Add test for CI (#3114)

### What problem does this PR solve?

Add test for CI

### Type of change

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

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

sdk/python/hello_ragflow.py

@@ -1,3 +1,3 @@
-import ragflow
+import ragflow_sdk
 
-print(ragflow.__version__)
+print(ragflow_sdk.__version__)

sdk/python/poetry.lock

@@ -125,6 +125,31 @@ files = [
     {file = "charset_normalizer-3.4.0.tar.gz", hash = "sha256:223217c3d4f82c3ac5e29032b3f1c2eb0fb591b72161f86d93f5719079dae93e"},
 ]
 
+[[package]]
+name = "colorama"
+version = "0.4.6"
+description = "Cross-platform colored terminal text."
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+files = [
+    {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
+    {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
+]
+
+[[package]]
+name = "exceptiongroup"
+version = "1.2.2"
+description = "Backport of PEP 654 (exception groups)"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "exceptiongroup-1.2.2-py3-none-any.whl", hash = "sha256:3111b9d131c238bec2f8f516e123e14ba243563fb135d3fe885990585aa7795b"},
+    {file = "exceptiongroup-1.2.2.tar.gz", hash = "sha256:47c2edf7c6738fafb49fd34290706d1a1a2f4d1c6df275526b62cbb4aa5393cc"},
+]
+
+[package.extras]
+test = ["pytest (>=6)"]
+
 [[package]]
 name = "idna"
 version = "3.10"
@@ -139,6 +164,65 @@ files = [
 [package.extras]
 all = ["flake8 (>=7.1.1)", "mypy (>=1.11.2)", "pytest (>=8.3.2)", "ruff (>=0.6.2)"]
 
+[[package]]
+name = "iniconfig"
+version = "2.0.0"
+description = "brain-dead simple config-ini parsing"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"},
+    {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
+]
+
+[[package]]
+name = "packaging"
+version = "24.1"
+description = "Core utilities for Python packages"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "packaging-24.1-py3-none-any.whl", hash = "sha256:5b8f2217dbdbd2f7f384c41c628544e6d52f2d0f53c6d0c3ea61aa5d1d7ff124"},
+    {file = "packaging-24.1.tar.gz", hash = "sha256:026ed72c8ed3fcce5bf8950572258698927fd1dbda10a5e981cdf0ac37f4f002"},
+]
+
+[[package]]
+name = "pluggy"
+version = "1.5.0"
+description = "plugin and hook calling mechanisms for python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669"},
+    {file = "pluggy-1.5.0.tar.gz", hash = "sha256:2cffa88e94fdc978c4c574f15f9e59b7f4201d439195c3715ca9e2486f1d0cf1"},
+]
+
+[package.extras]
+dev = ["pre-commit", "tox"]
+testing = ["pytest", "pytest-benchmark"]
+
+[[package]]
+name = "pytest"
+version = "8.3.3"
+description = "pytest: simple powerful testing with Python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "pytest-8.3.3-py3-none-any.whl", hash = "sha256:a6853c7375b2663155079443d2e45de913a911a11d669df02a50814944db57b2"},
+    {file = "pytest-8.3.3.tar.gz", hash = "sha256:70b98107bd648308a7952b06e6ca9a50bc660be218d53c257cc1fc94fda10181"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "sys_platform == \"win32\""}
+exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
+iniconfig = "*"
+packaging = "*"
+pluggy = ">=1.5,<2"
+tomli = {version = ">=1", markers = "python_version < \"3.11\""}
+
+[package.extras]
+dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
+
 [[package]]
 name = "requests"
 version = "2.32.3"
@@ -160,6 +244,17 @@ urllib3 = ">=1.21.1,<3"
 socks = ["PySocks (>=1.5.6,!=1.5.7)"]
 use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
 
