Spaces:
Configuration error
Configuration error
File size: 8,467 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 |
from typing import Any, AsyncIterator, Coroutine, Dict, List, Optional, Union, cast
import litellm
from litellm.llms.anthropic.experimental_pass_through.adapters.transformation import (
AnthropicAdapter,
)
from litellm.types.llms.anthropic_messages.anthropic_response import (
AnthropicMessagesResponse,
)
from litellm.types.utils import ModelResponse
########################################################
# init adapter
ANTHROPIC_ADAPTER = AnthropicAdapter()
########################################################
class LiteLLMMessagesToCompletionTransformationHandler:
@staticmethod
def _prepare_completion_kwargs(
*,
max_tokens: int,
messages: List[Dict],
model: str,
metadata: Optional[Dict] = None,
stop_sequences: Optional[List[str]] = None,
stream: Optional[bool] = False,
system: Optional[str] = None,
temperature: Optional[float] = None,
thinking: Optional[Dict] = None,
tool_choice: Optional[Dict] = None,
tools: Optional[List[Dict]] = None,
top_k: Optional[int] = None,
top_p: Optional[float] = None,
extra_kwargs: Optional[Dict[str, Any]] = None,
) -> Dict[str, Any]:
"""Prepare kwargs for litellm.completion/acompletion"""
request_data = {
"model": model,
"messages": messages,
"max_tokens": max_tokens,
}
if metadata:
request_data["metadata"] = metadata
if stop_sequences:
request_data["stop_sequences"] = stop_sequences
if system:
request_data["system"] = system
if temperature is not None:
request_data["temperature"] = temperature
if thinking:
request_data["thinking"] = thinking
if tool_choice:
request_data["tool_choice"] = tool_choice
if tools:
request_data["tools"] = tools
if top_k is not None:
request_data["top_k"] = top_k
if top_p is not None:
request_data["top_p"] = top_p
openai_request = ANTHROPIC_ADAPTER.translate_completion_input_params(
request_data
)
if openai_request is None:
raise ValueError("Failed to translate request to OpenAI format")
completion_kwargs: Dict[str, Any] = dict(openai_request)
if stream:
completion_kwargs["stream"] = stream
excluded_keys = {"litellm_logging_obj", "anthropic_messages"}
extra_kwargs = extra_kwargs or {}
for key, value in extra_kwargs.items():
if (
key not in excluded_keys
and key not in completion_kwargs
and value is not None
):
completion_kwargs[key] = value
return completion_kwargs
@staticmethod
async def async_anthropic_messages_handler(
max_tokens: int,
messages: List[Dict],
model: str,
metadata: Optional[Dict] = None,
stop_sequences: Optional[List[str]] = None,
stream: Optional[bool] = False,
system: Optional[str] = None,
temperature: Optional[float] = None,
thinking: Optional[Dict] = None,
tool_choice: Optional[Dict] = None,
tools: Optional[List[Dict]] = None,
top_k: Optional[int] = None,
top_p: Optional[float] = None,
**kwargs,
) -> Union[AnthropicMessagesResponse, AsyncIterator]:
"""Handle non-Anthropic models asynchronously using the adapter"""
completion_kwargs = (
LiteLLMMessagesToCompletionTransformationHandler._prepare_completion_kwargs(
max_tokens=max_tokens,
messages=messages,
model=model,
metadata=metadata,
stop_sequences=stop_sequences,
stream=stream,
system=system,
temperature=temperature,
thinking=thinking,
tool_choice=tool_choice,
tools=tools,
top_k=top_k,
top_p=top_p,
extra_kwargs=kwargs,
)
)
try:
completion_response = await litellm.acompletion(**completion_kwargs)
if stream:
transformed_stream = (
ANTHROPIC_ADAPTER.translate_completion_output_params_streaming(
completion_response
)
)
if transformed_stream is not None:
return transformed_stream
raise ValueError("Failed to transform streaming response")
else:
anthropic_response = (
ANTHROPIC_ADAPTER.translate_completion_output_params(
cast(ModelResponse, completion_response)
)
)
if anthropic_response is not None:
return anthropic_response
raise ValueError("Failed to transform response to Anthropic format")
except Exception as e: # noqa: BLE001
raise ValueError(
f"Error calling litellm.acompletion for non-Anthropic model: {str(e)}"
)
@staticmethod
def anthropic_messages_handler(
max_tokens: int,
messages: List[Dict],
model: str,
metadata: Optional[Dict] = None,
stop_sequences: Optional[List[str]] = None,
stream: Optional[bool] = False,
system: Optional[str] = None,
temperature: Optional[float] = None,
thinking: Optional[Dict] = None,
tool_choice: Optional[Dict] = None,
tools: Optional[List[Dict]] = None,
top_k: Optional[int] = None,
top_p: Optional[float] = None,
_is_async: bool = False,
**kwargs,
) -> Union[
AnthropicMessagesResponse,
AsyncIterator[Any],
Coroutine[Any, Any, Union[AnthropicMessagesResponse, AsyncIterator[Any]]],
]:
"""Handle non-Anthropic models using the adapter."""
if _is_async is True:
return LiteLLMMessagesToCompletionTransformationHandler.async_anthropic_messages_handler(
max_tokens=max_tokens,
messages=messages,
model=model,
metadata=metadata,
stop_sequences=stop_sequences,
stream=stream,
system=system,
temperature=temperature,
thinking=thinking,
tool_choice=tool_choice,
tools=tools,
top_k=top_k,
top_p=top_p,
**kwargs,
)
completion_kwargs = (
LiteLLMMessagesToCompletionTransformationHandler._prepare_completion_kwargs(
max_tokens=max_tokens,
messages=messages,
model=model,
metadata=metadata,
stop_sequences=stop_sequences,
stream=stream,
system=system,
temperature=temperature,
thinking=thinking,
tool_choice=tool_choice,
tools=tools,
top_k=top_k,
top_p=top_p,
extra_kwargs=kwargs,
)
)
try:
completion_response = litellm.completion(**completion_kwargs)
if stream:
transformed_stream = (
ANTHROPIC_ADAPTER.translate_completion_output_params_streaming(
completion_response
)
)
if transformed_stream is not None:
return transformed_stream
raise ValueError("Failed to transform streaming response")
else:
anthropic_response = (
ANTHROPIC_ADAPTER.translate_completion_output_params(
cast(ModelResponse, completion_response)
)
)
if anthropic_response is not None:
return anthropic_response
raise ValueError("Failed to transform response to Anthropic format")
except Exception as e: # noqa: BLE001
raise ValueError(
f"Error calling litellm.completion for non-Anthropic model: {str(e)}"
)
|