feat: enhance dataset file fetching with improved pagination and document loading support (#156)

runtime/datamate-python/app/common/__init__.py

@@ -0,0 +1,3 @@
+"""
+公共模块
+"""

runtime/datamate-python/app/common/document_loaders.py

@@ -0,0 +1,93 @@
+from typing import List, Union, Optional
+from pathlib import Path
+
+from langchain_core.documents import Document
+from langchain_community.document_loaders import (
+    TextLoader,
+    JSONLoader,
+    CSVLoader,
+    UnstructuredMarkdownLoader,
+    PyPDFLoader,
+    Docx2txtLoader
+)
+
+from app.core.logging import get_logger
+
+log = get_logger(__name__)
+
+class UniversalDocLoader:
+    """
+    通用泛文本文档加载类
+    支持格式：TXT/JSON/CSV/Markdown/Word(.docx)/PPT(.pptx)/PDF
+    """
+    # 格式-加载器映射（轻量优先）
+    SUPPORTED_FORMATS = {
+        # 纯文本类
+        ".txt": TextLoader,
+        ".json": JSONLoader,
+        ".csv": CSVLoader,
+        ".md": UnstructuredMarkdownLoader,
+        # 办公文档类
+        ".docx": Docx2txtLoader,
+        ".doc": Docx2txtLoader,
+        # PDF 类
+        ".pdf": PyPDFLoader
+    }
+
+    def __init__(self, file_path: Union[str, Path]):
+        self.file_path = Path(file_path).resolve()
+        self.file_suffix = self.file_path.suffix.lower()
+        log.info(f"初始化文档加载器: {self.file_path} (格式: {self.file_suffix})")
+        self._validate_file()
+
+    def _validate_file(self) -> None:
+        """验证文件存在性和格式支持性"""
+        if not self.file_path.exists():
+            raise FileNotFoundError(f"文件不存在: {self.file_path}")
+        if self.file_suffix not in self.SUPPORTED_FORMATS:
+            raise ValueError(
+                f"不支持的格式: {self.file_suffix} | 支持格式: {list(self.SUPPORTED_FORMATS.keys())}"
+            )
+
+    def load(
+        self,
+        file_format: Optional[str] = None,
+        **loader_kwargs
+    ) -> List[Document]:
+        """
+        加载文档并返回 LangChain Document 列表
+        :param file_format: 手动指定格式（如 ".pdf"），默认自动识别
+        :param loader_kwargs: 传递给具体加载器的参数（如 JSONLoader 的 jq_schema）
+        :return: List[Document]
+        """
+        # 确定目标格式
+        target_format = file_format.lower() if file_format else self.file_suffix
+        loader_cls = self.SUPPORTED_FORMATS[target_format]
+
+        # 加载器默认参数优化
+        loader_kwargs = self._set_default_kwargs(loader_cls, loader_kwargs)
+
+        # 初始化并加载
+        loader = loader_cls(str(self.file_path), **loader_kwargs)
+        return loader.load()
+
+    @staticmethod
+    def _set_default_kwargs(loader_cls, kwargs: dict) -> dict:
+        """为不同加载器设置默认参数，简化调用"""
+        if loader_cls == JSONLoader and "jq_schema" not in kwargs:
+            kwargs.setdefault("jq_schema", ".")
+            kwargs.setdefault("text_content", False)
+        if loader_cls == CSVLoader and "csv_args" not in kwargs:
+            kwargs["csv_args"] = {"delimiter": ","}
+        return kwargs
+
+
+# 文档加载器便捷函数
+def load_documents(
+    file_path: Union[str, Path],
+    file_format: Optional[str] = None,
+    **loader_kwargs
+) -> List[Document]:
+    """快速加载文档的便捷函数"""
+    loader = UniversalDocLoader(file_path)
+    return loader.load(file_format=file_format, **loader_kwargs)

runtime/datamate-python/app/module/generation/service/generation_service.py

@@ -1,20 +1,8 @@
 import asyncio
-import uuid
 import json
+import uuid
 from pathlib import Path
 
