evalscope 0.5.5rc1__py3-none-any.whl → 0.6.0rc0__py3-none-any.whl

{evalscope-0.5.5rc1.dist-info → evalscope-0.6.0rc0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: evalscope
-Version: 0.5.5rc1
+Version: 0.6.0rc0
 Summary: EvalScope: Lightweight LLMs Evaluation Framework
 Home-page: https://github.com/modelscope/evalscope
 Author: ModelScope team
@@ -19,22 +19,22 @@ Requires-Dist: torch
 Requires-Dist: absl-py
 Requires-Dist: accelerate
 Requires-Dist: cachetools
-Requires-Dist: datasets (<3.0.0,>=2.18.0)
+Requires-Dist: datasets (<=3.0.1,>=3.0.0)
 Requires-Dist: editdistance
 Requires-Dist: jsonlines
 Requires-Dist: matplotlib
 Requires-Dist: modelscope[framework]
-Requires-Dist: nltk
+Requires-Dist: nltk (>=3.9)
 Requires-Dist: openai
 Requires-Dist: pandas
 Requires-Dist: plotly
-Requires-Dist: pyarrow
+Requires-Dist: pyarrow (<=17.0.0)
 Requires-Dist: pympler
 Requires-Dist: pyyaml
 Requires-Dist: regex
 Requires-Dist: requests
 Requires-Dist: requests-toolbelt
-Requires-Dist: rouge-score
+Requires-Dist: rouge-score (>=0.1.0)
 Requires-Dist: sacrebleu
 Requires-Dist: scikit-learn
 Requires-Dist: seaborn
@@ -52,22 +52,22 @@ Requires-Dist: torch ; extra == 'all'
 Requires-Dist: absl-py ; extra == 'all'
 Requires-Dist: accelerate ; extra == 'all'
 Requires-Dist: cachetools ; extra == 'all'
-Requires-Dist: datasets (<3.0.0,>=2.18.0) ; extra == 'all'
+Requires-Dist: datasets (<=3.0.1,>=3.0.0) ; extra == 'all'
 Requires-Dist: editdistance ; extra == 'all'
 Requires-Dist: jsonlines ; extra == 'all'
 Requires-Dist: matplotlib ; extra == 'all'
 Requires-Dist: modelscope[framework] ; extra == 'all'
-Requires-Dist: nltk ; extra == 'all'
+Requires-Dist: nltk (>=3.9) ; extra == 'all'
 Requires-Dist: openai ; extra == 'all'
 Requires-Dist: pandas ; extra == 'all'
 Requires-Dist: plotly ; extra == 'all'
-Requires-Dist: pyarrow ; extra == 'all'
+Requires-Dist: pyarrow (<=17.0.0) ; extra == 'all'
 Requires-Dist: pympler ; extra == 'all'
 Requires-Dist: pyyaml ; extra == 'all'
 Requires-Dist: regex ; extra == 'all'
 Requires-Dist: requests ; extra == 'all'
 Requires-Dist: requests-toolbelt ; extra == 'all'
-Requires-Dist: rouge-score ; extra == 'all'
+Requires-Dist: rouge-score (>=0.1.0) ; extra == 'all'
 Requires-Dist: sacrebleu ; extra == 'all'
 Requires-Dist: scikit-learn ; extra == 'all'
 Requires-Dist: seaborn ; extra == 'all'
@@ -80,8 +80,11 @@ Requires-Dist: transformers (>=4.33) ; extra == 'all'
 Requires-Dist: transformers-stream-generator ; extra == 'all'
 Requires-Dist: jieba ; extra == 'all'
 Requires-Dist: rouge-chinese ; extra == 'all'
-Requires-Dist: ms-opencompass (>=0.1.1) ; extra == 'all'
+Requires-Dist: ms-opencompass (>=0.1.3) ; extra == 'all'
 Requires-Dist: ms-vlmeval (>=0.0.5) ; extra == 'all'
+Requires-Dist: mteb (==1.19.4) ; extra == 'all'
+Requires-Dist: ragas (==0.2.3) ; extra == 'all'
+Requires-Dist: webdataset (>0.2.0) ; extra == 'all'
 Provides-Extra: inner
 Requires-Dist: absl-py ; extra == 'inner'
 Requires-Dist: accelerate ; extra == 'inner'
@@ -109,15 +112,22 @@ Requires-Dist: tqdm ; extra == 'inner'
 Requires-Dist: transformers (<4.43,>=4.33) ; extra == 'inner'
 Requires-Dist: transformers-stream-generator ; extra == 'inner'
 Provides-Extra: opencompass
-Requires-Dist: ms-opencompass (>=0.1.1) ; extra == 'opencompass'
+Requires-Dist: ms-opencompass (>=0.1.3) ; extra == 'opencompass'
+Provides-Extra: rag
+Requires-Dist: mteb (==1.19.4) ; extra == 'rag'
+Requires-Dist: ragas (==0.2.3) ; extra == 'rag'
+Requires-Dist: webdataset (>0.2.0) ; extra == 'rag'
 Provides-Extra: vlmeval
 Requires-Dist: ms-vlmeval (>=0.0.5) ; extra == 'vlmeval'
 
