Refactor Document API (#2833)

### What problem does this PR solve?

Refactor Document API

### Type of change


- [x] Refactoring

Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>

sdk/python/ragflow/modules/base.py

@@ -18,8 +18,8 @@ class Base(object):
                     pr[name] = value
         return pr
 
-    def post(self, path, json, stream=False):
-        res = self.rag.post(path, json, stream=stream)
+    def post(self, path, json=None, stream=False, files=None):
+        res = self.rag.post(path, json, stream=stream,files=files)
         return res
 
     def get(self, path, params):

sdk/python/ragflow/modules/dataset.py

@@ -1,5 +1,7 @@
 from typing import Optional, List
 
+from transformers.models.bloom.modeling_bloom import bloom_gelu_back
+
 from .document import Document
 
 from .base import Base
@@ -39,39 +41,27 @@ class DataSet(Base):
         if res.get("code") != 0:
             raise Exception(res["message"])
 
+    def upload_documents(self,document_list: List[dict]):
+        url = f"/dataset/{self.id}/document"
+        files = [("file",(ele["name"],ele["blob"])) for ele in document_list]
+        res = self.post(path=url,json=None,files=files)
+        res = res.json()
+        if res.get("code") != 0:
+            raise Exception(res.get("message"))
 
-    def list_docs(self, keywords: Optional[str] = None, offset: int = 0, limit: int = -1) -> List[Document]:
-        """
-        List the documents in the dataset, optionally filtering by keywords, with pagination support.
-
-        Args:
-            keywords (Optional[str]): A string of keywords to filter the documents. Defaults to None.
-            offset (int): The starting point for pagination. Defaults to 0.
-            limit (int): The maximum number of documents to return. Defaults to -1 (no limit).
-
-        Returns:
-            List[Document]: A list of Document objects.
-        """
-        # Construct the request payload for listing documents
-        payload = {
-            "knowledgebase_id": self.id,
-            "keywords": keywords,
-            "offset": offset,
-            "limit": limit
-        }
-
-        # Send the request to the server to list documents
-        res = self.get(f'/doc/dataset/{self.id}/documents', payload)
-        res_json = res.json()
-
-        # Handle response and error checking
-        if res_json.get("retmsg") != "success":
-            raise Exception(res_json.get("retmsg"))
-
-        # Parse the document data from the response
+    def list_documents(self, id: str = None, keywords: str = None, offset: int =1, limit: int = 1024, orderby: str = "create_time", desc: bool = True):
+        res = self.get(f"/dataset/{self.id}/info",params={"id": id,"keywords": keywords,"offset": offset,"limit": limit,"orderby": orderby,"desc": desc})
+        res = res.json()
         documents = []
-        for doc_data in res_json["data"].get("docs", []):
-            doc = Document(self.rag, doc_data)
-            documents.append(doc)
+        if res.get("code") == 0:
+            for document in res["data"].get("docs"):
+                documents.append(Document(self.rag,document))
+            return documents
+        raise Exception(res["message"])
+
+    def delete_documents(self,ids: List[str] = None):
+        res = self.rm(f"/dataset/{self.id}/document",{"ids":ids})
+        res = res.json()
+        if res.get("code") != 0:
+            raise Exception(res["message"])
 
-        return documents

sdk/python/ragflow/modules/document.py

@@ -29,18 +29,14 @@ class Document(Base):
                 res_dict.pop(k)
         super().__init__(rag, res_dict)
 
-    def save(self) -> bool:
+    def update(self,update_message:dict) -> bool:
         """
         Save the document details to the server.
         """
-        res = self.post('/doc/save',
-                        {"id": self.id, "name": self.name, "thumbnail": self.thumbnail, "knowledgebase_id": self.knowledgebase_id,
-                         "parser_method": self.parser_method, "parser_config": self.parser_config.to_json(),
-                         })
+        res = self.post(f'/dataset/{self.knowledgebase_id}/info/{self.id}',update_message)
         res = res.json()
-        if res.get("retmsg") == "success":
-            return True
-        raise Exception(res["retmsg"])
+        if res.get("code") != 0:
+            raise Exception(res["message"])
 
     def delete(self) -> bool:
         """
@@ -60,8 +56,7 @@ class Document(Base):
         :return: The downloaded document content in bytes.
         """
         # Construct the URL for the API request using the document ID and knowledge base ID
-        res = self.get(f"/doc/{self.id}",
-                       {"headers": self.rag.authorization_header, "id": self.id, "name": self.name, "stream": True})
+        res = self.get(f"/dataset/{self.knowledgebase_id}/document/{self.id}")
 
         # Check the response status code to ensure the request was successful
         if res.status_code == 200: