API: show status of parsing (#1504)

### What problem does this PR solve?

show status of parsing.

### Type of change

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

api/apps/dataset_api.py

@@ -750,7 +750,27 @@ def get_message_during_parsing_document(id, message):
 # ----------------------------stop parsing-----------------------------------------------------
 
 # ----------------------------show the status of the file-----------------------------------------------------
+@manager.route("/<dataset_id>/documents/<document_id>/status", methods=["GET"])
+@login_required
+def show_parsing_status(dataset_id, document_id):
+    try:
+        # valid dataset
+        exist, _ = KnowledgebaseService.get_by_id(dataset_id)
+        if not exist:
+            return construct_json_result(code=RetCode.DATA_ERROR,
+                                         message=f"This dataset: '{dataset_id}' cannot be found!")
+        # valid document
+        exist, _ = DocumentService.get_by_id(document_id)
+        if not exist:
+            return construct_json_result(code=RetCode.DATA_ERROR,
+                                         message=f"This document: '{document_id}' is not a valid document.")
 
+        _, doc = DocumentService.get_by_id(document_id)  # get doc object
+        doc_attributes = doc.to_dict()
+
+        return construct_json_result(data={"progress": doc_attributes["progress"], "status": doc_attributes["status"]}, code=RetCode.SUCCESS)
+    except Exception as e:
+        return construct_error_response(e)
 # ----------------------------list the chunks of the file-----------------------------------------------------
 
 # -- --------------------------delete the chunk-----------------------------------------------------

sdk/python/ragflow/ragflow.py

@@ -159,7 +159,11 @@ class RAGFlow:
     # ----------------------------stop parsing-----------------------------------------------------
 
     # ----------------------------show the status of the file-----------------------------------------------------
+    def show_parsing_status(self, dataset_id, document_id):
+        endpoint = f"{self.dataset_url}/{dataset_id}/documents/{document_id}/status"
+        res = requests.get(endpoint, headers=self.authorization_header)
 
+        return res.json()
     # ----------------------------list the chunks of the file-----------------------------------------------------
 
     # ----------------------------delete the chunk-----------------------------------------------------

sdk/python/test/test_document.py

@@ -953,7 +953,52 @@ class TestFile(TestSdk):
 # ----------------------------stop parsing-----------------------------------------------------
 
 # ----------------------------show the status of the file-----------------------------------------------------
+    def test_show_status_with_success(self):
+        # create a dataset
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_show_status_with_success")
+        created_res_id = created_res["data"]["dataset_id"]
+        # upload files
+        file_paths = ["test_data/lol.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"]
+        # parse file
+        res = ragflow.start_parsing_document(created_res_id, doc_id)
+        assert res["code"] == RetCode.SUCCESS and res["message"] == ""
+        # show status
+        status_res = ragflow.show_parsing_status(created_res_id, doc_id)
+        assert status_res["code"] == RetCode.SUCCESS and status_res["data"]["status"] == "1"
 
+    def test_show_status_nonexistent_document(self):
+        """
+        Test showing the status of a document which does not exist.
+        """
+        # create a dataset
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_show_status_nonexistent_document")
+        created_res_id = created_res["data"]["dataset_id"]
+        res = ragflow.show_parsing_status(created_res_id, "imagination")
+        assert res["code"] == RetCode.DATA_ERROR and res["message"] == "This document: 'imagination' is not a valid document."
+
+    def test_show_status_document_in_nonexistent_dataset(self):
+        """
+        Test showing the status of a document whose dataset is nonexistent.
+        """
+        # create a dataset
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_show_status_document_in_nonexistent_dataset")
+        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"]
+        # parse
+        res = ragflow.show_parsing_status("imagination", doc_id)
+        assert res["code"] == RetCode.DATA_ERROR and res["message"] == "This dataset: 'imagination' cannot be found!"
 # ----------------------------list the chunks of the file-----------------------------------------------------
 
 # ----------------------------delete the chunk-----------------------------------------------------