+[[package]]
+name = "tomli"
+version = "2.0.2"
+description = "A lil' TOML parser"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "tomli-2.0.2-py3-none-any.whl", hash = "sha256:2ebe24485c53d303f690b0ec092806a085f07af5a5aa1464f3931eec36caaa38"},
+    {file = "tomli-2.0.2.tar.gz", hash = "sha256:d46d457a85337051c36524bc5349dd91b1877838e2979ac5ced3e710ed8a60ed"},
+]
+
 [[package]]
 name = "urllib3"
 version = "2.2.3"
@@ -180,4 +275,4 @@ zstd = ["zstandard (>=0.18.0)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "3423d9502ced305145882182d8e309fa020c3ab007d9877b755dcb9d16e9da2c"
+content-hash = "202bfd3e121f1d57a2f9c9d91cd7a50eacf2362cd1995c9f6347bcb100cf9336"

sdk/python/pyproject.toml

@@ -10,6 +10,7 @@ package-mode = true
 [tool.poetry.dependencies]
 python = "^3.10"
 requests = "^2.30.0"
+pytest = "^8.0.0"
 
 
 [build-system]

sdk/python/test/conftest.py

@@ -1,11 +1,11 @@
-import pytest
-import requests
 import string
 import random
+import os
+import pytest
+import requests
 
 
-
-HOST_ADDRESS = 'http://127.0.0.1:9380'
+HOST_ADDRESS = os.getenv('HOST_ADDRESS', 'http://127.0.0.1:9380')
 
 def generate_random_email():
     return 'user_' + ''.join(random.choices(string.ascii_lowercase + string.digits, k=8))+'@1.com'

sdk/python/test/t_chat.py

@@ -1,12 +1,14 @@
+import os
 from ragflow_sdk import RAGFlow
-HOST_ADDRESS = 'http://127.0.0.1:9380'
+
+HOST_ADDRESS = os.getenv('HOST_ADDRESS', 'http://127.0.0.1:9380')
 
 def test_create_chat_with_name(get_api_key_fixture):
     API_KEY = get_api_key_fixture
     rag = RAGFlow(API_KEY, HOST_ADDRESS)
     kb = rag.create_dataset(name="test_create_chat")
     displayed_name = "ragflow.txt"
-    with open("./ragflow.txt","rb") as file:
+    with open("ragflow.txt", "rb") as file:
         blob = file.read()
     document = {"displayed_name":displayed_name,"blob":blob}
     documents = []
@@ -22,7 +24,7 @@ def test_update_chat_with_name(get_api_key_fixture):
     rag = RAGFlow(API_KEY, HOST_ADDRESS)
     kb = rag.create_dataset(name="test_update_chat")
     displayed_name = "ragflow.txt"
-    with open("./ragflow.txt", "rb") as file:
+    with open("ragflow.txt", "rb") as file:
         blob = file.read()
     document = {"displayed_name": displayed_name, "blob": blob}
     documents = []
@@ -39,7 +41,7 @@ def test_delete_chats_with_success(get_api_key_fixture):
     rag = RAGFlow(API_KEY, HOST_ADDRESS)
     kb = rag.create_dataset(name="test_delete_chat")
     displayed_name = "ragflow.txt"
-    with open("./ragflow.txt", "rb") as file:
+    with open("ragflow.txt", "rb") as file:
         blob = file.read()
     document = {"displayed_name": displayed_name, "blob": blob}
     documents = []
@@ -53,9 +55,9 @@ def test_delete_chats_with_success(get_api_key_fixture):
 def test_list_chats_with_success(get_api_key_fixture):
     API_KEY = get_api_key_fixture
     rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    kb = rag.create_dataset(name="test_delete_chat")
+    kb = rag.create_dataset(name="test_list_chats")
     displayed_name = "ragflow.txt"
-    with open("./ragflow.txt", "rb") as file:
+    with open("ragflow.txt", "rb") as file:
         blob = file.read()
     document = {"displayed_name": displayed_name, "blob": blob}
     documents = []

