Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

sdk/python/test/conftest.py

@@ -113,12 +113,7 @@ def add_model_instance(auth):
         pytest.exit(f"Critical error in add model provider: {add_provider_res.get('message')}")
 
     add_instance_api = HOST_ADDRESS + "/api/v1/providers/ZHIPU-AI/instances"
-    add_instance_response = requests.post(url=add_instance_api, headers=authorization, json={
-        "instance_name": "CI",
-        "api_key": ZHIPU_AI_API_KEY,
-        "region": "default",
-        "base_url": ""
-    })
+    add_instance_response = requests.post(url=add_instance_api, headers=authorization, json={"instance_name": "CI", "api_key": ZHIPU_AI_API_KEY, "region": "default", "base_url": ""})
     add_instance_res = add_instance_response.json()
     if add_instance_res.get("code") != 0:
         pytest.exit(f"Critical error in add model instance: {add_instance_res.get('message')}")
@@ -139,41 +134,19 @@ def set_tenant_info(get_auth):
     url = HOST_ADDRESS + "/api/v1/models/default"
     authorization = {"Authorization": get_auth}
     # set chat model
-    set_default_llm_response = requests.patch(
-        url=url,
-        headers=authorization,
-        json={
-            "model_provider": "ZHIPU-AI",
-            "model_instance": "CI",
-            "model_type": "chat",
-            "model_name": "glm-4-flash"
-        })
+    set_default_llm_response = requests.patch(url=url, headers=authorization, json={"model_provider": "ZHIPU-AI", "model_instance": "CI", "model_type": "chat", "model_name": "glm-4-flash"})
     llm_res = set_default_llm_response.json()
     if llm_res.get("code") != 0:
         raise Exception(llm_res.get("message"))
     # set embedding model
     set_default_embedding_response = requests.patch(
-        url=url,
-        headers=authorization,
-        json={
-            "model_provider": "Builtin",
-            "model_instance": "Local",
-            "model_type": "embedding",
-            "model_name": "BAAI/bge-small-en-v1.5"
-        })
+        url=url, headers=authorization, json={"model_provider": "Builtin", "model_instance": "Local", "model_type": "embedding", "model_name": "BAAI/bge-small-en-v1.5"}
+    )
     embd_res = set_default_embedding_response.json()
     if embd_res.get("code") != 0:
         raise Exception(embd_res.get("message"))
     # set image to text model
-    set_default_img2txt_response = requests.patch(
-        url=url,
-        headers=authorization,
-        json={
-            "model_provider": "ZHIPU-AI",
-            "model_instance": "CI",
-            "model_type": "vision",
-            "model_name": "glm-4v"
-        })
+    set_default_img2txt_response = requests.patch(url=url, headers=authorization, json={"model_provider": "ZHIPU-AI", "model_instance": "CI", "model_type": "vision", "model_name": "glm-4v"})
     img2txt_res = set_default_img2txt_response.json()
     if img2txt_res.get("code") != 0:
         raise Exception(img2txt_res.get("message"))

sdk/python/test/test_frontend_api/common.py

@@ -73,20 +73,20 @@ def list_document(auth, dataset_id):
 def get_docs_info(auth, dataset_id, doc_ids=None, doc_id=None):
     """
     Get document information by IDs.
-    
+
     Args:
         auth: Authorization header
         dataset_id: Dataset ID
         doc_ids: List of document IDs (use for multiple) - exclusive with doc_id
         doc_id: Single document ID (use for one) - exclusive with doc_ids
-    
+
     Raises:
         ValueError: If both doc_id and doc_ids are provided
     """
     # Validate that id and ids are not used together
     if doc_id and doc_ids:
         raise ValueError("Cannot use both 'id' and 'ids' parameters at the same time.")
-    
+
     authorization = {"Authorization": auth}
     params = {}
     if doc_ids:
@@ -96,7 +96,7 @@ def get_docs_info(auth, dataset_id, doc_ids=None, doc_id=None):
     elif doc_id:
         # Single ID
         params["id"] = doc_id
-    
+
     # Use /api/v1 prefix for dataset API
     url = f"{HOST_ADDRESS}/api/v1/datasets/{dataset_id}/documents"
     res = requests.get(url=url, headers=authorization, params=params)
@@ -113,4 +113,3 @@ def parse_docs(auth, doc_ids):
 
