update assets

assets/data/test_background.json

@@ -0,0 +1,2 @@
+{"background": "The application scope of large-scale language models such as GPT-4 and LLaMA has rapidly expanded, demonstrating powerful capabilities in natural language processing and multimodal tasks. However, as the size and complexity of the models increase, understanding how they make decisions becomes increasingly difficult. Challenge: 1 The complexity of model interpretation: The billions of parameters and nonlinear decision paths within large-scale language models make it very difficult to track and interpret specific outputs. The existing interpretation methods usually only provide a local perspective and are difficult to systematize. 2. Transparency and Fairness: In specific scenarios, models may exhibit biased or discriminatory behavior. Ensuring the transparency of these models, reducing bias, and providing credible explanations is one of the current challenges."}
+{"background": "Multimodal learning is committed to integrating multiple information sources such as text, images, audio, and video to create more powerful and universal AI models. The research on unified representation aims to find representation methods that can generalize across modalities. Challenge: 1 Modal alignment: There is heterogeneity between different modalities, and how to achieve semantic alignment of these modalities to ensure that the model can comprehensively understand different types of data is a core challenge. 2. Data sparsity and imbalance: There is usually an imbalance in the amount of data in different modalities, such as video and audio data being relatively scarce, while text data is relatively abundant. How to effectively utilize and fuse these modalities to avoid overfitting or underfitting remains a research difficulty.", "cue_words": ["cross-modal embedding", "dat augmentation", "modality-aware fusion", "heterogeneous data integration"]}

assets/data/user_agents.txt

@@ -0,0 +1,36 @@
+Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50
+Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50
+Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0
+Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko
+Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)
+Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)
+Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)
+Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)
+Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1
+Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1
+Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11
+Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11
+Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11
+Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)
+Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)
+Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)
+Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)
+Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)
+Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)
+Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)
+Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)
+Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5
+Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5
+Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5
+Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1
+MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1
+Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10
+Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13
+Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+
+Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0
+Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124
+Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)
+UCWEB7.0.2.37/28/999
+NOKIA5700/ UCWEB7.0.2.37/28/999
+Openwave/ UCWEB7.0.2.37/28/999
+Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999

prompt/summarizing.xml

@@ -1,43 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?>
-<!DOCTYPE body [
-  <!ENTITY warning "Warning: Something bad happened... please refresh and try again.">
-]>
-<body>
-<query rank="0">
-<title>User Message</title>
-<text>
-Task Description:
-
-You are provided with the title, abstract, and introduction of a research paper. Your task is to generate a concise summary of what kind of problem does this paper aim to solve and what methods are proposed to address it. The summary should follow this format:
-The problem of [problem] can be addressed by [main idea/approach].
-
-Instructions:
-
-Title: Read the title to understand the general topic of the paper.
-Abstract: Read the abstract to get a concise summary of the research, including the problem addressed, the methods used, and the main findings.
-Introduction: Read the introduction to gain a deeper understanding of the background, significance, and specific problem the paper addresses, as well as the proposed approach or solution.
-Based on the provided information, generate a single sentence that captures the essence of the paper, following the format specified above.
-
-Your Turn:
-
-Given the following paper information:
-Title: {title}
-Abstract: {abstract}
-Introduction: {introduction}
-
-Output:
-The problem of [problem] can be addressed by [main idea/approach].
-</text>
-</query>
-<query rank="1">
-<title>User Message</title>
-<text>
-Please read the title, abstract, and introduction of the paper again, as well as the summary you provided. Complete the following two tasks:
-1.Briefly provide the two most critical motivations behind proposing these methods to address the problems. 
-2.Briefly provide the three most critical or innovative details of the paper that were not mentioned in your summary (It's best if these details are the new methods or techniques adopted in this paper).
-
-Output:
-Motivations:1.[motivation1]. 2.[motivation2]. Details:1.[detail1]. 2.[detail2]. 3.[detail3].
-</text>
-</query>
-</body>

