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
|
import json
import time
from typing import Callable
import litellm
from litellm.types.utils import ModelResponse, Usage
class BasetenError(Exception):
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
def validate_environment(api_key):
headers = {
"accept": "application/json",
"content-type": "application/json",
}
if api_key:
headers["Authorization"] = f"Api-Key {api_key}"
return headers
def completion(
model: str,
messages: list,
model_response: ModelResponse,
print_verbose: Callable,
encoding,
api_key,
logging_obj,
optional_params: dict,
litellm_params=None,
logger_fn=None,
):
headers = validate_environment(api_key)
completion_url_fragment_1 = "https://app.baseten.co/models/"
completion_url_fragment_2 = "/predict"
model = model
prompt = ""
for message in messages:
if "role" in message:
if message["role"] == "user":
prompt += f"{message['content']}"
else:
prompt += f"{message['content']}"
else:
prompt += f"{message['content']}"
data = {
"inputs": prompt,
"prompt": prompt,
"parameters": optional_params,
"stream": (
True
if "stream" in optional_params and optional_params["stream"] is True
else False
),
}
## LOGGING
logging_obj.pre_call(
input=prompt,
api_key=api_key,
additional_args={"complete_input_dict": data},
)
## COMPLETION CALL
response = litellm.module_level_client.post(
completion_url_fragment_1 + model + completion_url_fragment_2,
headers=headers,
data=json.dumps(data),
stream=(
True
if "stream" in optional_params and optional_params["stream"] is True
else False
),
)
if "text/event-stream" in response.headers["Content-Type"] or (
"stream" in optional_params and optional_params["stream"] is True
):
return response.iter_lines()
else:
## LOGGING
logging_obj.post_call(
input=prompt,
api_key=api_key,
original_response=response.text,
additional_args={"complete_input_dict": data},
)
print_verbose(f"raw model_response: {response.text}")
## RESPONSE OBJECT
completion_response = response.json()
if "error" in completion_response:
raise BasetenError(
message=completion_response["error"],
status_code=response.status_code,
)
else:
if "model_output" in completion_response:
if (
isinstance(completion_response["model_output"], dict)
and "data" in completion_response["model_output"]
and isinstance(completion_response["model_output"]["data"], list)
):
model_response.choices[0].message.content = completion_response[ # type: ignore
"model_output"
][
"data"
][
0
]
elif isinstance(completion_response["model_output"], str):
model_response.choices[0].message.content = completion_response[ # type: ignore
"model_output"
]
elif "completion" in completion_response and isinstance(
completion_response["completion"], str
):
model_response.choices[0].message.content = completion_response[ # type: ignore
"completion"
]
elif isinstance(completion_response, list) and len(completion_response) > 0:
if "generated_text" not in completion_response:
raise BasetenError(
message=f"Unable to parse response. Original response: {response.text}",
status_code=response.status_code,
)
model_response.choices[0].message.content = completion_response[0][ # type: ignore
"generated_text"
]
## GETTING LOGPROBS
if (
"details" in completion_response[0]
and "tokens" in completion_response[0]["details"]
):
model_response.choices[0].finish_reason = completion_response[0][
"details"
]["finish_reason"]
sum_logprob = 0
for token in completion_response[0]["details"]["tokens"]:
sum_logprob += token["logprob"]
model_response.choices[0].logprobs = sum_logprob # type: ignore
else:
raise BasetenError(
message=f"Unable to parse response. Original response: {response.text}",
status_code=response.status_code,
)
## CALCULATING USAGE - baseten charges on time, not tokens - have some mapping of cost here.
prompt_tokens = len(encoding.encode(prompt))
completion_tokens = len(
encoding.encode(model_response["choices"][0]["message"]["content"])
)
model_response.created = int(time.time())
model_response.model = model
usage = Usage(
prompt_tokens=prompt_tokens,
completion_tokens=completion_tokens,
total_tokens=prompt_tokens + completion_tokens,
)
setattr(model_response, "usage", usage)
return model_response
def embedding():
# logic for parsing in - calling - parsing out model embedding calls
pass
|