-English | [简体中文](README_zh.md)
 
 
 ![](docs/en/_static/images/evalscope_logo.png)
 
+<p align="center">
+    English | <a href="README_zh.md">简体中文</a>
+</p>
+
 <p align="center">
 <a href="https://badge.fury.io/py/evalscope"><img src="https://badge.fury.io/py/evalscope.svg" alt="PyPI version" height="18"></a>
 <a href="https://pypi.org/project/evalscope"><img alt="PyPI - Downloads" src="https://static.pepy.tech/badge/evalscope">
@@ -126,7 +136,7 @@ English | [简体中文](README_zh.md)
     <img src='https://readthedocs.org/projects/evalscope-en/badge/?version=latest' alt='Documentation Status' />
 </a>
 <br>
- <a href="https://evalscope.readthedocs.io/en/latest/"><span style="font-size: 16px;">📖 Documents</span></a> &nbsp | &nbsp<a href="https://evalscope.readthedocs.io/zh-cn/latest/"><span style="font-size: 16px;"> 📖  中文文档</span></a>
+ <a href="https://evalscope.readthedocs.io/en/latest/">📖 Documents</a>
 <p>
 
 
@@ -140,34 +150,15 @@ English | [简体中文](README_zh.md)
 - [Offline Evaluation](#offline-evaluation)
 - [Arena Mode](#arena-mode)
 - [Model Serving Performance Evaluation](#Model-Serving-Performance-Evaluation)
-- [Leaderboard](#leaderboard)
-
-## 📝 Introduction
-
-Large Model (including Large Language Models, Multi-modal Large Language Models) evaluation has become a critical process for assessing and improving LLMs. To better support the evaluation of large models, we propose the EvalScope framework.
 
-### Framework Features
-- **Benchmark Datasets**: Preloaded with several commonly used test benchmarks, including MMLU, CMMLU, C-Eval, GSM8K, ARC, HellaSwag, TruthfulQA, MATH, HumanEval, etc.
-- **Evaluation Metrics**: Implements various commonly used evaluation metrics.
-- **Model Access**: A unified model access mechanism that is compatible with the Generate and Chat interfaces of multiple model families.
-- **Automated Evaluation**: Includes automatic evaluation of objective questions and complex task evaluation using expert models.
-- **Evaluation Reports**: Automatically generates evaluation reports.
-- **Arena Mode**: Used for comparisons between models and objective evaluation of models, supporting various evaluation modes, including:
-  - **Single mode**: Scoring a single model.
-  - **Pairwise-baseline mode**: Comparing against a baseline model.
-  - **Pairwise (all) mode**: Pairwise comparison among all models.
-- **Visualization Tools**: Provides intuitive displays of evaluation results.
-- **Model Performance Evaluation**: Offers a performance testing tool for model inference services and detailed statistics, see [Model Performance Evaluation Documentation](https://evalscope.readthedocs.io/en/latest/user_guides/stress_test.html).
-- **OpenCompass Integration**: Supports OpenCompass as the evaluation backend, providing advanced encapsulation and task simplification, allowing for easier task submission for evaluation.
-- **VLMEvalKit Integration**: Supports VLMEvalKit as the evaluation backend, facilitating the initiation of multi-modal evaluation tasks, supporting various multi-modal models and datasets.
-- **Full-Link Support**: Through seamless integration with the [ms-swift](https://github.com/modelscope/ms-swift) training framework, provides a one-stop development process for model training, model deployment, model evaluation, and report viewing, enhancing user development efficiency.
 
