File size: 4,671 Bytes
395201c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# ##### THESE TESTS CAN ONLY RUN LOCALLY WITH THE OLLAMA SERVER RUNNING ######
# # https://ollama.ai/

# import sys, os
# import traceback
# from dotenv import load_dotenv
# load_dotenv()
# import os
# sys.path.insert(0, os.path.abspath('../..'))  # Adds the parent directory to the system path
# import pytest
# import litellm
# from litellm import embedding, completion
# import asyncio


# user_message = "respond in 20 words. who are you?"
# messages = [{ "content": user_message,"role": "user"}]

# def test_completion_ollama():
#     try:
#         response = completion(
#             model="ollama/llama2", 
#             messages=messages, 
#             max_tokens=200,
#             request_timeout = 10,

#         )
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# test_completion_ollama()

# def test_completion_ollama_with_api_base():
#     try:
#         response = completion(
#             model="ollama/llama2", 
#             messages=messages, 
#             api_base="http://localhost:11434"
#         )
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# test_completion_ollama_with_api_base()


# def test_completion_ollama_custom_prompt_template():
#     user_message = "what is litellm?"
#     litellm.register_prompt_template(
#         model="ollama/llama2",
#         roles={
#             "system": {"pre_message": "System: "},
#             "user": {"pre_message": "User: "},
#             "assistant": {"pre_message": "Assistant: "}
#         }
#     )
#     messages = [{ "content": user_message,"role": "user"}]
#     litellm.set_verbose = True
#     try:
#         response = completion(
#             model="ollama/llama2", 
#             messages=messages, 
#             stream=True
#         )
#         print(response)
#         for chunk in response:
#             print(chunk)
#             # print(chunk['choices'][0]['delta'])

#     except Exception as e:
#         traceback.print_exc()
#         pytest.fail(f"Error occurred: {e}")

# test_completion_ollama_custom_prompt_template()

# async def test_completion_ollama_async_stream():
#     user_message = "what is the weather"
#     messages = [{ "content": user_message,"role": "user"}]
#     try:
#         response = await litellm.acompletion(
#             model="ollama/llama2", 
#             messages=messages, 
#             api_base="http://localhost:11434", 
#             stream=True
#         )
#         async for chunk in response:
#             print(chunk['choices'][0]['delta'])
        

#         print("TEST ASYNC NON Stream")
#         response = await litellm.acompletion(
#             model="ollama/llama2", 
#             messages=messages, 
#             api_base="http://localhost:11434", 
#         )
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# import asyncio
# asyncio.run(test_completion_ollama_async_stream())



# def prepare_messages_for_chat(text: str) -> list:
#     messages = [
#         {"role": "user", "content": text},
#     ]
#     return messages


# async def ask_question():
#     params = {
#         "messages": prepare_messages_for_chat("What is litellm? tell me 10 things about it who is sihaan.write an essay"),
#         "api_base": "http://localhost:11434",
#         "model": "ollama/llama2",
#         "stream": True,
#     }
#     response = await litellm.acompletion(**params)
#     return response

# async def main():
#     response = await ask_question()
#     async for chunk in response:
#         print(chunk)
    
#     print("test async completion without streaming")
#     response = await litellm.acompletion(
#         model="ollama/llama2",
#         messages=prepare_messages_for_chat("What is litellm? respond in 2 words"),
#     )
#     print("response", response)


# def test_completion_expect_error():
#     # this tests if we can exception map correctly for ollama
#     print("making ollama request")
#     # litellm.set_verbose=True
#     user_message = "what is litellm?"
#     messages = [{ "content": user_message,"role": "user"}]
#     try:
#         response = completion(
#             model="ollama/invalid", 
#             messages=messages, 
#             stream=True
#         )
#         print(response)
#         for chunk in response:
#             print(chunk)
#             # print(chunk['choices'][0]['delta'])

#     except Exception as e:
#         pass
#         pytest.fail(f"Error occurred: {e}")

# test_completion_expect_error()

# if __name__ == "__main__":
#     import asyncio
#     asyncio.run(main())