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
|
# What is this?
## Handler file for a Custom Chat LLM
"""
- completion
- acompletion
- streaming
- async_streaming
"""
from typing import Any, AsyncIterator, Callable, Iterator, Optional, Union
import httpx
from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
from litellm.types.utils import GenericStreamingChunk
from litellm.utils import ImageResponse, ModelResponse
from .base import BaseLLM
class CustomLLMError(Exception): # use this for all your exceptions
def __init__(
self,
status_code,
message,
):
self.status_code = status_code
self.message = message
super().__init__(
self.message
) # Call the base class constructor with the parameters it needs
class CustomLLM(BaseLLM):
def __init__(self) -> None:
super().__init__()
def completion(
self,
model: str,
messages: list,
api_base: str,
custom_prompt_dict: dict,
model_response: ModelResponse,
print_verbose: Callable,
encoding,
api_key,
logging_obj,
optional_params: dict,
acompletion=None,
litellm_params=None,
logger_fn=None,
headers={},
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[HTTPHandler] = None,
) -> ModelResponse:
raise CustomLLMError(status_code=500, message="Not implemented yet!")
def streaming(
self,
model: str,
messages: list,
api_base: str,
custom_prompt_dict: dict,
model_response: ModelResponse,
print_verbose: Callable,
encoding,
api_key,
logging_obj,
optional_params: dict,
acompletion=None,
litellm_params=None,
logger_fn=None,
headers={},
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[HTTPHandler] = None,
) -> Iterator[GenericStreamingChunk]:
raise CustomLLMError(status_code=500, message="Not implemented yet!")
async def acompletion(
self,
model: str,
messages: list,
api_base: str,
custom_prompt_dict: dict,
model_response: ModelResponse,
print_verbose: Callable,
encoding,
api_key,
logging_obj,
optional_params: dict,
acompletion=None,
litellm_params=None,
logger_fn=None,
headers={},
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[AsyncHTTPHandler] = None,
) -> ModelResponse:
raise CustomLLMError(status_code=500, message="Not implemented yet!")
async def astreaming(
self,
model: str,
messages: list,
api_base: str,
custom_prompt_dict: dict,
model_response: ModelResponse,
print_verbose: Callable,
encoding,
api_key,
logging_obj,
optional_params: dict,
acompletion=None,
litellm_params=None,
logger_fn=None,
headers={},
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[AsyncHTTPHandler] = None,
) -> AsyncIterator[GenericStreamingChunk]:
raise CustomLLMError(status_code=500, message="Not implemented yet!")
def image_generation(
self,
model: str,
prompt: str,
api_key: Optional[str],
api_base: Optional[str],
model_response: ImageResponse,
optional_params: dict,
logging_obj: Any,
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[HTTPHandler] = None,
) -> ImageResponse:
raise CustomLLMError(status_code=500, message="Not implemented yet!")
async def aimage_generation(
self,
model: str,
prompt: str,
model_response: ImageResponse,
api_key: Optional[
str
], # dynamically set api_key - https://docs.litellm.ai/docs/set_keys#api_key
api_base: Optional[
str
], # dynamically set api_base - https://docs.litellm.ai/docs/set_keys#api_base
optional_params: dict,
logging_obj: Any,
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[AsyncHTTPHandler] = None,
) -> ImageResponse:
raise CustomLLMError(status_code=500, message="Not implemented yet!")
def custom_chat_llm_router(
async_fn: bool, stream: Optional[bool], custom_llm: CustomLLM
):
"""
Routes call to CustomLLM completion/acompletion/streaming/astreaming functions, based on call type
Validates if response is in expected format
"""
if async_fn:
if stream:
return custom_llm.astreaming
return custom_llm.acompletion
if stream:
return custom_llm.streaming
return custom_llm.completion
|