+## 📝 Introduction
 
-<details><summary>Overall Architecture</summary>
+EvalScope is the official model evaluation and performance benchmarking framework launched by the [ModelScope](https://modelscope.cn/) community. It comes with built-in common benchmarks and evaluation metrics, such as MMLU, CMMLU, C-Eval, GSM8K, ARC, HellaSwag, TruthfulQA, MATH, and HumanEval. EvalScope supports various types of model evaluations, including LLMs, multimodal LLMs, embedding models, and reranker models. It is also applicable to multiple evaluation scenarios, such as end-to-end RAG evaluation, arena mode, and model inference performance stress testing. Moreover, with the seamless integration of the ms-swift training framework, evaluations can be initiated with a single click, providing full end-to-end support from model training to evaluation 🚀
 
 <p align="center">
   <img src="docs/en/_static/images/evalscope_framework.png" width="70%">
-  <br>Fig 1. EvalScope Framework.
+  <br>EvalScope Framework.
 </p>
 
 The architecture includes the following modules:
@@ -177,14 +168,17 @@ The architecture includes the following modules:
     - **Native**: EvalScope’s own **default evaluation framework**, supporting various evaluation modes, including single model evaluation, arena mode, baseline model comparison mode, etc.
     - **OpenCompass**: Supports [OpenCompass](https://github.com/open-compass/opencompass) as the evaluation backend, providing advanced encapsulation and task simplification, allowing you to submit tasks for evaluation more easily.
     - **VLMEvalKit**: Supports [VLMEvalKit](https://github.com/open-compass/VLMEvalKit) as the evaluation backend, enabling easy initiation of multi-modal evaluation tasks, supporting various multi-modal models and datasets.
+    - **RAGEval**: Supports RAG evaluation, supporting independent evaluation of embedding models and rerankers using [MTEB/CMTEB](https://evalscope.readthedocs.io/en/latest/user_guides/backend/rageval_backend/mteb.html), as well as end-to-end evaluation using [RAGAS](https://evalscope.readthedocs.io/en/latest/user_guides/backend/rageval_backend/ragas.html).
     - **ThirdParty**: Other third-party evaluation tasks, such as ToolBench.
 4. **Performance Evaluator**: Model performance evaluation, responsible for measuring model inference service performance, including performance testing, stress testing, performance report generation, and visualization.
 5. **Evaluation Report**: The final generated evaluation report summarizes the model's performance, which can be used for decision-making and further model optimization.
 6. **Visualization**: Visualization results help users intuitively understand evaluation results, facilitating analysis and comparison of different model performances.
-</details>
 