 def parse_file(auth, document_id):
     pass
-

sdk/python/test/test_frontend_api/get_email.py

@@ -14,6 +14,7 @@
 #  limitations under the License.
 #
 
+
 def test_get_email(get_email):
-    print("\nEmail account:",flush=True)
-    print(f"{get_email}\n",flush=True)
+    print("\nEmail account:", flush=True)
+    print(f"{get_email}\n", flush=True)

sdk/python/test/test_frontend_api/test_chunk.py

@@ -40,15 +40,15 @@ def test_parse_txt_document(get_auth):
             break
         page_number += 1
 
-    filename = 'ragflow_test.txt'
+    filename = "ragflow_test.txt"
     res = upload_file(get_auth, dataset_id, f"../test_sdk_api/test_data/{filename}")
     assert res.get("code") == 0, f"{res.get('message')}"
 
     res = list_document(get_auth, dataset_id)
 
     doc_id_list = []
-    for doc in res['data']['docs']:
-        doc_id_list.append(doc['id'])
+    for doc in res["data"]["docs"]:
+        doc_id_list.append(doc["id"])
 
     res = get_docs_info(get_auth, dataset_id, doc_ids=doc_id_list)
     print(doc_id_list)
@@ -59,13 +59,13 @@ def test_parse_txt_document(get_auth):
     while True:
         res = get_docs_info(get_auth, dataset_id, doc_ids=doc_id_list)
         finished_count = 0
-        for doc_info in res['data']:
-            if doc_info['progress'] == 1:
+        for doc_info in res["data"]:
+            if doc_info["progress"] == 1:
                 finished_count += 1
         if finished_count == doc_count:
             break
         sleep(1)
-    print('time cost {:.1f}s'.format(timer() - start_ts))
+    print("time cost {:.1f}s".format(timer() - start_ts))
 
     # delete dataset
     if dataset_list:

sdk/python/test/test_frontend_api/test_dataset.py

@@ -89,7 +89,7 @@ def test_duplicated_name_dataset(get_auth):
     if isinstance(data, dict):
         data = data.get("kbs", [])
     dataset_list = []
-    pattern = r'^test_create_dataset.*'
+    pattern = r"^test_create_dataset.*"
     for item in data:
         dataset_name = item.get("name")
         dataset_id = item.get("id")
@@ -106,10 +106,10 @@ def test_duplicated_name_dataset(get_auth):
 def test_invalid_name_dataset(get_auth):
     # create dataset
     res = create_dataset(get_auth, {"name": 0})
-    assert res['code'] != 0
+    assert res["code"] != 0
 
     res = create_dataset(get_auth, {"name": ""})
-    assert res['code'] != 0
+    assert res["code"] != 0
 
     long_string = ""
 
@@ -117,7 +117,7 @@ def test_invalid_name_dataset(get_auth):
         long_string += random.choice(string.ascii_letters + string.digits)
 
     res = create_dataset(get_auth, {"name": long_string})
-    assert res['code'] != 0
+    assert res["code"] != 0
     print(res)
 
 
@@ -144,13 +144,17 @@ def test_update_different_params_dataset_success(get_auth):
     print(f"found {len(dataset_list)} datasets")
     dataset_id = dataset_list[0]
 
-    res = update_dataset(get_auth, dataset_id, {
-        "name": "test_update_dataset",
-        "description": "test",
-        "permission": "me",
-        "chunk_method": "presentation",
-        "language": "spanish",
-    })
+    res = update_dataset(
+        get_auth,
+        dataset_id,
+        {
+            "name": "test_update_dataset",
+            "description": "test",
+            "permission": "me",
+            "chunk_method": "presentation",
+            "language": "spanish",
+        },
+    )
     assert res.get("code") == 0, f"{res.get('message')}"
 
     # delete dataset