00RuFJBy38,2324
 judgeval/data/datasets/__init__.py,sha256=IdNKhQv9yYZ_op0rdBacrFaFVmiiYQ3JTzXzxOTsEVQ,176
 judgeval/data/datasets/dataset.py,sha256=oU9hvZTifK2x8em3FhL3oIqgHOByfJWH6C_9rIKnL5g,12773
 judgeval/data/datasets/eval_dataset_client.py,sha256=3RBfkaMrkudjnmY_qFwY4I-2mOPE3XK4WxkfSweLB-Q,15016
@@ -30,17 +30,18 @@ judgeval/judges/litellm_judge.py,sha256=DhB6px9ELZL3gbMb2w4FkBliuTlaCVIcjE8v149G
 judgeval/judges/mixture_of_judges.py,sha256=D97h8L-6saPwwppVwitrIdlMAjizzxGWeVOfNyVnXZA,15550
 judgeval/judges/together_judge.py,sha256=l00hhPerAZXg3oYBd8cyMtWsOTNt_0FIqoxhKJKQe3k,2302
 judgeval/judges/utils.py,sha256=vL-15_udU94JHUAiyrAvHAKMj6Fqypg01ek4YH5zVCM,2687
-judgeval/scorers/__init__.py,sha256=-4GLkYiLKI_BxpoIfgadCFEUfqJcBWZLAtfrInjZT0Q,1282
+judgeval/scorers/__init__.py,sha256=VKPveyGCv5Rc0YtuT7iAxSv-M5EuikqAVeaGNnYMuWE,1340
 judgeval/scorers/api_scorer.py,sha256=NQ_CrrUPhSUk1k2Q8rKpCG_TU2FT32sFEqvb-Yi54B0,2688
 judgeval/scorers/exceptions.py,sha256=eGW5CuJgZ5YJBFrE4FHDSF651PO1dKAZ379mJ8gOsfo,178
-judgeval/scorers/judgeval_scorer.py,sha256=79-JJurqHP-qTaWNWInx4SjvQYwXc9lvfPPNgwsh2yA,6773
-judgeval/scorers/prompt_scorer.py,sha256=PaAs2qRolw1P3_I061Xvk9qzvF4O-JR8g_39RqXnHcM,17728
-judgeval/scorers/score.py,sha256=m9luk5ZLeUCual5CpI-9ZR9nqR3eC9wJLVT87SFPN6g,18747
+judgeval/scorers/judgeval_scorer.py,sha256=id4s72vn4pWKbjZDnWKHGlc4kqyUkrFqdlX1SgyDj6c,7027
+judgeval/scorers/prompt_scorer.py,sha256=9MGSG2OVvX2i2CUZmXg0i3rJHQKMe2dMBdMDcnjp8mg,11845
+judgeval/scorers/score.py,sha256=h4eVlbItqG8R0nQgSgeyicYSIraZV9MvV-RRaFu46mg,18762
 judgeval/scorers/utils.py,sha256=iHQVTlIANbmCTXz9kTeSdOytgUZ_T74Re61ajqsk_WQ,6827
 judgeval/scorers/judgeval_scorers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-judgeval/scorers/judgeval_scorers/api_scorers/__init__.py,sha256=QhHKpl6kNEXxuwriSEwQ5gIIxb7NeHZ1H_7SAZhQiQk,1872
+judgeval/scorers/judgeval_scorers/api_scorers/__init__.py,sha256=knJr1fMqdisS2dt1caMyiMmVkP9QMZBTBTRgjoIRKdQ,2112
 judgeval/scorers/judgeval_scorers/api_scorers/answer_correctness.py,sha256=Fnd9CVIOZ73sWEWymsU5eBrrZqPFjMZ0BKpeW-PDyTg,711
 judgeval/scorers/judgeval_scorers/api_scorers/answer_relevancy.py,sha256=oETeN9K0HSIRdL2SDqn82Vskpwh5SlKnZvs5VDm2OBU,658
+judgeval/scorers/judgeval_scorers/api_scorers/classifier_scorer.py,sha256=s5DKbvLgWN5kV00isu56A5U4R7w1ahlGVN1yxscqHHc,4515
 judgeval/scorers/judgeval_scorers/api_scorers/comparison.py,sha256=kuzf9OWvpY38yYSwlBgneLkUZwJNM4FQqvbS66keA90,1249
 judgeval/scorers/judgeval_scorers/api_scorers/contextual_precision.py,sha256=tpSuzFAaW8X9xqA0aLLKwh7qmBK0Pc_bJZMIe_q412U,770
 judgeval/scorers/judgeval_scorers/api_scorers/contextual_recall.py,sha256=pFVhk4pLtQ-FnNlbI-dFF-SIh69Jza7erHqiPkFWoBo,758
@@ -53,14 +54,15 @@ judgeval/scorers/judgeval_scorers/api_scorers/hallucination.py,sha256=k5gDOki-8K
 judgeval/scorers/judgeval_scorers/api_scorers/instruction_adherence.py,sha256=XnSGEkQfwVqaqnHEGMCsxNiHVzrsrej48uDbLoWc8CQ,678
 judgeval/scorers/judgeval_scorers/api_scorers/json_correctness.py,sha256=mMKEuR87_yanEuZJ5YSGFMHDD_oLVZ6-rQuciFaDOMA,1095