 
 ## 🎉 News
+- 🔥 **[2024.10.31]** The best practice for evaluating Multimodal-RAG has been updated, please check the [📖 Blog](https://evalscope.readthedocs.io/zh-cn/latest/blog/RAG/multimodal_RAG.html#multimodal-rag) for more details.
+- 🔥 **[2024.10.23]** Supports multimodal RAG evaluation, including the assessment of image-text retrieval using [CLIP_Benchmark](https://evalscope.readthedocs.io/en/latest/user_guides/backend/rageval_backend/clip_benchmark.html), and extends [RAGAS](https://evalscope.readthedocs.io/en/latest/user_guides/backend/rageval_backend/ragas.html) to support end-to-end multimodal metrics evaluation.
+- 🔥 **[2024.10.8]** Support for RAG evaluation, including independent evaluation of embedding models and rerankers using [MTEB/CMTEB](https://evalscope.readthedocs.io/en/latest/user_guides/backend/rageval_backend/mteb.html), as well as end-to-end evaluation using [RAGAS](https://evalscope.readthedocs.io/en/latest/user_guides/backend/rageval_backend/ragas.html).
 - 🔥 **[2024.09.18]** Our documentation has been updated to include a blog module, featuring some technical research and discussions related to evaluations. We invite you to [📖 read it](https://evalscope.readthedocs.io/en/refact_readme/blog/index.html).
 - 🔥 **[2024.09.12]** Support for LongWriter evaluation, which supports 10,000+ word generation. You can use the benchmark [LongBench-Write](evalscope/third_party/longbench_write/README.md) to measure the long output quality as well as the output length.
 - 🔥 **[2024.08.30]** Support for custom dataset evaluations, including text datasets and multimodal image-text datasets.
@@ -355,9 +349,10 @@ run_task(task_cfg=your_task_cfg)
 ## Evaluation Backend
 EvalScope supports using third-party evaluation frameworks to initiate evaluation tasks, which we call Evaluation Backend. Currently supported Evaluation Backend includes:
 - **Native**: EvalScope's own **default evaluation framework**, supporting various evaluation modes including single model evaluation, arena mode, and baseline model comparison mode.
-- [OpenCompass](https://github.com/open-compass/opencompass): Initiate OpenCompass evaluation tasks through EvalScope. Lightweight, easy to customize, supports seamless integration with the LLM fine-tuning framework ms-swift. [📖 User Guide](https://evalscope.readthedocs.io/en/latest/user_guides/opencompass_backend.html)
-- [VLMEvalKit](https://github.com/open-compass/VLMEvalKit): Initiate VLMEvalKit multimodal evaluation tasks through EvalScope. Supports various multimodal models and datasets, and offers seamless integration with the LLM fine-tuning framework ms-swift. [📖 User Guide](https://evalscope.readthedocs.io/en/latest/user_guides/vlmevalkit_backend.html)
-- **ThirdParty**: The third-party task, e.g. [ToolBench](https://evalscope.readthedocs.io/en/latest/third_party/toolbench.html), you can contribute your own evaluation task to EvalScope as third-party backend.
+- [OpenCompass](https://github.com/open-compass/opencompass): Initiate OpenCompass evaluation tasks through EvalScope. Lightweight, easy to customize, supports seamless integration with the LLM fine-tuning framework ms-swift. [📖 User Guide](https://evalscope.readthedocs.io/en/latest/user_guides/backend/opencompass_backend.html)
+- [VLMEvalKit](https://github.com/open-compass/VLMEvalKit): Initiate VLMEvalKit multimodal evaluation tasks through EvalScope. Supports various multimodal models and datasets, and offers seamless integration with the LLM fine-tuning framework ms-swift. [📖 User Guide](https://evalscope.readthedocs.io/en/latest/user_guides/backend/vlmevalkit_backend.html)
+- **RAGEval**: Initiate RAG evaluation tasks through EvalScope, supporting independent evaluation of embedding models and rerankers using [MTEB/CMTEB](https://evalscope.readthedocs.io/en/latest/user_guides/backend/rageval_backend/mteb.html), as well as end-to-end evaluation using [RAGAS](https://evalscope.readthedocs.io/en/latest/user_guides/backend/rageval_backend/ragas.html): [📖 User Guide](https://evalscope.readthedocs.io/en/latest/user_guides/backend/rageval_backend/index.html)
+- **ThirdParty**: Third-party evaluation tasks, such as [ToolBench](https://evalscope.readthedocs.io/en/latest/third_party/toolbench.html) and [LongBench-Write](https://evalscope.readthedocs.io/en/latest/third_party/longwriter.html).
 
 ## Custom Dataset Evaluation
 EvalScope supports custom dataset evaluation. For detailed information, please refer to the Custom Dataset Evaluation [📖User Guide](https://evalscope.readthedocs.io/en/latest/advanced_guides/custom_dataset.html)
@@ -379,13 +374,10 @@ A stress testing tool that focuses on large language models and can be customize
 Refer to : Model Serving Performance Evaluation [📖 User Guide](https://evalscope.readthedocs.io/en/latest/user_guides/stress_test.html)
 
 
-## Leaderboard
-The LLM Leaderboard aims to provide an objective and comprehensive evaluation standard and platform to help researchers and developers understand and compare the performance of models on various tasks on ModelScope.
-
-Refer to : [Leaderboard](https://modelscope.cn/leaderboard/58/ranking?type=free)
-
 
 ## TO-DO List
+- [x] RAG evaluation
+- [x] VLM evaluation
 - [x] Agents evaluation
 - [x] vLLM
 - [ ] Distributed evaluating
@@ -397,3 +389,7 @@ Refer to : [Leaderboard](https://modelscope.cn/leaderboard/58/ranking?type=free)
 - [ ] Auto-reviewer
   - [ ] Qwen-max
 
+
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=modelscope/evalscope&type=Date)](https://star-history.com/#modelscope/evalscope&Date)