sdk/python/test/t_dataset.py

@@ -1,54 +1,55 @@
-from ragflow_sdk import RAGFlow
-import random
-import pytest
-
-HOST_ADDRESS = 'http://127.0.0.1:9380'
-
-def test_create_dataset_with_name(get_api_key_fixture):
-    API_KEY = get_api_key_fixture
-    rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    rag.create_dataset("test_create_dataset_with_name")
-
-def test_create_dataset_with_duplicated_name(get_api_key_fixture):
-    API_KEY = get_api_key_fixture
-    rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    with pytest.raises(Exception) as exc_info:
-        rag.create_dataset("test_create_dataset_with_name")
-    assert str(exc_info.value) == "Duplicated dataset name in creating dataset."
-
-def test_create_dataset_with_random_chunk_method(get_api_key_fixture):
-    API_KEY = get_api_key_fixture
-    rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    valid_chunk_methods = ["naive","manual","qa","table","paper","book","laws","presentation","picture","one","knowledge_graph","email"]
-    random_chunk_method = random.choice(valid_chunk_methods)
-    rag.create_dataset("test_create_dataset_with_random_chunk_method",chunk_method=random_chunk_method)
-
-def test_create_dataset_with_invalid_parameter(get_api_key_fixture):
-    API_KEY = get_api_key_fixture
-    rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    valid_chunk_methods = ["naive", "manual", "qa", "table", "paper", "book", "laws", "presentation", "picture", "one",
-                           "knowledge_graph", "email"]
-    chunk_method = "invalid_chunk_method"
-    with pytest.raises(Exception) as exc_info:
-        rag.create_dataset("test_create_dataset_with_name",chunk_method=chunk_method)
-    assert str(exc_info.value) == f"{chunk_method} is not in {valid_chunk_methods}"
-
-
-def test_update_dataset_with_name(get_api_key_fixture):
-    API_KEY = get_api_key_fixture
-    rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    ds = rag.create_dataset("test_update_dataset")
-    ds.update({"name": "updated_dataset"})
-
-
-def test_delete_datasets_with_success(get_api_key_fixture):
-    API_KEY = get_api_key_fixture
-    rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    ds = rag.create_dataset("MA")
-    rag.delete_datasets(ids=[ds.id])
-
-
-def test_list_datasets_with_success(get_api_key_fixture):
-    API_KEY = get_api_key_fixture
-    rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    rag.list_datasets()
+import os
+import random
+import pytest
+from ragflow_sdk import RAGFlow
+
+HOST_ADDRESS = os.getenv('HOST_ADDRESS', 'http://127.0.0.1:9380')
+
+def test_create_dataset_with_name(get_api_key_fixture):
+    API_KEY = get_api_key_fixture
+    rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    rag.create_dataset("test_create_dataset_with_name")
+
+def test_create_dataset_with_duplicated_name(get_api_key_fixture):
+    API_KEY = get_api_key_fixture
+    rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    with pytest.raises(Exception) as exc_info:
+        rag.create_dataset("test_create_dataset_with_name")
+    assert str(exc_info.value) == "Duplicated dataset name in creating dataset."
+
+def test_create_dataset_with_random_chunk_method(get_api_key_fixture):
+    API_KEY = get_api_key_fixture
+    rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    valid_chunk_methods = ["naive","manual","qa","table","paper","book","laws","presentation","picture","one","knowledge_graph","email"]
+    random_chunk_method = random.choice(valid_chunk_methods)
+    rag.create_dataset("test_create_dataset_with_random_chunk_method",chunk_method=random_chunk_method)
+
+def test_create_dataset_with_invalid_parameter(get_api_key_fixture):
+    API_KEY = get_api_key_fixture
+    rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    valid_chunk_methods = ["naive", "manual", "qa", "table", "paper", "book", "laws", "presentation", "picture", "one",
+                           "knowledge_graph", "email"]
+    chunk_method = "invalid_chunk_method"
+    with pytest.raises(Exception) as exc_info:
+        rag.create_dataset("test_create_dataset_with_name",chunk_method=chunk_method)
+    assert str(exc_info.value) == f"'{chunk_method}' is not in {valid_chunk_methods}"
+
+
+def test_update_dataset_with_name(get_api_key_fixture):
+    API_KEY = get_api_key_fixture
+    rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    ds = rag.create_dataset("test_update_dataset")
+    ds.update({"name": "updated_dataset"})
+
+
+def test_delete_datasets_with_success(get_api_key_fixture):
+    API_KEY = get_api_key_fixture
+    rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    ds = rag.create_dataset("MA")
+    rag.delete_datasets(ids=[ds.id])
+
+
+def test_list_datasets_with_success(get_api_key_fixture):
+    API_KEY = get_api_key_fixture
+    rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    rag.list_datasets()

sdk/python/test/t_document.py

@@ -1,6 +1,7 @@
+import os
 from ragflow_sdk import RAGFlow, DataSet, Document, Chunk
 
