feat: add llm core use and example.

README.md

@@ -51,7 +51,40 @@ pip install dingo-python
 
 ## Example Use Cases
 
-### 1. Evaluate Local Text File (Plaintext)
+### 1. Using Evaluate Core
+
+```python
+from dingo.config.config import DynamicLLMConfig
+from dingo.io.input.MetaData import MetaData
+from dingo.model.llm.detect_text_quality_detail import DetectTextQualityDetail
+from dingo.model.prompt.prompt_common import PromptRepeat
+from dingo.model.rule.rule_common import RuleEnterAndSpace
+
+def llm():
+    DetectTextQualityDetail.prompt = PromptRepeat()
+    DetectTextQualityDetail.dynamic_config = DynamicLLMConfig(
+        key='',
+        api_url='',
+        # model='',
+    )
+    res = DetectTextQualityDetail.call_api(MetaData(
+        data_id='123',
+        prompt="hello, introduce the world",
+        content="Hello! The world is a vast and diverse place, full of wonders, cultures, and incredible natural beauty."
+    ))
+    print(res)
+
+def rule():
+    data = MetaData(
+        data_id='123',
+        prompt="hello, introduce the world",
+        content="Hello! The world is a vast and diverse place, full of wonders, cultures, and incredible natural beauty."
+    )
+    res = RuleEnterAndSpace().eval(data)
+    print(res)
+```
+
+### 2. Evaluate Local Text File (Plaintext)
 
 ```python
 from dingo.io import InputArgs
@@ -72,7 +105,7 @@ result = executor.execute()
 print(result)
 ```
 
-### 2. Evaluate Hugging Face Dataset
+### 3. Evaluate Hugging Face Dataset
 
 ```python
 from dingo.io import InputArgs
@@ -92,7 +125,7 @@ result = executor.execute()
 print(result)
 ```
 
-### 3. Evaluate JSON/JSONL Format
+### 4. Evaluate JSON/JSONL Format
 
 ```python
 from dingo.io import InputArgs
@@ -114,7 +147,7 @@ result = executor.execute()
 print(result)
 ```
 
-### 4. Using LLM for Evaluation
+### 5. Using LLM for Evaluation
 
 ```python
 from dingo.io import InputArgs

README_zh-CN.md

@@ -40,7 +40,40 @@ pip install dingo-python
 
 ## 2. 使用示例
 
-### 2.1 评估本地文本文件（纯文本）
+### 2.1 使用评估核心方法
+
+```python
+from dingo.config.config import DynamicLLMConfig
+from dingo.io.input.MetaData import MetaData
+from dingo.model.llm.detect_text_quality_detail import DetectTextQualityDetail
+from dingo.model.prompt.prompt_common import PromptRepeat
+from dingo.model.rule.rule_common import RuleEnterAndSpace
+
+def llm():
+    DetectTextQualityDetail.prompt = PromptRepeat()
+    DetectTextQualityDetail.dynamic_config = DynamicLLMConfig(
+        key='',
+        api_url='',
+        # model='',
+    )
+    res = DetectTextQualityDetail.call_api(MetaData(
+        data_id='123',
+        prompt="hello, introduce the world",
+        content="Hello! The world is a vast and diverse place, full of wonders, cultures, and incredible natural beauty."
+    ))
+    print(res)
+
+def rule():
+    data = MetaData(
+        data_id='123',
+        prompt="hello, introduce the world",
+        content="Hello! The world is a vast and diverse place, full of wonders, cultures, and incredible natural beauty."
+    )
+    res = RuleEnterAndSpace().eval(data)
+    print(res)
+```
+
+### 2.2 评估本地文本文件（纯文本）
 
 ```python
 from dingo.io import InputArgs
@@ -61,7 +94,7 @@ result = executor.execute()
 print(result)
 ```
 
-### 2.2 评估Hugging Face数据集
+### 2.3 评估Hugging Face数据集
 
 ```python
 from dingo.io import InputArgs
@@ -81,7 +114,7 @@ result = executor.execute()
 print(result)
 ```
 
-### 2.3 评估JSON/JSONL格式
+### 2.4 评估JSON/JSONL格式
 
 ```python
 from dingo.io import InputArgs
@@ -103,7 +136,7 @@ result = executor.execute()
 print(result)
 ```
 
-### 2.4 使用LLM进行评估
+### 2.5 使用LLM进行评估
 
 ```python
 from dingo.io import InputArgs

dingo/model/llm/detect_text_quality_detail.py

@@ -1,8 +1,12 @@
 import json
 
+from dingo.config.config import DynamicLLMConfig
+from dingo.io.input.MetaData import MetaData
 from dingo.model import Model
 from dingo.model.llm.base_openai import BaseOpenAI
 from dingo.model.modelres import ModelRes
+from dingo.model.prompt.base import BasePrompt
+from dingo.model.prompt.prompt_common import PromptRepeat
 from dingo.model.response.response_class import ResponseScoreTypeNameReason
 from dingo.utils import log
 from dingo.utils.exception import ConvertJsonError
@@ -38,3 +42,13 @@ def process_response(cls, response: str) -> ModelRes:
             result.reason = [response_model.reason]
 
         return result
+
+if __name__ == "__main__":
+    DetectTextQualityDetail.prompt = PromptRepeat()
+    DetectTextQualityDetail.dynamic_config = DynamicLLMConfig(
+        key='',
+        api_url='',
+        # model='',
+    )
+    res = DetectTextQualityDetail.call_api(MetaData(data_id='123', content="hello, introduce the world"))
+    print(res)

examples/core/score.py

@@ -0,0 +1,33 @@
+from dingo.config.config import DynamicLLMConfig
+from dingo.io.input.MetaData import MetaData
+from dingo.model.llm.detect_text_quality_detail import DetectTextQualityDetail
+from dingo.model.prompt.prompt_common import PromptRepeat
+from dingo.model.rule.rule_common import RuleEnterAndSpace
+
+
+def llm():
+    DetectTextQualityDetail.prompt = PromptRepeat()
+    DetectTextQualityDetail.dynamic_config = DynamicLLMConfig(
+        key='',
+        api_url='',
+        # model='',
+    )
+    res = DetectTextQualityDetail.call_api(MetaData(
+        data_id='123',
+        prompt="hello, introduce the world",
+        content="Hello! The world is a vast and diverse place, full of wonders, cultures, and incredible natural beauty."
+    ))
+    print(res)
+
+def rule():
+    data = MetaData(
+        data_id='123',
+        prompt="hello, introduce the world",
+        content="Hello! The world is a vast and diverse place, full of wonders, cultures, and incredible natural beauty."
+    )
+    res = RuleEnterAndSpace().eval(data)
+    print(res)
+
+if __name__ == "__main__":
+    llm()
+    rule()