{evalscope-0.5.5rc1.dist-info → evalscope-0.6.0rc0.dist-info}/RECORD

@@ -2,22 +2,53 @@ evalscope/__init__.py,sha256=3eLMMrjkAIAs3vGluXNZn5-xTSbO_vfba9yNPbkVtg8,105
 evalscope/cache.py,sha256=zpGjL9JMosqjk_dkODVwvIGiUC0WAMmMTHDNJOvBQU8,3288
 evalscope/config.py,sha256=G_rpSn5Kd1aPlFJO6asnZu5FUggZmwcYdAxxpuq0yDs,6972
 evalscope/constants.py,sha256=g8lGYlpA4Wk88HwtqId1-jJX_z8Lr2k02gWLsyofyj0,2670
-evalscope/run.py,sha256=T-2zoJpBx6YxLnLJH-iFF3UxUGYTU36PMV_DQ9e8tSM,18484
+evalscope/run.py,sha256=uAXtaxIBcR94jyfHGFAecuzn0y71oLgu-d9VOohCJAw,18738
 evalscope/run_arena.py,sha256=BCWCAiX0BQ9pLMIq08svEcd-IoFr75gFShpV88robIY,8963
 evalscope/run_ms.py,sha256=UtJoGnah64SXigTawJQWTi_TEGjr7Td0rjCTaO-htL8,6028
 evalscope/summarizer.py,sha256=rIyML8HpjQxIpXg8KvQ0CzOS6xMS-JHZh6kUZzkaRsk,6640
-evalscope/version.py,sha256=auPe2msc57SycidTCg5C82JBZdws4TSukCurfVAMuVg,121
-evalscope/backend/__init__.py,sha256=UP_TW5KBq6V_Nvqkeb7PGvGGX3rVYussT43npwCwDgE,135
+evalscope/version.py,sha256=HbExGw191bJuKShYz5RiaxbmdfvIqJQ_bjIjXZhfMDw,121
+evalscope/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/backend/base.py,sha256=5BLrDNNwxsGp35zorD-kphmN15tlBbkuuqwkz8jWZq0,876
 evalscope/backend/opencompass/__init__.py,sha256=UP_TW5KBq6V_Nvqkeb7PGvGGX3rVYussT43npwCwDgE,135
 evalscope/backend/opencompass/api_meta_template.py,sha256=sBW0XbVDOKeJ7mVUDLhmcG4e0yClw3eluazdp_8wtgQ,1753
 evalscope/backend/opencompass/backend_manager.py,sha256=_eg82FLAVxQ6t5e1OqlyuxZcngqD8rxvI5EijLUh_zI,10294
 evalscope/backend/opencompass/tasks/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/backend/opencompass/tasks/eval_api.py,sha256=12lrgDpMzZ1XBRboq5TEOovDPCMDwwGCJoRT78Ox_yo,1108
-evalscope/backend/opencompass/tasks/eval_datasets.py,sha256=bYFHkjiwZqh2FVRo1I88xEDZ6nYmZjAgG5ZODbthKFI,5241
+evalscope/backend/opencompass/tasks/eval_datasets.py,sha256=t2t3_dHZf-eMfNqpQaD2XIjWZejTN4AxVXITdj_4Y3o,5324
+evalscope/backend/rag_eval/__init__.py,sha256=8om6TVnTMmyTEQt1jBuUQA4UfIzyps-_-ih90H_Qjio,284
+evalscope/backend/rag_eval/backend_manager.py,sha256=jmO-UMu6_iOXMnl4--PrMWCsnIYEhsbiX017rtURqm0,2997
+evalscope/backend/rag_eval/clip_benchmark/__init__.py,sha256=gDXCiRUTSeGQHxd5SjQsnphMqHJ2si2jywRiHvujEOg,150
+evalscope/backend/rag_eval/clip_benchmark/arguments.py,sha256=VbB7JY4NunV83ewkZrUiM74jTzSETMPcOLlllRs7djA,1537
+evalscope/backend/rag_eval/clip_benchmark/dataset_builder.py,sha256=vaguNflVBC5-0lk1kaU7CLTbkJuBf0hHGIdmoq4Bn8s,8474
+evalscope/backend/rag_eval/clip_benchmark/task_template.py,sha256=asEF_Nt2Xt3DtIS49J9nQKEjTdrcAkYhY4zumCDzSws,3990
