flashrag-dev 0.1.4.dev20250111__tar.gz → 0.1.4.dev20250113__tar.gz

{flashrag_dev-0.1.4.dev20250111 → flashrag_dev-0.1.4.dev20250113}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: flashrag_dev
-Version: 0.1.4.dev20250111
+Version: 0.1.4.dev20250113
 Summary: A library for efficient Retrieval-Augmented Generation research
 Home-page: https://github.com/RUC-NLPIR/FlashRAG
 Author: Jiajie Jin, Yutao Zhu, Chenghao Zhang, Xinyu Yang, Zhicheng Dou
@@ -32,19 +32,24 @@ License-File: LICENSE
 <a href="#sparkles-features">Features</a> |
 <a href="#rocket-quick-start">Quick-Start</a> |
 <a href="#gear-components"> Components</a> |
+<a href="#art-flashrag-ui"> FlashRAG-UI</a> |
 <a href="#robot-supporting-methods"> Supporting Methods</a> |
 <a href="#notebook-supporting-datasets--document-corpus"> Supporting Datasets</a> |
 <a href="#raised_hands-additional-faqs"> FAQs</a>
 </p>
 
 </h4>
-FlashRAG is a Python toolkit for the reproduction and development of Retrieval Augmented Generation (RAG) research. Our toolkit includes 36 pre-processed benchmark RAG datasets and 15 state-of-the-art RAG algorithms.
+
+
+FlashRAG is a Python toolkit for the reproduction and development of Retrieval Augmented Generation (RAG) research. Our toolkit includes 36 pre-processed benchmark RAG datasets and 16 state-of-the-art RAG algorithms.
 
 <p align="center">
 <img src="asset/framework.jpg">
 </p>
 
-With FlashRAG and provided resources, you can effortlessly reproduce existing SOTA works in the RAG domain or implement your custom RAG processes and components.
+With FlashRAG and provided resources, you can effortlessly reproduce existing SOTA works in the RAG domain or implement your custom RAG processes and components. Besides, we provide an easy-to-use UI:
+
+https://github.com/user-attachments/assets/8ca00873-5df2-48a7-b853-89e7b18bc6e9
 
 <p>
 <a href="https://trendshift.io/repositories/10454" target="_blank"><img src="https://trendshift.io/api/badge/repositories/10454" alt="RUC-NLPIR%2FFlashRAG | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
@@ -57,6 +62,7 @@ With FlashRAG and provided resources, you can effortlessly reproduce existing SO
 - [Installation](#wrench-installation)
 - [Quick Start](#rocket-quick-start)
 - [Components](#gear-components)
+- [FlashRAG-UI](#art-flashrag-ui)
 - [Supporting Methods](#robot-supporting-methods)
 - [Supporting Datasets & Document Corpus](#notebook-supporting-datasets--document-corpus)
 - [Additional FAQs](#raised_hands-additional-faqs)
@@ -69,7 +75,7 @@ With FlashRAG and provided resources, you can effortlessly reproduce existing SO
 
 - **Comprehensive Benchmark Datasets**: A collection of 36 pre-processed RAG benchmark datasets to test and validate RAG models' performances.
 
-- **Pre-implemented Advanced RAG Algorithms**: Features 15 advancing RAG algorithms with reported results, based on our framework. Easily reproducing results under different settings.
+- **Pre-implemented Advanced RAG Algorithms**: Features 16 advancing RAG algorithms with reported results, based on our framework. Easily reproducing results under different settings.
 
 - **Efficient Preprocessing Stage**: Simplifies the RAG workflow preparation by providing various scripts like corpus processing for retrieval, retrieval index building, and pre-retrieval of documents.
 
@@ -89,6 +95,9 @@ FlashRAG is still under development and there are many issues and room for impro
 - [ ] Enhance code adaptability and readability
 
 ## :page_with_curl: Changelog
+[25/01/12] Introduce <strong>FlashRAG-UI</strong>, an easy to use interface. You can easily and quickly configure and experience the supported RAG methods and evaluate them on the benchmarks.
+
+[25/01/11] We have added support for a new method [<u>RQRAG</u>](https://arxiv.org/abs/2404.00610) method, see it in [**reproduce_experiment**](docs/reproduce_experiment.md).
 