src/config/__init__.py

@@ -0,0 +1,22 @@
+r"""_summary_
+-*- coding: utf-8 -*-
+
+Module : config
+
+File Name : __init__.py
+
+Description : About config.
+    for example:
+    ```
+    from config import ConfigReader
+    
+    config = ConfigReader.load(f, **kwargs)
+    ```
+
+Creation Date : 2024-10-30
+
+Author : Frank Kang([email protected])
+"""
+from .reader import ConfigReader
+
+__all__ = ['ConfigReader']

configs/config.py → src/config/reader.py

@@ -1,13 +1,13 @@
 r"""_summary_
 -*- coding: utf-8 -*-
 
-Module : configs.config
+Module : configs.reader
 
-File Name : config.py
+File Name : reader.py
 
 Description : Load the config file, which supports referencing other configuration files. If a circular reference occurs, an exception will be thrown
-   
-Creation Date : 2024-08-18
+
+Creation Date : 2024-07-13
 
 Author : Frank Kang([email protected])
 """
@@ -57,7 +57,10 @@ def update_config_with_api_aliases(config, llms_api, sum_api, gen_api):
     gen_api_found = check_api_alias(config, gen_api)
     if gen_api_found is None:
         raise KeyError('{} cannot match any llms api in config'.format(gen_api))
-    config.used_llms_apis = {'summarization': sum_api_found, 'generation': gen_api_found}
+    config.used_llms_apis = {
+        'summarization': sum_api_found,
+        'generation': gen_api_found
+        }
 
 
 class ConfigReader:

{configs → src/config}/utils.py

@@ -1,9 +1,19 @@
 #!/usr/bin/env python
-# coding: utf-8
-# Author: Frank Kang
-# Data: 13 July 2024
+r"""_summary_
+-*- coding: utf-8 -*-
+
+Module : configs.utils
+
+File Name : utils.py
+
+Description : utils about path
+
+Creation Date : 2024-07-13
+
+Author : Frank Kang([email protected])
+"""
 import os
-ROOT = os.path.dirname(os.path.dirname(__file__))
+ROOT = os.path.dirname(os.path.dirname(os.path.dirname(__file__)))
 
 
 def get_dir(config_dir):

prompt/prompt_reader.py → src/prompt/reader.py

@@ -1,8 +1,17 @@
 #!/usr/bin/env python
-# coding: utf-8
-# Author: Frank Kang
-# Data: 16 July 2024
+r"""_summary_
+-*- coding: utf-8 -*-
 
+Module : prompt.reader
+
+File Name : reader.py
+
+Description : Read prompt template
+
+Creation Date : 2024-07-16
+
+Author : Frank Kang([email protected])
+"""
 import xml.etree.ElementTree as ET
 from xml.etree.ElementTree import Element
 

src/utils/header.py

@@ -1,11 +1,20 @@
-import sys
-import os
+r"""_summary_
+-*- coding: utf-8 -*-
 
-sys.path.append(
-    os.path.dirname(os.path.dirname(os.path.dirname(os.path.realpath(__file__))))
-)
-from configs.utils import get_dir
-from configs.config import ConfigReader
-from prompt.prompt_reader import Prompt, AssistantCreateQuery, MessageQuery
+Module : utils.header
 
-__all__ = ["get_dir", "ConfigReader", "Prompt", "AssistantCreateQuery", "MessageQuery"]
+File Name : header.py
+
+Description : import some modules from top-level package
+
+Creation Date : 2024-07-16
+
+Author : Frank Kang([email protected])
+"""
+from config.utils import get_dir
+from config import ConfigReader
+from prompt.reader import Prompt, AssistantCreateQuery, MessageQuery
+
+__all__ = [
+    "get_dir", "ConfigReader", "Prompt", "AssistantCreateQuery", "MessageQuery"
+]