+evalscope/backend/rag_eval/clip_benchmark/tasks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/backend/rag_eval/clip_benchmark/tasks/image_caption.py,sha256=Bj2ysvM0JT-6T40v0rffeZgJIRht5KVX0GzMOiUphf0,2578
+evalscope/backend/rag_eval/clip_benchmark/tasks/zeroshot_classification.py,sha256=ZrUYDbQ75eo0vmIwXh5Bb9c4nyEwd4AO2oURaIqjIII,7502
+evalscope/backend/rag_eval/clip_benchmark/tasks/zeroshot_retrieval.py,sha256=Bcs64xece4BMNhxuaFimOwMJnlpjNxfGrdSCWOYItko,5977
+evalscope/backend/rag_eval/cmteb/__init__.py,sha256=ajVz6XP5hqPq-jm66hp2poA2qKj1V19ZGoqjrGUlO7U,279
+evalscope/backend/rag_eval/cmteb/arguments.py,sha256=wZvnVir2tSxYCV_DPR3TSDj4VxtUn3wLhBPqyMJYKno,2330
+evalscope/backend/rag_eval/cmteb/base.py,sha256=fYrIjKwOLwBAHb2rlNkEjYScjZ5Qpyv2LdMmWZYWREA,2830
+evalscope/backend/rag_eval/cmteb/task_template.py,sha256=Clyc8TZCtZrL6MjAw49rh55Xb3hf2y1C3SzLvZsorLE,2646
+evalscope/backend/rag_eval/cmteb/tasks/Classification.py,sha256=7adR40W6Uu58-QR9jCUP4k7TdAnG0oT225v4xHXah2g,10635
+evalscope/backend/rag_eval/cmteb/tasks/Clustering.py,sha256=-oJ9rXy7pgOB7Gyf68TcSlmmAUoBx5hKofcKNuIsCd8,8977
+evalscope/backend/rag_eval/cmteb/tasks/CustomTask.py,sha256=rF6dtrwOfvJoq2Y4myZg9_638M1g06qq0hWCmvxsIo0,2039
+evalscope/backend/rag_eval/cmteb/tasks/PairClassification.py,sha256=2WkaTE-jF8jqsu1UcNDqN8A4567UzW5boD_0B83j-9A,4008
+evalscope/backend/rag_eval/cmteb/tasks/Reranking.py,sha256=C34nDuya8OT3aeMxYCYjUpUtWp7w00jSfIYQSInlNAg,5329
+evalscope/backend/rag_eval/cmteb/tasks/Retrieval.py,sha256=wUxiQH5aOmWNS4YswACyHqBn5xqP5eyvsq6U9WSp5R0,11457
+evalscope/backend/rag_eval/cmteb/tasks/STS.py,sha256=6GMaoCANM-IKYLk4srHOYr_eurav3DGihHMQeJPXR6k,12054
+evalscope/backend/rag_eval/cmteb/tasks/__init__.py,sha256=eBHm_TWeh7WiwpdVBtUlegeXMAxJyVQdUHRhJERobIs,1506
+evalscope/backend/rag_eval/ragas/__init__.py,sha256=-VnStCVy7uHih2uipG_7AD4i2FQ5sVM7_NI-sEZBpRQ,170
+evalscope/backend/rag_eval/ragas/arguments.py,sha256=BriXjcXVk2FqjDNuFYpfBZsUVzrkrYH7egbO9x-jcZ4,1873
+evalscope/backend/rag_eval/ragas/task_template.py,sha256=nv2i9-NE2SXpLrVKo5zhadYYKbDFVXVVA4sfgb4ti4g,1693
+evalscope/backend/rag_eval/ragas/metrics/__init__.py,sha256=HgY5nrcNtWpQ7gBi5lCEJXJVINd_R57dsmI8ldS2rd0,160
+evalscope/backend/rag_eval/ragas/metrics/multi_modal_faithfulness.py,sha256=Uqz5qWZ76Gos95_QlhwncbATXyk0YX4wkI0LiAdPElU,3838
+evalscope/backend/rag_eval/ragas/metrics/multi_modal_relevance.py,sha256=CdLnWHq1eTna6j3F5-pncW5YusxD_v3ScjzeCsZ7mng,3967
+evalscope/backend/rag_eval/ragas/tasks/__init__.py,sha256=WO2xja0g0JSiYGdu2uAEDQgDceuFcgPWwPoqFnwDU0s,172
+evalscope/backend/rag_eval/ragas/tasks/testset_generation.py,sha256=In-2VvZJIZvXl9idGUUQBTb7Gu-o1yFLjaqj-eJkWw0,8437
