API: Download doc api (#1354)

### What problem does this PR solve?

Adds download_document api

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

sdk/python/ragflow/ragflow.py

@@ -12,12 +12,12 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
-
 import json
 import os
 
 import requests
 
+from api.db.services.document_service import DocumentService
 from api.settings import RetCode
 
 
@@ -126,7 +126,22 @@ class RAGFlow:
         return response.json()
 
     # ----------------------------download a file-----------------------------------------------------
+    def download_file(self, dataset_id, document_id):
+        endpoint = f"{self.dataset_url}/{dataset_id}/documents/{document_id}"
+        res = requests.get(endpoint, headers=self.authorization_header)
 
+        content = res.content  # binary data
+        # decode the binary data
+        try:
+            decoded_content = content.decode("utf-8")
+            json_data = json.loads(decoded_content)
+            return json_data  # message
+        except json.JSONDecodeError:  # binary data
+            _, document = DocumentService.get_by_id(document_id)
+            file_path = os.path.join(os.getcwd(), document.name)
+            with open(file_path, "wb") as file:
+                file.write(content)
+            return {"code": RetCode.SUCCESS, "data": content}
     # ----------------------------start parsing-----------------------------------------------------
 
     # ----------------------------stop parsing-----------------------------------------------------
@@ -144,3 +159,4 @@ class RAGFlow:
     # ----------------------------get a specific chunk-----------------------------------------------------
 
     # ----------------------------retrieval test-----------------------------------------------------
+

sdk/python/test/common.py

@@ -1,4 +1,4 @@
 
 
-API_KEY = 'ImFhMmJhZmUwMmQxNzExZWZhZDdmMzA0M2Q3ZWU1MzdlIg.ZnDsIQ.u-0-_qCRU6a4WICxyAPsjaafyOo'
+API_KEY = 'IjJkOGQ4ZDE2MzkyMjExZWZhYTk0MzA0M2Q3ZWU1MzdlIg.ZoUfug.RmqcYyCrlAnLtkzk6bYXiXN3eEY'
 HOST_ADDRESS = 'http://127.0.0.1:9380'

sdk/python/test/test_document.py

@@ -3,7 +3,6 @@ from test_sdkbase import TestSdk
 from ragflow import RAGFlow
 import pytest
 from common import API_KEY, HOST_ADDRESS
-from api.contants import NAME_LENGTH_LIMIT
 
 
 class TestFile(TestSdk):
@@ -625,8 +624,76 @@ class TestFile(TestSdk):
         update_res = ragflow.update_file(created_res_id, doc_id, **params)
         assert (update_res["code"] == RetCode.DATA_ERROR and
                 update_res["message"] == "Illegal value ? for 'template_type' field.")
+
 # ----------------------------download a file-----------------------------------------------------
 
+    def test_download_nonexistent_document(self):
+        """
+        Test downloading a document which does not exist.
+        """
+        # create a dataset
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_download_nonexistent_document")
+        created_res_id = created_res["data"]["dataset_id"]
+        res = ragflow.download_file(created_res_id, "imagination")
+        assert res["code"] == RetCode.ARGUMENT_ERROR and res["message"] == f"This document 'imagination' cannot be found!"
+
+    def test_download_document_in_nonexistent_dataset(self):
+        """
+        Test downloading a document whose dataset is nonexistent.
+        """
+        # create a dataset
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_download_nonexistent_document")
+        created_res_id = created_res["data"]["dataset_id"]
+        # upload files
+        file_paths = ["test_data/test.txt"]
+        uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
+        # get the doc_id
+        data = uploading_res["data"][0]
+        doc_id = data["id"]
+        # download file
+        res = ragflow.download_file("imagination", doc_id)
+        assert res["code"] == RetCode.DATA_ERROR and res["message"] == f"This dataset 'imagination' cannot be found!"
+
+    def test_download_document_with_success(self):
+        """
+        Test the downloading of a document with success.
+        """
+        # create a dataset
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_download_nonexistent_document")
+        created_res_id = created_res["data"]["dataset_id"]
+        # upload files
+        file_paths = ["test_data/test.txt"]
+        uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
+        # get the doc_id
+        data = uploading_res["data"][0]
+        doc_id = data["id"]
+        # download file
+        with open("test_data/test.txt", "rb") as file:
+            binary_data = file.read()
+        res = ragflow.download_file(created_res_id, doc_id)
+        assert res["code"] == RetCode.SUCCESS and res["data"] == binary_data
+
+    def test_download_an_empty_document(self):
+        """
+        Test the downloading of an empty document.
+        """
+        # create a dataset
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_download_nonexistent_document")
+        created_res_id = created_res["data"]["dataset_id"]
+        # upload files
+        file_paths = ["test_data/empty.txt"]
+        uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
+        # get the doc_id
+        data = uploading_res["data"][0]
+        doc_id = data["id"]
+        # download file
+        res = ragflow.download_file(created_res_id, doc_id)
+        assert res["code"] == RetCode.DATA_ERROR and res["message"] == "This file is empty."
+
 # ----------------------------start parsing-----------------------------------------------------
 
 # ----------------------------stop parsing-----------------------------------------------------