feat: support Reader classes

Author: ChenZiHong-Gavin

README.md

@@ -100,7 +100,7 @@ For any questions, please check [FAQ](https://github.com/open-sciencelab/GraphGe
 ### Run Gradio Demo
 
    ```bash
-   python -m webui.app.py
+   python -m webui.app
    ```
 
 ![ui](https://github.com/user-attachments/assets/3024e9bc-5d45-45f8-a4e6-b57bd2350d84)
@@ -148,7 +148,7 @@ For any questions, please check [FAQ](https://github.com/open-sciencelab/GraphGe
     ```yaml
       # configs/cot_config.yaml
       input_data_type: raw
-      input_file: resources/input_examples/raw_demo.jsonl
+      input_file: resources/input_examples/jsonl_demo.jsonl
       output_data_type: cot
       tokenizer: cl100k_base
       # additional settings...

README_ZH.md

@@ -99,7 +99,7 @@ GraphGen 首先根据源文本构建细粒度的知识图谱，然后利用期
 ### 运行 Gradio 演示
 
    ```bash
-   python -m webui.app.py
+   python -m webui.app
    ```
 
 ![ui](https://github.com/user-attachments/assets/3024e9bc-5d45-45f8-a4e6-b57bd2350d84)
@@ -147,7 +147,7 @@ GraphGen 首先根据源文本构建细粒度的知识图谱，然后利用期
     ```yaml
       # configs/cot_config.yaml
       input_data_type: raw
-      input_file: resources/input_examples/raw_demo.jsonl
+      input_file: resources/input_examples/jsonl_demo.jsonl
       output_data_type: cot
       tokenizer: cl100k_base
       # 其他设置...

baselines/EntiGraph/entigraph.py

@@ -232,7 +232,7 @@ async def generate_qa_sft(content):
     parser.add_argument(
         "--input_file",
         help="Raw context jsonl path.",
-        default="resources/input_examples/chunked_demo.json",
+        default="resources/input_examples/json_demo.json",
         type=str,
     )
     parser.add_argument(

baselines/Genie/genie.py

@@ -100,7 +100,7 @@ async def process_chunk(content: str):
     parser.add_argument(
         "--input_file",
         help="Raw context jsonl path.",
-        default="resources/input_examples/chunked_demo.json",
+        default="resources/input_examples/json_demo.json",
         type=str,
     )
     parser.add_argument(

baselines/LongForm/longform.py

@@ -67,7 +67,7 @@ async def process_chunk(content: str):
     parser.add_argument(
         "--input_file",
         help="Raw context jsonl path.",
-        default="resources/input_examples/chunked_demo.json",
+        default="resources/input_examples/json_demo.json",
         type=str,
     )
     parser.add_argument(

baselines/SELF-QA/self-qa.py

@@ -134,7 +134,7 @@ async def process_chunk(content: str):
     parser.add_argument(
         "--input_file",
         help="Raw context jsonl path.",
-        default="resources/input_examples/chunked_demo.json",
+        default="resources/input_examples/json_demo.json",
         type=str,
     )
     parser.add_argument(

baselines/Wrap/wrap.py

@@ -87,7 +87,7 @@ async def process_chunk(content: str):
     parser.add_argument(
         "--input_file",
         help="Raw context jsonl path.",
-        default="resources/input_examples/chunked_demo.json",
+        default="resources/input_examples/json_demo.json",
         type=str,
     )
     parser.add_argument(

graphgen/version.py graphgen/_version.pygraphgen/version.py renamed to graphgen/_version.py

@@ -1,7 +1,6 @@
-
 from typing import Tuple
 
-__version__ = '20250416'
+__version__ = "20250416"
 short_version = __version__
 
 
@@ -15,13 +14,13 @@ def parse_version_info(version_str: str) -> Tuple:
         tuple: A sequence of integer and string represents version.
     """
     _version_info = []
-    for x in version_str.split('.'):
+    for x in version_str.split("."):
         if x.isdigit():
             _version_info.append(int(x))
-        elif x.find('rc') != -1:
-            patch_version = x.split('rc')
+        elif x.find("rc") != -1:
+            patch_version = x.split("rc")
             _version_info.append(int(patch_version[0]))
-            _version_info.append(f'rc{patch_version[1]}')
+            _version_info.append(f"rc{patch_version[1]}")
     return tuple(_version_info)
 
 

graphgen/models/embed/__init__.py graphgen/bases/__init__.pygraphgen/models/embed/__init__.py renamed to graphgen/bases/__init__.py

@@ -0,0 +1,20 @@
+from abc import ABC, abstractmethod
+from typing import Any, Dict, List
+
+
+class BaseReader(ABC):
+    """
+    Abstract base class for reading and processing data.
+    """
+
+    def __init__(self, text_column: str = "content"):
+        self.text_column = text_column
+
+    @abstractmethod
+    def read(self, file_path: str) -> List[Dict[str, Any]]:
+        """
+        Read data from the specified file path.
+
+        :param file_path: Path to the input file.
+        :return: List of dictionaries containing the data.
+        """