+evalscope/backend/rag_eval/ragas/tasks/translate_prompt.py,sha256=bXOqik6qKWzbrEz21ykdkqeqqPrmoUIhTwW6eRQXy0M,2222
 evalscope/backend/vlm_eval_kit/__init__.py,sha256=xTgHM95lWzh4s0W7zxLwYkgUbPAZfAb0UoGGmyyBXrs,83
-evalscope/backend/vlm_eval_kit/backend_manager.py,sha256=k52qTUqkp1kJivKn8bVrKoF8cng4xYTQLUmjnH_CWPM,6080
-evalscope/backend/vlm_eval_kit/custom_dataset.py,sha256=zC40Jw9bIqcGKuWS9oKPAlQdBARc-zY3sJlSiU-u-sI,1625
+evalscope/backend/vlm_eval_kit/backend_manager.py,sha256=ewhpE9yzsqf5ED6kqsqek2YEgg96GBQOupxtVNhaXxI,6046
+evalscope/backend/vlm_eval_kit/custom_dataset.py,sha256=Yz2A5kB1E8DYBnjuVCA6TTPtLjhg8vYKeJTh6FU_Ecw,1645
 evalscope/benchmarks/__init__.py,sha256=6TKP35wfKf7R_h870fsEtcIlIAgomKOcukNL9M-5I1Y,162
 evalscope/benchmarks/benchmark.py,sha256=EmwYyFdrAHBGMkSbsMZQOR_62Q0CSKl8zeLlr7xvJdQ,2159
 evalscope/benchmarks/data_adapter.py,sha256=eVQvOQYQOQbIl8UlvOEUqRThL3FP3aUD6DSlqF1bqO0,10395
@@ -91,7 +122,7 @@ evalscope/cli/cli.py,sha256=uZ-qC8WBsLd5-Hn94d43sSGg0UC_12RebSD4ToKjypg,844
 evalscope/cli/start_perf.py,sha256=TL6bMXYl3ln-tfs5uBmzb9x94uxz6f3PBFIt1l7g3VA,994
 evalscope/cli/start_server.py,sha256=ATGLP2TE0aImJNicpehdzBuFlNb50F7KhyL4A_ZSoGU,3885
 evalscope/evaluator/__init__.py,sha256=S6MU1O_iiNAaKxNIhO9MEmdW-BSNf_YH2l6NQ9lxVNo,103
-evalscope/evaluator/evaluator.py,sha256=gB408byOpu269Psh6MjYC9-a_uv9GvThoT7t07Oqh6w,30712
+evalscope/evaluator/evaluator.py,sha256=eSCgPPDGfIJfKu0cthhbDLFm1xMhj_869iT3ngcQkPc,30817
 evalscope/evaluator/rating_eval.py,sha256=cJbkyXIuwFUZoe7ZJZM6eUskNd9zlORgndckuon2OQ8,5768
 evalscope/evaluator/reviewer/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/evaluator/reviewer/auto_reviewer.py,sha256=JycPYti9h1j_8DRcu_rc5U0wkEASHYg-XBqrUUoiO-Q,17054
@@ -109,7 +140,7 @@ evalscope/models/model_adapter.py,sha256=Cgs68ajRwTETEo1eU-OhFiFGuSx4eS1p7-JT3jO
 evalscope/models/openai_model.py,sha256=PoQS1FIiWIxp1xBJPV7Bq81LFD9FIT3vAHUvNa22DCc,3452
 evalscope/models/template.py,sha256=Yk7-QnvjiLD0zchSZcaDSLmpW8onIeFpngSwtUOYVPk,56035
 evalscope/models/api/__init__.py,sha256=0c75K78O1KaV02BqqtEp-hhtSSClXLawb8E0c2iqN_A,105
-evalscope/models/api/openai_api.py,sha256=o-FVJFSvfk5mFJm4egXcKfR5ya1fduo5b-uqTkeRu9A,7871
+evalscope/models/api/openai_api.py,sha256=uBicJPaFLOhIrB5PKI8FE-SItb7v-fuDwBgkgns3CY0,7883
 evalscope/models/custom/__init__.py,sha256=K4Ewo7Qrs73-jBuPq4ffxd8hMnttKhic-Zj0amH3wiU,103
 evalscope/models/custom/custom_model.py,sha256=2ivxfGQs5V5HDnQEhTBi5v8KNBxJDbzPVJdNOGo3iSg,1566
 evalscope/perf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -119,8 +150,8 @@ evalscope/perf/custom_api.py,sha256=H2IgM-LMjqXxVhbrtkXuiREb-p14zwMmllgl26a-jgw,