-HOST_ADDRESS = 'http://127.0.0.1:9380'
+HOST_ADDRESS = os.getenv('HOST_ADDRESS', 'http://127.0.0.1:9380')
 
 
 def test_upload_document_with_success(get_api_key_fixture):
@@ -66,7 +67,7 @@ def test_download_document_with_success(get_api_key_fixture):
     # Check if the retrieved document is of type Document
     if isinstance(doc, Document):
         # Download the document content and save it to a file
-        with open("./ragflow.txt", "wb+") as file:
+        with open("ragflow.txt", "wb+") as file:
             file.write(doc.download())
             # Print the document object for debugging
         print(doc)
@@ -144,7 +145,7 @@ def test_parse_and_cancel_document(get_api_key_fixture):
 
     # Define the document name and path
     name3 = 'westworld.pdf'
-    path = './test_data/westworld.pdf'
+    path = 'test_data/westworld.pdf'
 
     # Create a document in the dataset using the file path
     ds.upload_documents({"name": name3, "blob": open(path, "rb").read()})

sdk/python/test/t_session.py

@@ -1,94 +1,96 @@
-from ragflow_sdk import RAGFlow
-HOST_ADDRESS = 'http://127.0.0.1:9380'
-
-
-def test_create_session_with_success(get_api_key_fixture):
-    API_KEY = get_api_key_fixture
-    rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    kb = rag.create_dataset(name="test_create_session")
-    displayed_name = "ragflow.txt"
-    with open("./ragflow.txt", "rb") as file:
-        blob = file.read()
-    document = {"displayed_name":displayed_name,"blob":blob}
-    documents = []
-    documents.append(document)
-    docs= kb.upload_documents(documents)
-    for doc in docs:
-        doc.add_chunk("This is a test to add chunk")
-    assistant=rag.create_chat("test_create", dataset_ids=[kb.id])
-    assistant.create_session()
-
-
-def test_create_conversation_with_success(get_api_key_fixture):
-    API_KEY = get_api_key_fixture
-    rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    kb = rag.create_dataset(name="test_create_conversation")
-    displayed_name = "ragflow.txt"
-    with open("./ragflow.txt","rb") as file:
-        blob = file.read()
-    document = {"displayed_name": displayed_name, "blob": blob}
-    documents = []
-    documents.append(document)
-    docs = kb.upload_documents(documents)
-    for doc in docs:
-        doc.add_chunk("This is a test to add chunk")
-    assistant = rag.create_chat("test_create", dataset_ids=[kb.id])
-    session = assistant.create_session()
-    question = "What is AI"
-    for ans in session.ask(question, stream=True):
-        pass
-    assert not ans.content.startswith("**ERROR**"), "Please check this error."
-
-
-def test_delete_sessions_with_success(get_api_key_fixture):
-    API_KEY = get_api_key_fixture
-    rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    kb = rag.create_dataset(name="test_delete_session")
-    displayed_name = "ragflow.txt"
-    with open("./ragflow.txt","rb") as file:
-        blob = file.read()
-    document = {"displayed_name":displayed_name,"blob":blob}
-    documents = []
-    documents.append(document)
-    docs= kb.upload_documents(documents)
-    for doc in docs:
-        doc.add_chunk("This is a test to add chunk")
-    assistant=rag.create_chat("test_create", dataset_ids=[kb.id])
-    session = assistant.create_session()
-    assistant.delete_sessions(ids=[session.id])
-
-def test_update_session_with_name(get_api_key_fixture):
-    API_KEY = get_api_key_fixture
-    rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    kb = rag.create_dataset(name="test_update_session")
-    displayed_name = "ragflow.txt"
-    with open("./ragflow.txt","rb") as file:
-        blob = file.read()
-    document = {"displayed_name": displayed_name, "blob": blob}
-    documents = []
-    documents.append(document)
-    docs = kb.upload_documents(documents)
-    for doc in docs:
-        doc.add_chunk("This is a test to add chunk")
-    assistant = rag.create_chat("test_create", dataset_ids=[kb.id])
-    session = assistant.create_session(name="old session")
-    session.update({"name": "new session"})
-
-
-def test_list_sessions_with_success(get_api_key_fixture):
-    API_KEY = get_api_key_fixture
-    rag = RAGFlow(API_KEY, HOST_ADDRESS)
-    kb = rag.create_dataset(name="test_list_session")
-    displayed_name = "ragflow.txt"
