File size: 5,808 Bytes
447ebeb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
import json
import os
import sys
from datetime import datetime
from unittest.mock import AsyncMock

sys.path.insert(
    0, os.path.abspath("../..")
)  # Adds the parent directory to the system path


import httpx
import pytest
from respx import MockRouter
from unittest.mock import patch, MagicMock, AsyncMock

import litellm
from litellm import Choices, Message, ModelResponse, EmbeddingResponse, Usage
from litellm import completion


def test_completion_nvidia_nim():
    from openai import OpenAI

    litellm.set_verbose = True
    model_name = "nvidia_nim/databricks/dbrx-instruct"
    client = OpenAI(
        api_key="fake-api-key",
    )

    with patch.object(
        client.chat.completions.with_raw_response, "create"
    ) as mock_client:
        try:
            completion(
                model=model_name,
                messages=[
                    {
                        "role": "user",
                        "content": "What's the weather like in Boston today in Fahrenheit?",
                    }
                ],
                presence_penalty=0.5,
                frequency_penalty=0.1,
                client=client,
            )
        except Exception as e:
            print(e)
        # Add any assertions here to check the response

        mock_client.assert_called_once()
        request_body = mock_client.call_args.kwargs

        print("request_body: ", request_body)

        assert request_body["messages"] == [
            {
                "role": "user",
                "content": "What's the weather like in Boston today in Fahrenheit?",
            },
        ]
        assert request_body["model"] == "databricks/dbrx-instruct"
        assert request_body["frequency_penalty"] == 0.1
        assert request_body["presence_penalty"] == 0.5


def test_embedding_nvidia_nim():
    litellm.set_verbose = True
    from openai import OpenAI

    client = OpenAI(
        api_key="fake-api-key",
    )
    with patch.object(client.embeddings.with_raw_response, "create") as mock_client:
        try:
            litellm.embedding(
                model="nvidia_nim/nvidia/nv-embedqa-e5-v5",
                input="What is the meaning of life?",
                input_type="passage",
                dimensions=1024,
                client=client,
            )
        except Exception as e:
            print(e)
        mock_client.assert_called_once()
        request_body = mock_client.call_args.kwargs
        print("request_body: ", request_body)
        assert request_body["input"] == "What is the meaning of life?"
        assert request_body["model"] == "nvidia/nv-embedqa-e5-v5"
        assert request_body["extra_body"]["input_type"] == "passage"
        assert request_body["dimensions"] == 1024


def test_chat_completion_nvidia_nim_with_tools():
    from openai import OpenAI

    litellm.set_verbose = True
    model_name = "nvidia_nim/meta/llama3-70b-instruct"
    client = OpenAI(
        api_key="fake-api-key",
    )

    # Define tools
    tools = [
        {
            "type": "function",
            "function": {
                "name": "get_weather",
                "description": "Get the current weather in a given location",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "location": {
                            "type": "string",
                            "description": "The city and state, e.g. San Francisco, CA",
                        },
                        "unit": {
                            "type": "string",
                            "enum": ["celsius", "fahrenheit"],
                            "description": "The unit of temperature to use",
                        },
                    },
                    "required": ["location"],
                },
            },
        },
        {
            "type": "function",
            "function": {
                "name": "get_current_time",
                "description": "Get the current time in a given timezone",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "timezone": {
                            "type": "string",
                            "description": "The timezone, e.g. EST, PST",
                        },
                    },
                    "required": ["timezone"],
                },
            },
        },
    ]

    with patch.object(
        client.chat.completions.with_raw_response, "create"
    ) as mock_client:
        try:
            completion(
                model=model_name,
                messages=[
                    {
                        "role": "user",
                        "content": "What's the weather like in Boston today and what time is it in EST?",
                    }
                ],
                tools=tools,
                tool_choice="auto",
                parallel_tool_calls=True,
                temperature=0.7,
                client=client,
            )
        except Exception as e:
            print(e)
        
        # Add assertions to check the request
        mock_client.assert_called_once()
        request_body = mock_client.call_args.kwargs

        print("request_body: ", request_body)

        assert request_body["messages"] == [
            {
                "role": "user",
                "content": "What's the weather like in Boston today and what time is it in EST?",
            },
        ]
        assert request_body["model"] == "meta/llama3-70b-instruct"
        assert request_body["temperature"] == 0.7
        assert request_body["tools"] == tools
        assert request_body["tool_choice"] == "auto"
        assert request_body["parallel_tool_calls"] == True