 evalscope/perf/dashscope_api.py,sha256=_XUF3czkYdPdVgtP7nqzRxROKxlqDjWs4DQnTyocNvM,3410
 evalscope/perf/dataset_plugin_base.py,sha256=6veUTyZ38W1Iig65vxNV9SfmqrsR8ID_UHgNiUO9Bv4,1814
 evalscope/perf/how_to_analysis_result.py,sha256=UVd_aYJ_7N5hl_wK9oIZig1vSwfgzodxW7XC6IWqbdg,1044
-evalscope/perf/http_client.py,sha256=WYHuGY_BCeeh8vHi1fm9zrAndOKpVQp4h21j1kKnM64,34535
-evalscope/perf/openai_api.py,sha256=XrH6jg8VlO9Wu0vGwZna_bHq65XMAlCfCEyqMjs8w1c,5970
+evalscope/perf/http_client.py,sha256=4ppaZAIwrajJ9nzdgdwc3EdjmGSJz1_dg7Q6wQYELgw,34537
+evalscope/perf/openai_api.py,sha256=rJSGlXtnHgMNYcgO0bJQCsSLhKChUxklTk4cI63YTMQ,6066
 evalscope/perf/plugin_registry.py,sha256=D2MG2AXDBScjuKxB4g_Hg026pSRO752dBimonYtaAzM,782
 evalscope/perf/query_parameters.py,sha256=HfGRZJSzRMVfPezWTvbWhYeprCetGNPX_M_paoDtuOY,1346
 evalscope/perf/server_sent_event.py,sha256=s2UqUr1qAMWzBG1XWCFxhulyztd6FM0tGqVvPC8jD5o,1153
@@ -169,12 +200,12 @@ evalscope/tools/rewrite_eval_results.py,sha256=ZVi2hVjiTOmR_O5IaLv6qnQNpMz6FnDb9
 evalscope/utils/__init__.py,sha256=6RjACRYUSpGj6fkZ7NzYpl0lFppQCp9KVn5ktZe626s,128
 evalscope/utils/arena_utils.py,sha256=RMkymUv9Cxs37arUntzgDY5P0Dand2jGpsb7uy6wZmg,7670
 evalscope/utils/completion_parsers.py,sha256=61l8CTh1VxHgRoMDhtznpAhuJp47MssGgS-LdEe_h80,2997
-evalscope/utils/logger.py,sha256=Ycd0W17Z_oiByPuPX3_umNrOCHjT9O_e_Kws7ZWUSvU,1855
+evalscope/utils/logger.py,sha256=cf3U400Mx1speMMNXorjwEE8noDz5Mbd-9PNgaulGeY,3013
 evalscope/utils/task_cfg_parser.py,sha256=LiNQ2X8lbZU0cODpaY_PbKyUhNoxZIC495UsLJigX64,138
-evalscope/utils/task_utils.py,sha256=Mv_u_f4Z91zcUeko6acZCmnOAPRfk61kf_dliLzG5Yk,459
+evalscope/utils/task_utils.py,sha256=IMtBSBUp3H95Ko0vn8Q55Wmz2SFZXSfjVy49tyomL_g,537
 evalscope/utils/utils.py,sha256=zHo9hfxGBUVKE2xNMR7lDoEvfRnk4V4946DEfXQhlq4,20509
-evalscope-0.5.5rc1.dist-info/METADATA,sha256=yKE-108cG8WZFEHoDyY2FoNBcFIf4BgHkwTOnNhEc7w,20708
-evalscope-0.5.5rc1.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-evalscope-0.5.5rc1.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
-evalscope-0.5.5rc1.dist-info/top_level.txt,sha256=jNR-HMn3TR8Atolq7_4rW8IWVX6GhvYV5_1Y_KbJKlY,10
-evalscope-0.5.5rc1.dist-info/RECORD,,
+evalscope-0.6.0rc0.dist-info/METADATA,sha256=w2k8y1h3gVVNAI7Ey-mc4RWsaSjNBlokuu0hw4e-3aI,21242
+evalscope-0.6.0rc0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+evalscope-0.6.0rc0.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
+evalscope-0.6.0rc0.dist-info/top_level.txt,sha256=jNR-HMn3TR8Atolq7_4rW8IWVX6GhvYV5_1Y_KbJKlY,10
+evalscope-0.6.0rc0.dist-info/RECORD,,