File size: 4,847 Bytes
cfd3735
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
"""Test PromptLayerChatOpenAI wrapper."""

import pytest

from langchain.callbacks.manager import CallbackManager
from langchain.chat_models.promptlayer_openai import PromptLayerChatOpenAI
from langchain.schema import (
    BaseMessage,
    ChatGeneration,
    ChatResult,
    HumanMessage,
    LLMResult,
    SystemMessage,
)
from tests.unit_tests.callbacks.fake_callback_handler import FakeCallbackHandler


def test_promptlayer_chat_openai() -> None:
    """Test PromptLayerChatOpenAI wrapper."""
    chat = PromptLayerChatOpenAI(max_tokens=10)
    message = HumanMessage(content="Hello")
    response = chat([message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)


def test_promptlayer_chat_openai_system_message() -> None:
    """Test PromptLayerChatOpenAI wrapper with system message."""
    chat = PromptLayerChatOpenAI(max_tokens=10)
    system_message = SystemMessage(content="You are to chat with the user.")
    human_message = HumanMessage(content="Hello")
    response = chat([system_message, human_message])
    assert isinstance(response, BaseMessage)
    assert isinstance(response.content, str)


def test_promptlayer_chat_openai_generate() -> None:
    """Test PromptLayerChatOpenAI wrapper with generate."""
    chat = PromptLayerChatOpenAI(max_tokens=10, n=2)
    message = HumanMessage(content="Hello")
    response = chat.generate([[message], [message]])
    assert isinstance(response, LLMResult)
    assert len(response.generations) == 2
    for generations in response.generations:
        assert len(generations) == 2
        for generation in generations:
            assert isinstance(generation, ChatGeneration)
            assert isinstance(generation.text, str)
            assert generation.text == generation.message.content


def test_promptlayer_chat_openai_multiple_completions() -> None:
    """Test PromptLayerChatOpenAI wrapper with multiple completions."""
    chat = PromptLayerChatOpenAI(max_tokens=10, n=5)
    message = HumanMessage(content="Hello")
    response = chat._generate([message])
    assert isinstance(response, ChatResult)
    assert len(response.generations) == 5
    for generation in response.generations:
        assert isinstance(generation.message, BaseMessage)
        assert isinstance(generation.message.content, str)


def test_promptlayer_chat_openai_streaming() -> None:
    """Test that streaming correctly invokes on_llm_new_token callback."""
    callback_handler = FakeCallbackHandler()
    callback_manager = CallbackManager([callback_handler])
    chat = PromptLayerChatOpenAI(
        max_tokens=10,
        streaming=True,
        temperature=0,
        callback_manager=callback_manager,
        verbose=True,
    )
    message = HumanMessage(content="Hello")
    response = chat([message])
    assert callback_handler.llm_streams > 0
    assert isinstance(response, BaseMessage)


def test_promptlayer_chat_openai_invalid_streaming_params() -> None:
    """Test that streaming correctly invokes on_llm_new_token callback."""
    with pytest.raises(ValueError):
        PromptLayerChatOpenAI(
            max_tokens=10,
            streaming=True,
            temperature=0,
            n=5,
        )


@pytest.mark.asyncio
async def test_async_promptlayer_chat_openai() -> None:
    """Test async generation."""
    chat = PromptLayerChatOpenAI(max_tokens=10, n=2)
    message = HumanMessage(content="Hello")
    response = await chat.agenerate([[message], [message]])
    assert isinstance(response, LLMResult)
    assert len(response.generations) == 2
    for generations in response.generations:
        assert len(generations) == 2
        for generation in generations:
            assert isinstance(generation, ChatGeneration)
            assert isinstance(generation.text, str)
            assert generation.text == generation.message.content


@pytest.mark.asyncio
async def test_async_promptlayer_chat_openai_streaming() -> None:
    """Test that streaming correctly invokes on_llm_new_token callback."""
    callback_handler = FakeCallbackHandler()
    callback_manager = CallbackManager([callback_handler])
    chat = PromptLayerChatOpenAI(
        max_tokens=10,
        streaming=True,
        temperature=0,
        callback_manager=callback_manager,
        verbose=True,
    )
    message = HumanMessage(content="Hello")
    response = await chat.agenerate([[message], [message]])
    assert callback_handler.llm_streams > 0
    assert isinstance(response, LLMResult)
    assert len(response.generations) == 2
    for generations in response.generations:
        assert len(generations) == 1
        for generation in generations:
            assert isinstance(generation, ChatGeneration)
            assert isinstance(generation.text, str)
            assert generation.text == generation.message.content