 [25/01/07] We have currently support the aggregation of multiple retrievers, see it in [**multi retriever usage**](https://github.com/RUC-NLPIR/FlashRAG/blob/main/docs/multi_retriever_usage.md).
 
@@ -100,15 +109,15 @@ FlashRAG is still under development and there are many issues and room for impro
 
 [24/09/24] We have released a version based on the MindSpore framework that supports Chinese hardware platforms. Please refer to [FlashRAG MindSpore](https://github.com/RUC-NLPIR/FlashRAG-MindSpore) for details.
 
+<details>
+<summary>Show more</summary>
+
 [24/09/18] Due to the complexity and limitations of installing Pyserini in certain environments, we have introduced a lightweight `BM25s` package as an alternative (faster and easier to use). The retriever based on Pyserini will be deprecated in future versions. To use retriever with `bm25s`, just set `bm25_backend` to `bm25s` in config.
 
 [24/09/09] We add support for a new method [<u>Adaptive-RAG</u>](https://aclanthology.org/2024.naacl-long.389.pdf), which can automatically select the RAG process to execute based on the type of query. See it result in [<u>result table</u>](#robot-supporting-methods).
 
 [24/08/02] We add support for a new method [<u>Spring</u>](https://arxiv.org/abs/2405.19670), significantly improve the performance of LLM by adding only a few token embeddings. See it result in [<u>result table</u>](#robot-supporting-methods).
 
-<details>
-<summary>Show more</summary>
-
 [24/07/17] Due to some unknown issues with HuggingFace, our original dataset link has been invalid. We have updated it. Please check the [new link](https://huggingface.co/datasets/RUC-NLPIR/FlashRAG_datasets/) if you encounter any problems.
 
 [24/07/06] We add support for a new method: [<u>Trace</u>](https://arxiv.org/abs/2406.11460), which refine text by constructing a knowledge graph. See it [<u>results</u>](#robot-supporting-methods) and [<u>details</u>](./docs/baseline_details.md).
@@ -182,9 +191,8 @@ From the official Faiss repository ([source](https://github.com/facebookresearch
 To build an index, you first need to save your corpus as a `jsonl` file with each line representing a document.
 
 ```jsonl
-{"id": "0", "contents": "content"}
-{"id": "1", "contents": "content"}
-...
+{"id": "0", "contents": "..."}
+{"id": "1", "contents": "..."}
 ```
 
 If you want to use Wikipedia as your corpus, you can refer to our documentation [Processing Wikipedia](./docs/process-wiki.md) to convert it into an indexable format.
@@ -492,6 +500,49 @@ In each category, we have implemented corresponding common pipelines. Some pipel
     </tbody>
 </table>
 
+## :art: FlashRAG-UI
+<p>With <strong>FlashRAG-UI</strong>, you can easily and quickly configure and experience the supported RAG methods through our meticulously designed visual interface, and evaluate these methods on benchmarks, making complex research work more efficient!</p>
+
+### :star2: Features
+- **One-Click Configuration Loading**
+  - You can load parameters and configuration files for various RAG methods through simple clicks, selections, and inputs.</li>
+  - Supports preview interface for intuitive parameter settings.</li>
+  - Provides save functionality to easily store configurations for future use.</li>
+- **Quick Method Experience**
+  - Quickly load corpora and index files to explore the characteristics and application scenarios of various RAG methods.</li>
+  - Supports loading and switching different components and hyperparameters, seamlessly connecting different RAG Pipelines to quickly experience their performance and differences!</li>
+- **Efficient Benchmark Reproduction**
+  - Easily reproduce the built-in baseline methods and carefully collected benchmarks on FlashRAG-UI.</li>
+  - Use cutting-edge research tools directly without complex settings, providing a smooth experience for your research work!</li>
+  
+<details>
+<summary>Show more</summary>
+<table align="center">
+  <tr>
+    <td align="center">
+      <img src="./asset/demo_en1.jpg" alt="Image 1" width="505"/>
+    </td>
+    <td align="center">
+      <img src="./asset/demo_en2.jpg" alt="Image 2" width="505"/>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <img src="./asset/demo_en4.png" alt="Image 3" width="500"/>
+    </td>
+    <td align="center">
+      <img src="./asset/demo_en3.jpg" alt="Image 4" width="500"/>
+    </td>
+  </tr>
+</table>
+</details>
+
+#### Experience our meticulously designed FlashRAG-UI—both user-friendly and visually appealing:
+```bash
+cd webui
+python interface.py
+```
+
 ## :robot: Supporting Methods
 
 We have implemented 15 works with a consistent setting of:
@@ -525,6 +576,8 @@ It’s important to note that, to ensure consistency, we have utilized a uniform
 | [FLARE](https://arxiv.org/abs/2305.06983)                                                 | Loop        | 22.5    | 55.8          | 28.0          | 33.9       | 20.7       | 20.2      |                                                 |
 | [Iter-Retgen](https://arxiv.org/abs/2305.15294), [ITRG](https://arxiv.org/abs/2310.05149) | Loop        | 36.8    | 60.1          | 38.3          | 21.6       | 37.9       | 18.2      |                                                 |
 | [IRCoT](https://aclanthology.org/2023.acl-long.557.pdf)                                   | Loop        | 33.3    | 56.9          | 41.5          | 32.4       | 45.6       | 20.7      |                                                 |
+| [RQRAG](https://arxiv.org/abs/2404.00610)                                   | Loop        | 32.6    | 52.5          | 33.5          | 35.8       | 46.4       | 26.2      |  Use trained rqrag-llama2-7B                                               |
+
 
 ## :notebook: Supporting Datasets & Document Corpus
 
@@ -589,7 +642,7 @@ Below is the list of datasets along with the corresponding sample sizes:
 Our toolkit supports jsonl format for retrieval document collections, with the following structure:
 
 ```jsonl
-{"id":"0", "contents": "...."}
+{"id":"0", "contents": "..."}
 {"id":"1", "contents": "..."}
 ```
 

{flashrag_dev-0.1.4.dev20250111 → flashrag_dev-0.1.4.dev20250113}/README.md

@@ -15,19 +15,24 @@
 <a href="#sparkles-features">Features</a> |
 <a href="#rocket-quick-start">Quick-Start</a> |
 <a href="#gear-components"> Components</a> |
+<a href="#art-flashrag-ui"> FlashRAG-UI</a> |
 <a href="#robot-supporting-methods"> Supporting Methods</a> |
 <a href="#notebook-supporting-datasets--document-corpus"> Supporting Datasets</a> |
 <a href="#raised_hands-additional-faqs"> FAQs</a>
 </p>
 
 </h4>
-FlashRAG is a Python toolkit for the reproduction and development of Retrieval Augmented Generation (RAG) research. Our toolkit includes 36 pre-processed benchmark RAG datasets and 15 state-of-the-art RAG algorithms.
+
+
+FlashRAG is a Python toolkit for the reproduction and development of Retrieval Augmented Generation (RAG) research. Our toolkit includes 36 pre-processed benchmark RAG datasets and 16 state-of-the-art RAG algorithms.
 
 <p align="center">
 <img src="asset/framework.jpg">
 </p>
 
-With FlashRAG and provided resources, you can effortlessly reproduce existing SOTA works in the RAG domain or implement your custom RAG processes and components.
+With FlashRAG and provided resources, you can effortlessly reproduce existing SOTA works in the RAG domain or implement your custom RAG processes and components. Besides, we provide an easy-to-use UI:
+
+https://github.com/user-attachments/assets/8ca00873-5df2-48a7-b853-89e7b18bc6e9
 
 <p>
 <a href="https://trendshift.io/repositories/10454" target="_blank"><img src="https://trendshift.io/api/badge/repositories/10454" alt="RUC-NLPIR%2FFlashRAG | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
@@ -40,6 +45,7 @@ With FlashRAG and provided resources, you can effortlessly reproduce existing SO
 - [Installation](#wrench-installation)
 - [Quick Start](#rocket-quick-start)
 - [Components](#gear-components)
+- [FlashRAG-UI](#art-flashrag-ui)
 - [Supporting Methods](#robot-supporting-methods)
 - [Supporting Datasets & Document Corpus](#notebook-supporting-datasets--document-corpus)
 - [Additional FAQs](#raised_hands-additional-faqs)
@@ -52,7 +58,7 @@ With FlashRAG and provided resources, you can effortlessly reproduce existing SO
 
 - **Comprehensive Benchmark Datasets**: A collection of 36 pre-processed RAG benchmark datasets to test and validate RAG models' performances.
 
-- **Pre-implemented Advanced RAG Algorithms**: Features 15 advancing RAG algorithms with reported results, based on our framework. Easily reproducing results under different settings.
+- **Pre-implemented Advanced RAG Algorithms**: Features 16 advancing RAG algorithms with reported results, based on our framework. Easily reproducing results under different settings.
 
 - **Efficient Preprocessing Stage**: Simplifies the RAG workflow preparation by providing various scripts like corpus processing for retrieval, retrieval index building, and pre-retrieval of documents.
 
@@ -72,6 +78,9 @@ FlashRAG is still under development and there are many issues and room for impro
 - [ ] Enhance code adaptability and readability
 
 ## :page_with_curl: Changelog
+[25/01/12] Introduce <strong>FlashRAG-UI</strong>, an easy to use interface. You can easily and quickly configure and experience the supported RAG methods and evaluate them on the benchmarks.
+
+[25/01/11] We have added support for a new method [<u>RQRAG</u>](https://arxiv.org/abs/2404.00610) method, see it in [**reproduce_experiment**](docs/reproduce_experiment.md).
 
 [25/01/07] We have currently support the aggregation of multiple retrievers, see it in [**multi retriever usage**](https://github.com/RUC-NLPIR/FlashRAG/blob/main/docs/multi_retriever_usage.md).
 
@@ -83,15 +92,15 @@ FlashRAG is still under development and there are many issues and room for impro
 
 [24/09/24] We have released a version based on the MindSpore framework that supports Chinese hardware platforms. Please refer to [FlashRAG MindSpore](https://github.com/RUC-NLPIR/FlashRAG-MindSpore) for details.
 
+<details>
+<summary>Show more</summary>
+
 [24/09/18] Due to the complexity and limitations of installing Pyserini in certain environments, we have introduced a lightweight `BM25s` package as an alternative (faster and easier to use). The retriever based on Pyserini will be deprecated in future versions. To use retriever with `bm25s`, just set `bm25_backend` to `bm25s` in config.
 
 [24/09/09] We add support for a new method [<u>Adaptive-RAG</u>](https://aclanthology.org/2024.naacl-long.389.pdf), which can automatically select the RAG process to execute based on the type of query. See it result in [<u>result table</u>](#robot-supporting-methods).
 
 [24/08/02] We add support for a new method [<u>Spring</u>](https://arxiv.org/abs/2405.19670), significantly improve the performance of LLM by adding only a few token embeddings. See it result in [<u>result table</u>](#robot-supporting-methods).
 
-<details>
-<summary>Show more</summary>
-
 [24/07/17] Due to some unknown issues with HuggingFace, our original dataset link has been invalid. We have updated it. Please check the [new link](https://huggingface.co/datasets/RUC-NLPIR/FlashRAG_datasets/) if you encounter any problems.
 
 [24/07/06] We add support for a new method: [<u>Trace</u>](https://arxiv.org/abs/2406.11460), which refine text by constructing a knowledge graph. See it [<u>results</u>](#robot-supporting-methods) and [<u>details</u>](./docs/baseline_details.md).
@@ -165,9 +174,8 @@ From the official Faiss repository ([source](https://github.com/facebookresearch
 To build an index, you first need to save your corpus as a `jsonl` file with each line representing a document.
 
 ```jsonl
-{"id": "0", "contents": "content"}
-{"id": "1", "contents": "content"}
-...
+{"id": "0", "contents": "..."}
+{"id": "1", "contents": "..."}
 ```
 
 If you want to use Wikipedia as your corpus, you can refer to our documentation [Processing Wikipedia](./docs/process-wiki.md) to convert it into an indexable format.
@@ -475,6 +483,49 @@ In each category, we have implemented corresponding common pipelines. Some pipel
     </tbody>
 </table>
 
+## :art: FlashRAG-UI
+<p>With <strong>FlashRAG-UI</strong>, you can easily and quickly configure and experience the supported RAG methods through our meticulously designed visual interface, and evaluate these methods on benchmarks, making complex research work more efficient!</p>
+
+### :star2: Features
+- **One-Click Configuration Loading**
+  - You can load parameters and configuration files for various RAG methods through simple clicks, selections, and inputs.</li>
+  - Supports preview interface for intuitive parameter settings.</li>
+  - Provides save functionality to easily store configurations for future use.</li>
+- **Quick Method Experience**
+  - Quickly load corpora and index files to explore the characteristics and application scenarios of various RAG methods.</li>
+  - Supports loading and switching different components and hyperparameters, seamlessly connecting different RAG Pipelines to quickly experience their performance and differences!</li>
+- **Efficient Benchmark Reproduction**
+  - Easily reproduce the built-in baseline methods and carefully collected benchmarks on FlashRAG-UI.</li>
+  - Use cutting-edge research tools directly without complex settings, providing a smooth experience for your research work!</li>
+  
+<details>
+<summary>Show more</summary>
+<table align="center">
+  <tr>
+    <td align="center">
+      <img src="./asset/demo_en1.jpg" alt="Image 1" width="505"/>
+    </td>
+    <td align="center">
+      <img src="./asset/demo_en2.jpg" alt="Image 2" width="505"/>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <img src="./asset/demo_en4.png" alt="Image 3" width="500"/>
+    </td>
+    <td align="center">
+      <img src="./asset/demo_en3.jpg" alt="Image 4" width="500"/>
+    </td>
+  </tr>
+</table>
+</details>
+
+#### Experience our meticulously designed FlashRAG-UI—both user-friendly and visually appealing:
+```bash
+cd webui
+python interface.py
+```
+
 ## :robot: Supporting Methods
 
 We have implemented 15 works with a consistent setting of:
@@ -508,6 +559,8 @@ It’s important to note that, to ensure consistency, we have utilized a uniform
 | [FLARE](https://arxiv.org/abs/2305.06983)                                                 | Loop        | 22.5    | 55.8          | 28.0          | 33.9       | 20.7       | 20.2      |                                                 |
 | [Iter-Retgen](https://arxiv.org/abs/2305.15294), [ITRG](https://arxiv.org/abs/2310.05149) | Loop        | 36.8    | 60.1          | 38.3          | 21.6       | 37.9       | 18.2      |                                                 |
 | [IRCoT](https://aclanthology.org/2023.acl-long.557.pdf)                                   | Loop        | 33.3    | 56.9          | 41.5          | 32.4       | 45.6       | 20.7      |                                                 |
+| [RQRAG](https://arxiv.org/abs/2404.00610)                                   | Loop        | 32.6    | 52.5          | 33.5          | 35.8       | 46.4       | 26.2      |  Use trained rqrag-llama2-7B                                               |
+
 
 ## :notebook: Supporting Datasets & Document Corpus
 
@@ -572,7 +625,7 @@ Below is the list of datasets along with the corresponding sample sizes:
 Our toolkit supports jsonl format for retrieval document collections, with the following structure:
 
 ```jsonl
-{"id":"0", "contents": "...."}
+{"id":"0", "contents": "..."}
 {"id":"1", "contents": "..."}
 ```
 

{flashrag_dev-0.1.4.dev20250111 → flashrag_dev-0.1.4.dev20250113}/flashrag/refiner/refiner.py

@@ -73,7 +73,6 @@ class LLMLinguaRefiner(BaseRefiner):
         output = []
         for item in tqdm(dataset, desc="Refining process: "):
             question = item.question
-            retrieval_result = item.retrieval_result
             # TODO: suit more cases
             if self.input_prompt_flag:
                 input_prompt = item.prompt
@@ -88,6 +87,7 @@ class LLMLinguaRefiner(BaseRefiner):
                     **self.compress_config,
                 )
             else:
+                retrieval_result = item.retrieval_result
                 docs = self.format_reference(retrieval_result).split("\n")
                 docs = [i for i in docs if i != ""]
                 item_output = self.refiner.compress_prompt(

{flashrag_dev-0.1.4.dev20250111 → flashrag_dev-0.1.4.dev20250113}/flashrag/retriever/utils.py

@@ -5,6 +5,7 @@ from typing import Dict, Any, Union, List, Dict
 import numpy as np
 import datasets
 import re
+import langid
 from transformers import AutoTokenizer, AutoModel, AutoConfig
 
 def convert_numpy(obj: Union[Dict, list, np.ndarray, np.generic]) -> Any:
@@ -27,7 +28,14 @@ def judge_zh(input_str: str):
     assert isinstance(input_str, str), input_str
     if len(input_str) == 0:
         return False
-    return bool(re.search(r'[\u4e00-\u9fff]', input_str))
+    detect_result = langid.classify(input_str)
+    if detect_result[0] == 'zh':
+        return True
+    else:
+        return False
+    #return bool(re.search(r'[\u4e00-\u9fff]', input_str))
+
+
 def convert_numpy(obj: Union[Dict, list, np.ndarray, np.generic]) -> Any:
     """Recursively convert numpy objects in nested dictionaries or lists to native Python types."""
     if isinstance(obj, dict):

flashrag_dev-0.1.4.dev20250113/flashrag/version.py

@@ -0,0 +1 @@
+__version__ = "0.1.4dev20250113"

{flashrag_dev-0.1.4.dev20250111 → flashrag_dev-0.1.4.dev20250113}/flashrag_dev.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: flashrag-dev
-Version: 0.1.4.dev20250111
+Version: 0.1.4.dev20250113
 Summary: A library for efficient Retrieval-Augmented Generation research
 Home-page: https://github.com/RUC-NLPIR/FlashRAG
 Author: Jiajie Jin, Yutao Zhu, Chenghao Zhang, Xinyu Yang, Zhicheng Dou
@@ -32,19 +32,24 @@ License-File: LICENSE
 <a href="#sparkles-features">Features</a> |
 <a href="#rocket-quick-start">Quick-Start</a> |
 <a href="#gear-components"> Components</a> |
+<a href="#art-flashrag-ui"> FlashRAG-UI</a> |
 <a href="#robot-supporting-methods"> Supporting Methods</a> |
 <a href="#notebook-supporting-datasets--document-corpus"> Supporting Datasets</a> |
 <a href="#raised_hands-additional-faqs"> FAQs</a>
 </p>
 
 </h4>
-FlashRAG is a Python toolkit for the reproduction and development of Retrieval Augmented Generation (RAG) research. Our toolkit includes 36 pre-processed benchmark RAG datasets and 15 state-of-the-art RAG algorithms.
+
+
+FlashRAG is a Python toolkit for the reproduction and development of Retrieval Augmented Generation (RAG) research. Our toolkit includes 36 pre-processed benchmark RAG datasets and 16 state-of-the-art RAG algorithms.
 
 <p align="center">
 <img src="asset/framework.jpg">
 </p>
 
-With FlashRAG and provided resources, you can effortlessly reproduce existing SOTA works in the RAG domain or implement your custom RAG processes and components.
+With FlashRAG and provided resources, you can effortlessly reproduce existing SOTA works in the RAG domain or implement your custom RAG processes and components. Besides, we provide an easy-to-use UI:
+
+https://github.com/user-attachments/assets/8ca00873-5df2-48a7-b853-89e7b18bc6e9
 
 <p>
 <a href="https://trendshift.io/repositories/10454" target="_blank"><img src="https://trendshift.io/api/badge/repositories/10454" alt="RUC-NLPIR%2FFlashRAG | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
@@ -57,6 +62,7 @@ With FlashRAG and provided resources, you can effortlessly reproduce existing SO
 - [Installation](#wrench-installation)
 - [Quick Start](#rocket-quick-start)
 - [Components](#gear-components)
+- [FlashRAG-UI](#art-flashrag-ui)
 - [Supporting Methods](#robot-supporting-methods)
 - [Supporting Datasets & Document Corpus](#notebook-supporting-datasets--document-corpus)
 - [Additional FAQs](#raised_hands-additional-faqs)
@@ -69,7 +75,7 @@ With FlashRAG and provided resources, you can effortlessly reproduce existing SO
 
 - **Comprehensive Benchmark Datasets**: A collection of 36 pre-processed RAG benchmark datasets to test and validate RAG models' performances.
 
