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
185
186
187
188
|
#### What this does ####
# On success, logs events to Helicone
import os
import traceback
import litellm
class HeliconeLogger:
# Class variables or attributes
helicone_model_list = [
"gpt",
"claude",
"command-r",
"command-r-plus",
"command-light",
"command-medium",
"command-medium-beta",
"command-xlarge-nightly",
"command-nightly",
]
def __init__(self):
# Instance variables
self.provider_url = "https://api.openai.com/v1"
self.key = os.getenv("HELICONE_API_KEY")
def claude_mapping(self, model, messages, response_obj):
from anthropic import AI_PROMPT, HUMAN_PROMPT
prompt = f"{HUMAN_PROMPT}"
for message in messages:
if "role" in message:
if message["role"] == "user":
prompt += f"{HUMAN_PROMPT}{message['content']}"
else:
prompt += f"{AI_PROMPT}{message['content']}"
else:
prompt += f"{HUMAN_PROMPT}{message['content']}"
prompt += f"{AI_PROMPT}"
choice = response_obj["choices"][0]
message = choice["message"]
content = []
if "tool_calls" in message and message["tool_calls"]:
for tool_call in message["tool_calls"]:
content.append(
{
"type": "tool_use",
"id": tool_call["id"],
"name": tool_call["function"]["name"],
"input": tool_call["function"]["arguments"],
}
)
elif "content" in message and message["content"]:
content = [{"type": "text", "text": message["content"]}]
claude_response_obj = {
"id": response_obj["id"],
"type": "message",
"role": "assistant",
"model": model,
"content": content,
"stop_reason": choice["finish_reason"],
"stop_sequence": None,
"usage": {
"input_tokens": response_obj["usage"]["prompt_tokens"],
"output_tokens": response_obj["usage"]["completion_tokens"],
},
}
return claude_response_obj
@staticmethod
def add_metadata_from_header(litellm_params: dict, metadata: dict) -> dict:
"""
Adds metadata from proxy request headers to Helicone logging if keys start with "helicone_"
and overwrites litellm_params.metadata if already included.
For example if you want to add custom property to your request, send
`headers: { ..., helicone-property-something: 1234 }` via proxy request.
"""
if litellm_params is None:
return metadata
if litellm_params.get("proxy_server_request") is None:
return metadata
if metadata is None:
metadata = {}
proxy_headers = (
litellm_params.get("proxy_server_request", {}).get("headers", {}) or {}
)
for header_key in proxy_headers:
if header_key.startswith("helicone_"):
metadata[header_key] = proxy_headers.get(header_key)
return metadata
def log_success(
self, model, messages, response_obj, start_time, end_time, print_verbose, kwargs
):
# Method definition
try:
print_verbose(
f"Helicone Logging - Enters logging function for model {model}"
)
litellm_params = kwargs.get("litellm_params", {})
kwargs.get("litellm_call_id", None)
metadata = litellm_params.get("metadata", {}) or {}
metadata = self.add_metadata_from_header(litellm_params, metadata)
model = (
model
if any(
accepted_model in model
for accepted_model in self.helicone_model_list
)
else "gpt-3.5-turbo"
)
provider_request = {"model": model, "messages": messages}
if isinstance(response_obj, litellm.EmbeddingResponse) or isinstance(
response_obj, litellm.ModelResponse
):
response_obj = response_obj.json()
if "claude" in model:
response_obj = self.claude_mapping(
model=model, messages=messages, response_obj=response_obj
)
providerResponse = {
"json": response_obj,
"headers": {"openai-version": "2020-10-01"},
"status": 200,
}
# Code to be executed
provider_url = self.provider_url
url = "https://api.hconeai.com/oai/v1/log"
if "claude" in model:
url = "https://api.hconeai.com/anthropic/v1/log"
provider_url = "https://api.anthropic.com/v1/messages"
headers = {
"Authorization": f"Bearer {self.key}",
"Content-Type": "application/json",
}
start_time_seconds = int(start_time.timestamp())
start_time_milliseconds = int(
(start_time.timestamp() - start_time_seconds) * 1000
)
end_time_seconds = int(end_time.timestamp())
end_time_milliseconds = int(
(end_time.timestamp() - end_time_seconds) * 1000
)
meta = {"Helicone-Auth": f"Bearer {self.key}"}
meta.update(metadata)
data = {
"providerRequest": {
"url": provider_url,
"json": provider_request,
"meta": meta,
},
"providerResponse": providerResponse,
"timing": {
"startTime": {
"seconds": start_time_seconds,
"milliseconds": start_time_milliseconds,
},
"endTime": {
"seconds": end_time_seconds,
"milliseconds": end_time_milliseconds,
},
}, # {"seconds": .., "milliseconds": ..}
}
response = litellm.module_level_client.post(url, headers=headers, json=data)
if response.status_code == 200:
print_verbose("Helicone Logging - Success!")
else:
print_verbose(
f"Helicone Logging - Error Request was not successful. Status Code: {response.status_code}"
)
print_verbose(f"Helicone Logging - Error {response.text}")
except Exception:
print_verbose(f"Helicone Logging Error - {traceback.format_exc()}")
pass
|
