chore: fix integration tests

.markdownlint.json

@@ -0,0 +1,4 @@
+{
+  "MD013": false,
+  "MD033": false
+}

README.md

@@ -1,26 +1,40 @@
-# AI DIAL Client (Python)
+<h1 align="center">
+  DIAL Client SDK
+</h1>
+<p align="center">
+  <p align="center">
+  <a href="https://dialx.ai/">
+    <img src="https://dialx.ai/dialx_logo.svg" alt="About DIALX">
+  </a>
+</p>
+<h4 align="center">
+  <a href="https://discord.gg/ukzj9U9tEe">
+    <img src="https://img.shields.io/static/v1?label=DIALX%20Community%20on&message=Discord&color=blue&logo=Discord&style=flat-square" alt="Discord">
+  </a>
+</h4>
+
+- [AI DIAL Client (Python)](#ai-dial-client-python)
+  - [Authentication](#authentication)
+    - [API Keys](#api-keys)
+    - [Bearer Token](#bearer-token)
+  - [List Deployments](#list-deployments)
+  - [Make Completions Requests](#make-completions-requests)
+    - [Without Streaming](#without-streaming)
+    - [With Streaming](#with-streaming)
+  - [Working with Files](#working-with-files)
+    - [Working with URLs](#working-with-urls)
+    - [Uploading Files](#uploading-files)
+    - [Downloading Files](#downloading-files)
+    - [Deleting Files](#deleting-files)
+    - [Accessing Metadata](#accessing-metadata)
+  - [Applications](#applications)
+    - [List Applications](#list-applications)
+    - [Get Application by Id](#get-application-by-id)
+  - [Client Pool](#client-pool)
+    - [Synchronous Client Pool](#synchronous-client-pool)
+    - [Asynchronous Client Pool](#asynchronous-client-pool)
 
-## Table of Contents
-
-- [Authentication](#authentication)
-  - [API Keys](#api-keys)
-  - [Bearer Token](#bearer-token)
-- [List Deployments](#list-deployments)
-- [Make Chat Completions Requests](#make-completions-requests)
-  - [Without Streaming](#without-streaming)
-  - [With Streaming](#with-streaming)
-- [Working with Files](#working-with-files)
-  - [Working with URLs](#working-with-urls)
-  - [Uploading Files](#uploading-files)
-  - [Downloading Files](#downloading-files)
-  - [Deleting Files](#deleting-files)
-  - [Accessing Metadata](#accessing-metadata)
-- [Applications](#applications)
-  - [List Applications](#list-applications)
-  - [Get Application by Id](#get-application-by-id)
-- [Client Pool](#client-pool)
-  - [Synchronous Client Pool](#synchronous-client-pool)
-  - [Asynchronous Client Pool](#asynchronous-client-pool)
+# AI DIAL Client (Python)
 
 ## Authentication
 
@@ -139,7 +153,7 @@ Synchronous:
 client = Dial(api_key="your-api-key", base_url="https://your-dial-instance.com")
 
 completion = client.chat.completions.create(
-    deployment_name="gpt-35-turbo",
+    deployment_name="gpt-4o",
     stream=False,
     messages=[
         {
@@ -159,7 +173,7 @@ async_client = AsyncDial(
     api_key="your-api-key", base_url="https://your-dial-instance.com"
 )
 completion = await async_client.chat.completions.create(
-    deployment_name="gpt-35-turbo",
+    deployment_name="gpt-4o",
     stream=False,
     messages=[
         {
@@ -212,7 +226,7 @@ Synchronous:
 client = Dial(api_key="your-api-key", base_url="https://your-dial-instance.com")
 
 completion = client.chat.completions.create(
-    deployment_name="gpt-35-turbo",
+    deployment_name="gpt-4o",
     # Specify a stream parameter
     stream=True,
     messages=[
@@ -235,7 +249,7 @@ async_client = AsyncDial(
     api_key="your-api-key", base_url="https://your-dial-instance.com"
 )
 completion = await async_client.chat.completions.create(
-    deployment_name="gpt-35-turbo",
+    deployment_name="gpt-4o",
     # Specify a stream parameter
     stream=True,
     messages=[

tests/integration/configuration.py

@@ -0,0 +1,5 @@
+import os
+
+INTEGRATION_TEST_DEPLOYMENT_NAME = os.getenv(
+    "INTEGRATION_TEST_DEPLOYMENT_NAME", "gpt-4o"
+)

tests/integration/fixtures.py

@@ -35,7 +35,7 @@ def async_client(dial_url, dial_api_key):
 def test_deployment(sync_client: Dial) -> str:
     deployments = sync_client.deployments.list()
     assert len(deployments)
-    deployment = next((d for d in deployments if d.id.startswith("gpt-")))
+    deployment = next((d for d in deployments if d.id.startswith("gpt-4o")))
     assert deployment
     return deployment.id
 

tests/integration/test_async_completions.py

@@ -2,6 +2,7 @@
 
 from aidial_client import AsyncDial
 from aidial_client._exception import DialException
+from tests.integration.configuration import INTEGRATION_TEST_DEPLOYMENT_NAME
 from tests.integration.fixtures import *  # noqa
 