-- **Pre-implemented Advanced RAG Algorithms**: Features 15 advancing RAG algorithms with reported results, based on our framework. Easily reproducing results under different settings.
+- **Pre-implemented Advanced RAG Algorithms**: Features 16 advancing RAG algorithms with reported results, based on our framework. Easily reproducing results under different settings.
 
 - **Efficient Preprocessing Stage**: Simplifies the RAG workflow preparation by providing various scripts like corpus processing for retrieval, retrieval index building, and pre-retrieval of documents.
 
@@ -89,6 +95,9 @@ FlashRAG is still under development and there are many issues and room for impro
 - [ ] Enhance code adaptability and readability
 
 ## :page_with_curl: Changelog
+[25/01/12] Introduce <strong>FlashRAG-UI</strong>, an easy to use interface. You can easily and quickly configure and experience the supported RAG methods and evaluate them on the benchmarks.
+
+[25/01/11] We have added support for a new method [<u>RQRAG</u>](https://arxiv.org/abs/2404.00610) method, see it in [**reproduce_experiment**](docs/reproduce_experiment.md).
 
 [25/01/07] We have currently support the aggregation of multiple retrievers, see it in [**multi retriever usage**](https://github.com/RUC-NLPIR/FlashRAG/blob/main/docs/multi_retriever_usage.md).
 
@@ -100,15 +109,15 @@ FlashRAG is still under development and there are many issues and room for impro
 
 [24/09/24] We have released a version based on the MindSpore framework that supports Chinese hardware platforms. Please refer to [FlashRAG MindSpore](https://github.com/RUC-NLPIR/FlashRAG-MindSpore) for details.
 
+<details>
+<summary>Show more</summary>
+
 [24/09/18] Due to the complexity and limitations of installing Pyserini in certain environments, we have introduced a lightweight `BM25s` package as an alternative (faster and easier to use). The retriever based on Pyserini will be deprecated in future versions. To use retriever with `bm25s`, just set `bm25_backend` to `bm25s` in config.
 
 [24/09/09] We add support for a new method [<u>Adaptive-RAG</u>](https://aclanthology.org/2024.naacl-long.389.pdf), which can automatically select the RAG process to execute based on the type of query. See it result in [<u>result table</u>](#robot-supporting-methods).
 
 [24/08/02] We add support for a new method [<u>Spring</u>](https://arxiv.org/abs/2405.19670), significantly improve the performance of LLM by adding only a few token embeddings. See it result in [<u>result table</u>](#robot-supporting-methods).
 
-<details>
-<summary>Show more</summary>
-
 [24/07/17] Due to some unknown issues with HuggingFace, our original dataset link has been invalid. We have updated it. Please check the [new link](https://huggingface.co/datasets/RUC-NLPIR/FlashRAG_datasets/) if you encounter any problems.
 
 [24/07/06] We add support for a new method: [<u>Trace</u>](https://arxiv.org/abs/2406.11460), which refine text by constructing a knowledge graph. See it [<u>results</u>](#robot-supporting-methods) and [<u>details</u>](./docs/baseline_details.md).
@@ -182,9 +191,8 @@ From the official Faiss repository ([source](https://github.com/facebookresearch
 To build an index, you first need to save your corpus as a `jsonl` file with each line representing a document.
 
 ```jsonl
-{"id": "0", "contents": "content"}
-{"id": "1", "contents": "content"}
-...
+{"id": "0", "contents": "..."}
+{"id": "1", "contents": "..."}
 ```
 
 If you want to use Wikipedia as your corpus, you can refer to our documentation [Processing Wikipedia](./docs/process-wiki.md) to convert it into an indexable format.
@@ -492,6 +500,49 @@ In each category, we have implemented corresponding common pipelines. Some pipel
     </tbody>
 </table>
 