-    with open("./ragflow.txt","rb") as file:
-        blob = file.read()
-    document = {"displayed_name":displayed_name,"blob":blob}
-    documents = []
-    documents.append(document)
-    docs= kb.upload_documents(documents)
-    for doc in docs:
-        doc.add_chunk("This is a test to add chunk")
-    assistant=rag.create_chat("test_create", dataset_ids=[kb.id])
-    assistant.create_session("test_1")
-    assistant.create_session("test_2")
+import os
+from ragflow_sdk import RAGFlow
+
+HOST_ADDRESS = os.getenv('HOST_ADDRESS', 'http://127.0.0.1:9380')
+
+
+def test_create_session_with_success(get_api_key_fixture):
+    API_KEY = get_api_key_fixture
+    rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    kb = rag.create_dataset(name="test_create_session")
+    displayed_name = "ragflow.txt"
+    with open("ragflow.txt", "rb") as file:
+        blob = file.read()
+    document = {"displayed_name":displayed_name,"blob":blob}
+    documents = []
+    documents.append(document)
+    docs= kb.upload_documents(documents)
+    for doc in docs:
+        doc.add_chunk("This is a test to add chunk")
+    assistant=rag.create_chat("test_create_session", dataset_ids=[kb.id])
+    assistant.create_session()
+
+
+def test_create_conversation_with_success(get_api_key_fixture):
+    API_KEY = get_api_key_fixture
+    rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    kb = rag.create_dataset(name="test_create_conversation")
+    displayed_name = "ragflow.txt"
+    with open("ragflow.txt", "rb") as file:
+        blob = file.read()
+    document = {"displayed_name": displayed_name, "blob": blob}
+    documents = []
+    documents.append(document)
+    docs = kb.upload_documents(documents)
+    for doc in docs:
+        doc.add_chunk("This is a test to add chunk")
+    assistant = rag.create_chat("test_create_conversation", dataset_ids=[kb.id])
+    session = assistant.create_session()
+    question = "What is AI"
+    for ans in session.ask(question, stream=True):
+        pass
+    assert not ans.content.startswith("**ERROR**"), "Please check this error."
+
+
+def test_delete_sessions_with_success(get_api_key_fixture):
+    API_KEY = get_api_key_fixture
+    rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    kb = rag.create_dataset(name="test_delete_session")
+    displayed_name = "ragflow.txt"
+    with open("ragflow.txt", "rb") as file:
+        blob = file.read()
+    document = {"displayed_name":displayed_name,"blob":blob}
+    documents = []
+    documents.append(document)
+    docs= kb.upload_documents(documents)
+    for doc in docs:
+        doc.add_chunk("This is a test to add chunk")
+    assistant=rag.create_chat("test_delete_session", dataset_ids=[kb.id])
+    session = assistant.create_session()
+    assistant.delete_sessions(ids=[session.id])
+
+def test_update_session_with_name(get_api_key_fixture):
+    API_KEY = get_api_key_fixture
+    rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    kb = rag.create_dataset(name="test_update_session")
+    displayed_name = "ragflow.txt"
+    with open("ragflow.txt", "rb") as file:
+        blob = file.read()
+    document = {"displayed_name": displayed_name, "blob": blob}
+    documents = []
+    documents.append(document)
+    docs = kb.upload_documents(documents)
+    for doc in docs:
+        doc.add_chunk("This is a test to add chunk")
+    assistant = rag.create_chat("test_update_session", dataset_ids=[kb.id])
+    session = assistant.create_session(name="old session")
+    session.update({"name": "new session"})
+
+
+def test_list_sessions_with_success(get_api_key_fixture):
+    API_KEY = get_api_key_fixture
+    rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    kb = rag.create_dataset(name="test_list_session")
+    displayed_name = "ragflow.txt"
+    with open("ragflow.txt", "rb") as file:
+        blob = file.read()
+    document = {"displayed_name":displayed_name,"blob":blob}
+    documents = []
+    documents.append(document)
+    docs= kb.upload_documents(documents)
+    for doc in docs:
+        doc.add_chunk("This is a test to add chunk")
+    assistant=rag.create_chat("test_list_session", dataset_ids=[kb.id])
+    assistant.create_session("test_1")
+    assistant.create_session("test_2")
     assistant.list_sessions()