 judgeval/scorers/judgeval_scorers/api_scorers/summarization.py,sha256=QmWB8bVbDYHY5FcF0rYZE_3c2XXgMLRmR6aXJWfdMC4,655
+judgeval/scorers/judgeval_scorers/api_scorers/tool_dependency.py,sha256=xHt4NsPCOyQkI5mUnN35D-vBLLFu6ZCMaiIVc4RTlj8,620
 judgeval/scorers/judgeval_scorers/api_scorers/tool_order.py,sha256=urm8LgkeZA7e-ePWo6AToKGheQYSp6MOpKon5NF5EJw,570
 judgeval/scorers/judgeval_scorers/classifiers/__init__.py,sha256=Qt81W5ZCwMvBAne0LfQDb8xvg5iOG1vEYP7WizgwAZo,67
 judgeval/scorers/judgeval_scorers/classifiers/text2sql/__init__.py,sha256=8iTzMvou1Dr8pybul6lZHKjc9Ye2-0_racRGYkhEdTY,74
-judgeval/scorers/judgeval_scorers/classifiers/text2sql/text2sql_scorer.py,sha256=ly72Z7s_c8NID6-nQnuW8qEGEW2MqdvpJ-5WfXzbAQg,2579
+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/data_utils.py,sha256=pB4GBWi8XoM2zSR2NlLXH5kqcQ029BVhDxaVKkdmiBY,1860
-judgeval-0.0.39.dist-info/METADATA,sha256=Q4wTRKXRoTozgF96BJFFoGwOoy-vLnAGs0HOQ9PCZ_k,11860
-judgeval-0.0.39.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-judgeval-0.0.39.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
-judgeval-0.0.39.dist-info/RECORD,,
+judgeval-0.0.40.dist-info/METADATA,sha256=pAFVIDRiMlCOrbfQ0-epidECcUHl_fFuiLPgGnhDJYo,56712
+judgeval-0.0.40.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+judgeval-0.0.40.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
+judgeval-0.0.40.dist-info/RECORD,,

judgeval-0.0.39.dist-info/METADATA

@@ -1,247 +0,0 @@
-Metadata-Version: 2.4
-Name: judgeval
-Version: 0.0.39
-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: >=3.11
-Requires-Dist: anthropic
-Requires-Dist: boto3
-Requires-Dist: google-genai
-Requires-Dist: langchain-anthropic
-Requires-Dist: langchain-core
-Requires-Dist: langchain-huggingface
-Requires-Dist: langchain-openai
-Requires-Dist: litellm==1.38.12
-Requires-Dist: nest-asyncio
-Requires-Dist: openai
-Requires-Dist: pandas
-Requires-Dist: python-dotenv==1.0.1
-Requires-Dist: requests
-Requires-Dist: together
-Description-Content-Type: text/markdown
-
-<div align="center">
-
-<img src="assets/logo-light.svg#gh-light-mode-only" alt="Judgment Logo" width="400" />
-<img src="assets/logo-dark.svg#gh-dark-mode-only" alt="Judgment Logo" width="400" />
-
-**Build monitoring & evaluation pipelines for complex agents**
-
-<img src="assets/experiments_page.png" alt="Judgment Platform Experiments Page" width="800" />
-
-<br>
-
-## [🌐 Landing Page](https://www.judgmentlabs.ai/) • [Twitter/X](https://x.com/JudgmentLabs) • [💼 LinkedIn](https://www.linkedin.com/company/judgmentlabs) • [📚 Docs](https://judgment.mintlify.app/getting_started) • [🚀 Demos](https://www.youtube.com/@AlexShan-j3o) • [🎮 Discord](https://discord.gg/taAufyhf)
-</div>
-
-## Judgeval: open-source testing, monitoring, and optimization for AI agents
-
-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.
-
-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://judgment.mintlify.app/getting_started) to get started.
-
-Judgeval is created and maintained by [Judgment Labs](https://judgmentlabs.ai/).
-
-## 📋 Table of Contents
-* [✨ Features](#-features)
-    * [🔍 Tracing](#-tracing)
-    * [🧪 Evals](#-evals)
-    * [📡 Monitoring](#-monitoring)
-    * [📊 Datasets](#-datasets)
-    * [💡 Insights](#-insights)
-* [🛠️ Installation](#️-installation)
-* [🏁 Get Started](#-get-started)
-* [🏢 Self-Hosting](#-self-hosting)
-* [📚 Cookbooks](#-cookbooks)
-* [⭐ Star Us on GitHub](#-star-us-on-github)
-* [❤️ Contributors](#️-contributors)
-
-<!-- Created by https://github.com/ekalinin/github-markdown-toc -->
-
-
-## ✨ Features
-
-|  |  |
-|:---|:---:|
-| <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> |
-
-## 🛠️ Installation
-
-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/). 
-
-**If you don't have keys, [create an account](https://app.judgmentlabs.ai/register) on the platform!**
-
-## 🏁 Get Started
-
-Here's how you can quickly start using Judgeval:
-
-### 🛰️ 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
-from judgeval.common.tracer import Tracer, wrap
-from openai import OpenAI
-
-client = wrap(OpenAI())
-judgment = Tracer(project_name="my_project")
-
-@judgment.observe(span_type="tool")
-def my_tool():
-    return "What's the capital of the U.S.?"
-
-@judgment.observe(span_type="function")
-def main():
-    task_input = my_tool()
-    res = client.chat.completions.create(
-        model="gpt-4.1",
-        messages=[{"role": "user", "content": f"{task_input}"}]
-    )
-    return res.choices[0].message.content
-
-main()
-```
-
-[Click here](https://judgment.mintlify.app/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
-from judgeval import JudgmentClient
-from judgeval.data import Example
-from judgeval.scorers import FaithfulnessScorer
-
-client = JudgmentClient()
-
-example = Example(
-    input="What if these shoes don't fit?",
-    actual_output="We offer a 30-day full refund at no extra cost.",
-    retrieval_context=["All customers are eligible for a 30 day full refund at no extra cost."],
-)
-
-scorer = FaithfulnessScorer(threshold=0.5)
-results = client.run_evaluation(
-    examples=[example],
-    scorers=[scorer],
-    model="gpt-4.1",
-)
-print(results)
-```
-
-[Click here](https://judgment.mintlify.app/getting_started#create-your-first-experiment) for a more detailed explanation.
-
-### 📡 Online Evaluations
-
-Attach performance monitoring on traces to measure the quality of your systems in production.
-
-Using the same `traces.py` file we created earlier, modify `main` function:
-
-```python
-from judgeval.common.tracer import Tracer, wrap
-from judgeval.scorers import AnswerRelevancyScorer
-from openai import OpenAI
-
-client = wrap(OpenAI())
-judgment = Tracer(project_name="my_project")
-
-@judgment.observe(span_type="tool")
-def my_tool():
-    return "Hello world!"
-
-@judgment.observe(span_type="function")
-def main():
-    task_input = my_tool()
-    res = client.chat.completions.create(
-        model="gpt-4.1",
-        messages=[{"role": "user", "content": f"{task_input}"}]
-    ).choices[0].message.content
-
-    judgment.async_evaluate(
-        scorers=[AnswerRelevancyScorer(threshold=0.5)],
-        input=task_input,
-        actual_output=res,
-        model="gpt-4.1"
-    )
-    print("Online evaluation submitted.")
-    return res
-
-main()
-```
-
-[Click here](https://judgment.mintlify.app/getting_started#create-your-first-online-evaluation) for a more detailed explanation.
-
-## 🏢 Self-Hosting
-
-Run Judgment on your own infrastructure: we provide comprehensive self-hosting capabilities that give you full control over the backend and data plane that Judgeval interfaces with.
-
-### Key Features
-* Deploy Judgment on your own AWS account
-* Store data in your own Supabase instance
-* Access Judgment through your own custom domain
-
-### Getting Started
-1. Check out our [self-hosting documentation](https://judgment.mintlify.app/self_hosting/get_started) for detailed setup instructions, along with how your self-hosted instance can be accessed
-2. Use the [Judgment CLI](https://github.com/JudgmentLabs/judgment-cli) to deploy your self-hosted environment
-3. After your self-hosted instance is setup, make sure the `JUDGMENT_API_URL` environmental variable is set to your self-hosted backend endpoint
-
-## 📚 Cookbooks
-
-Have your own? We're happy to feature it if you create a PR or message us on [Discord](https://discord.gg/taAufyhf).
-
-You can access our repo of cookbooks [here](https://github.com/JudgmentLabs/judgment-cookbook). Here are some highlights:
-
-### 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.
-
-## ⭐ Star Us on GitHub
-
-If you find Judgeval useful, please consider giving us a star on GitHub! Your support helps us grow our community and continue improving the product.
-
-
-## ❤️ Contributors
-
-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)
-