+## :art: FlashRAG-UI
+<p>With <strong>FlashRAG-UI</strong>, you can easily and quickly configure and experience the supported RAG methods through our meticulously designed visual interface, and evaluate these methods on benchmarks, making complex research work more efficient!</p>
+
+### :star2: Features
+- **One-Click Configuration Loading**
+  - You can load parameters and configuration files for various RAG methods through simple clicks, selections, and inputs.</li>
+  - Supports preview interface for intuitive parameter settings.</li>
+  - Provides save functionality to easily store configurations for future use.</li>
+- **Quick Method Experience**
+  - Quickly load corpora and index files to explore the characteristics and application scenarios of various RAG methods.</li>
+  - Supports loading and switching different components and hyperparameters, seamlessly connecting different RAG Pipelines to quickly experience their performance and differences!</li>
+- **Efficient Benchmark Reproduction**
+  - Easily reproduce the built-in baseline methods and carefully collected benchmarks on FlashRAG-UI.</li>
+  - Use cutting-edge research tools directly without complex settings, providing a smooth experience for your research work!</li>
+  
+<details>
+<summary>Show more</summary>
+<table align="center">
+  <tr>
+    <td align="center">
+      <img src="./asset/demo_en1.jpg" alt="Image 1" width="505"/>
+    </td>
+    <td align="center">
+      <img src="./asset/demo_en2.jpg" alt="Image 2" width="505"/>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <img src="./asset/demo_en4.png" alt="Image 3" width="500"/>
+    </td>
+    <td align="center">
+      <img src="./asset/demo_en3.jpg" alt="Image 4" width="500"/>
+    </td>
+  </tr>
+</table>
+</details>
+
+#### Experience our meticulously designed FlashRAG-UI—both user-friendly and visually appealing:
+```bash
+cd webui
+python interface.py
+```
+
 ## :robot: Supporting Methods
 
 We have implemented 15 works with a consistent setting of:
@@ -525,6 +576,8 @@ It’s important to note that, to ensure consistency, we have utilized a uniform
 | [FLARE](https://arxiv.org/abs/2305.06983)                                                 | Loop        | 22.5    | 55.8          | 28.0          | 33.9       | 20.7       | 20.2      |                                                 |
 | [Iter-Retgen](https://arxiv.org/abs/2305.15294), [ITRG](https://arxiv.org/abs/2310.05149) | Loop        | 36.8    | 60.1          | 38.3          | 21.6       | 37.9       | 18.2      |                                                 |
 | [IRCoT](https://aclanthology.org/2023.acl-long.557.pdf)                                   | Loop        | 33.3    | 56.9          | 41.5          | 32.4       | 45.6       | 20.7      |                                                 |
+| [RQRAG](https://arxiv.org/abs/2404.00610)                                   | Loop        | 32.6    | 52.5          | 33.5          | 35.8       | 46.4       | 26.2      |  Use trained rqrag-llama2-7B                                               |
+
 
 ## :notebook: Supporting Datasets & Document Corpus
 
@@ -589,7 +642,7 @@ Below is the list of datasets along with the corresponding sample sizes:
 Our toolkit supports jsonl format for retrieval document collections, with the following structure:
 
 ```jsonl
-{"id":"0", "contents": "...."}
+{"id":"0", "contents": "..."}
 {"id":"1", "contents": "..."}
 ```
 

{flashrag_dev-0.1.4.dev20250111 → flashrag_dev-0.1.4.dev20250113}/flashrag_dev.egg-info/requires.txt

@@ -2,6 +2,7 @@ datasets
 base58
 nltk
 numpy
+langid
 openai
 peft
 PyYAML
@@ -16,12 +17,14 @@ bm25s[core]==0.2.0
 fschat
 streamlit
 chonkie>=0.4.0
+gradio==5.9.1
 
 [core]
 datasets
 base58
 nltk
 numpy
+langid
 openai
 peft
 PyYAML
@@ -36,12 +39,14 @@ bm25s[core]==0.2.0
 fschat
 streamlit
 chonkie>=0.4.0
+gradio==5.9.1
 
 [full]
 datasets
 base58
 nltk
 numpy
+langid
 openai
 peft
 PyYAML
@@ -56,6 +61,7 @@ bm25s[core]==0.2.0
 fschat
 streamlit
 chonkie>=0.4.0
+gradio==5.9.1
 pyserini
 sentence-transformers>=3.0.1
 vllm==0.5.5

flashrag_dev-0.1.4.dev20250111/flashrag/version.py

@@ -1 +0,0 @@
-__version__ = "0.1.4dev20250111"