 
@@ -14,7 +15,7 @@ async def test_async_default_api_version(
 ):
     with pytest.raises(DialException):
         await async_client.chat.completions.create(
-            deployment_name="gpt-35-turbo",
+            deployment_name=INTEGRATION_TEST_DEPLOYMENT_NAME,
             stream=False,
             messages=[
                 {

tests/integration/test_sync_completions.py

@@ -2,6 +2,7 @@
 
 from aidial_client import Dial
 from aidial_client._exception import DialException
+from tests.integration.configuration import INTEGRATION_TEST_DEPLOYMENT_NAME
 from tests.integration.fixtures import *  # type: ignore # noqa
 
 
@@ -36,7 +37,7 @@ def test_default_api_version(
 ):
     with pytest.raises(DialException):
         sync_client.chat.completions.create(
-            deployment_name="gpt-35-turbo",
+            deployment_name=INTEGRATION_TEST_DEPLOYMENT_NAME,
             stream=False,
             messages=[
                 {
@@ -51,7 +52,7 @@ def test_default_api_version(
         api_version="2024-02-15-preview",
     )
     client_with_default_api_version.chat.completions.create(
-        deployment_name="gpt-35-turbo",
+        deployment_name=INTEGRATION_TEST_DEPLOYMENT_NAME,
         stream=False,
         messages=[
             {

tests/resources/completions/test_completions_streaming_tool_call.py

@@ -5,6 +5,7 @@
 
 from aidial_client.types.chat import ChatCompletionChunk, ToolParam
 from tests.client_mock import get_async_client_mock, get_client_mock
+from tests.integration.configuration import INTEGRATION_TEST_DEPLOYMENT_NAME
 from tests.utils.chunks import create_mock_chunk, create_sse_data_field
 
 _TOOL_DEFINITION: ToolParam = {
@@ -172,7 +173,7 @@ def test_sync_streaming_tool_call():
     )
 
     response = client.chat.completions.create(
-        deployment_name="gpt-35-turbo",
+        deployment_name=INTEGRATION_TEST_DEPLOYMENT_NAME,
         messages=[{"role": "user", "content": "what's the weather in Paris?"}],
         tools=[_TOOL_DEFINITION],
         stream=True,
@@ -190,7 +191,7 @@ async def test_async_streaming_tool_call():
         stream_chunks_mock=_STREAM_CHUNKS_MOCK,
     )
     response = await async_client.chat.completions.create(
-        deployment_name="gpt-35-turbo",
+        deployment_name=INTEGRATION_TEST_DEPLOYMENT_NAME,
         messages=[{"role": "user", "content": "what's the weather in Paris?"}],
         tools=[_TOOL_DEFINITION],
         stream=True,

tests/resources/completions/test_completions_streaming_vanilla.py

@@ -5,6 +5,7 @@
 
 from aidial_client.types.chat import ChatCompletionChunk
 from tests.client_mock import get_async_client_mock, get_client_mock
+from tests.integration.configuration import INTEGRATION_TEST_DEPLOYMENT_NAME
 from tests.utils.chunks import create_mock_chunk, create_sse_data_field
 
 STREAM_CHUNKS_MOCK: List[bytes] = [
@@ -53,7 +54,7 @@ def test_sync_streaming():
     )
 
     response = client.chat.completions.create(
-        deployment_name="gpt-35-turbo",
+        deployment_name=INTEGRATION_TEST_DEPLOYMENT_NAME,
         messages=[{"role": "user", "content": "2+3="}],
         stream=True,
     )
@@ -70,7 +71,7 @@ async def test_async_streaming():
         stream_chunks_mock=STREAM_CHUNKS_MOCK,
     )
     response = await async_client.chat.completions.create(
-        deployment_name="gpt-35-turbo",
+        deployment_name=INTEGRATION_TEST_DEPLOYMENT_NAME,
         messages=[{"role": "user", "content": "2+3="}],
         stream=True,
     )

tests/utils/chunks.py

@@ -1,6 +1,8 @@
 import json
 from typing import Optional, Union
 
+from tests.integration.configuration import INTEGRATION_TEST_DEPLOYMENT_NAME
+
 
 def create_mock_chunk(
     *,
@@ -19,7 +21,7 @@ def create_mock_chunk(
             }
         ],
         "created": 1723806872,
-        "model": "gpt-35-turbo",
+        "model": INTEGRATION_TEST_DEPLOYMENT_NAME,
         "object": "chat.completion.chunk",
         "system_fingerprint": None,
         **({} if usage is None else {"usage": usage}),