-from langchain_community.document_loaders import (
-    TextLoader,
-    CSVLoader,
-    JSONLoader,
-    UnstructuredMarkdownLoader,
-    UnstructuredHTMLLoader,
-    UnstructuredFileLoader,
-    PyPDFLoader,
-    UnstructuredWordDocumentLoader,
-    UnstructuredPowerPointLoader,
-    UnstructuredExcelLoader,
-)
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
@@ -30,6 +18,7 @@ from app.db.models.model_config import get_model_by_id
 from app.db.session import logger
 from app.module.shared.util.model_chat import _extract_json_substring
 from app.module.system.service.common_service import get_chat_client, chat
+from app.common.document_loaders import load_documents
 
 
 class GenerationService:
@@ -250,8 +239,7 @@ class GenerationService:
 
         保留每个 Document 的 metadata，方便后续追加例如文件ID、chunk序号等信息。
         """
-        loader = self._build_loader(file_path)
-        docs = loader.load()
+        docs = load_documents(file_path)
 
         splitter = RecursiveCharacterTextSplitter(
             chunk_size=chunk_size,
@@ -262,67 +250,6 @@ class GenerationService:
         split_docs = splitter.split_documents(docs)
         return split_docs
 
-    @staticmethod
-    def _build_loader(file_path: str):
-        """根据文件扩展名选择合适的 LangChain 文本加载器，尽量覆盖常见泛文本格式。
-
-        优先按格式选择专门的 Loader，找不到匹配时退回到 TextLoader。
-        """
-        path = Path(file_path)
-        suffix = path.suffix.lower()
-        path_str = str(path)
-
-        # 1. 纯文本类
-        if suffix in {".txt", "", ".log"}:  # "" 兼容无扩展名
-            return TextLoader(path_str, encoding="utf-8")
-
-        # 2. Markdown
-        if suffix in {".md", ".markdown"}:
-            # UnstructuredMarkdownLoader 会保留更多结构信息
-            return UnstructuredMarkdownLoader(path_str)
-
-        # 3. HTML / HTM
-        if suffix in {".html", ".htm"}:
-            return UnstructuredHTMLLoader(path_str)
-
-        # 4. JSON
-        if suffix == ".json":
-            # 使用 JSONLoader 将 JSON 中的内容展开成文档
-            # 这里使用默认 jq_schema，后续需要更精细地提取可以在此调整
-            return JSONLoader(file_path=path_str, jq_schema=".")
-
-        # 5. CSV / TSV
-        if suffix in {".csv", ".tsv"}:
-            # CSVLoader 默认将每一行作为一条 Document
-            return CSVLoader(file_path=path_str)
-
-        # 6. YAML
-        if suffix in {".yaml", ".yml"}:
-            # 暂时按纯文本加载
-            return TextLoader(path_str, encoding="utf-8")
-
-        # 7. PDF
-        if suffix == ".pdf":
-            return PyPDFLoader(path_str)
-
-        # 8. Word 文档
-        if suffix in {".docx", ".doc"}:
-            # UnstructuredWordDocumentLoader 支持 .docx/.doc 文本抽取
-            return UnstructuredWordDocumentLoader(path_str)
-
-        # 9. PowerPoint
-        if suffix in {".ppt", ".pptx"}:
-            return UnstructuredPowerPointLoader(path_str)
-
-        # 10. Excel
-        if suffix in {".xls", ".xlsx"}:
-            return UnstructuredExcelLoader(path_str)
-
-        # 11. 兜底：使用 UnstructuredFileLoader 或 TextLoader 作为纯文本
-        try:
-            return UnstructuredFileLoader(path_str)
-        except Exception:
-            return TextLoader(path_str, encoding="utf-8")
 
     @staticmethod
     def _build_qa_prompt(chunk: str, synthesis_cfg: dict) -> str: