Spaces:
Runtime error
Runtime error
File size: 10,717 Bytes
ed4d993 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 |
"""Wrapper around Perplexity APIs."""
from __future__ import annotations
import logging
from typing import (
Any,
Dict,
Iterator,
List,
Mapping,
Optional,
Tuple,
Type,
Union,
)
from langchain_core.callbacks import CallbackManagerForLLMRun
from langchain_core.language_models.chat_models import (
BaseChatModel,
generate_from_stream,
)
from langchain_core.messages import (
AIMessage,
AIMessageChunk,
BaseMessage,
BaseMessageChunk,
ChatMessage,
ChatMessageChunk,
FunctionMessageChunk,
HumanMessage,
HumanMessageChunk,
SystemMessage,
SystemMessageChunk,
ToolMessageChunk,
)
from langchain_core.outputs import ChatGeneration, ChatGenerationChunk, ChatResult
from langchain_core.pydantic_v1 import Field, root_validator
from langchain_core.utils import get_from_dict_or_env, get_pydantic_field_names
logger = logging.getLogger(__name__)
class ChatPerplexity(BaseChatModel):
"""`Perplexity AI` Chat models API.
To use, you should have the ``openai`` python package installed, and the
environment variable ``PPLX_API_KEY`` set to your API key.
Any parameters that are valid to be passed to the openai.create call can be passed
in, even if not explicitly saved on this class.
Example:
.. code-block:: python
from langchain_community.chat_models import ChatPerplexity
chat = ChatPerplexity(model="pplx-70b-online", temperature=0.7)
"""
client: Any #: :meta private:
model: str = "pplx-70b-online"
"""Model name."""
temperature: float = 0.7
"""What sampling temperature to use."""
model_kwargs: Dict[str, Any] = Field(default_factory=dict)
"""Holds any model parameters valid for `create` call not explicitly specified."""
pplx_api_key: Optional[str] = Field(None, alias="api_key")
"""Base URL path for API requests,
leave blank if not using a proxy or service emulator."""
request_timeout: Optional[Union[float, Tuple[float, float]]] = Field(
None, alias="timeout"
)
"""Timeout for requests to PerplexityChat completion API. Default is 600 seconds."""
max_retries: int = 6
"""Maximum number of retries to make when generating."""
streaming: bool = False
"""Whether to stream the results or not."""
max_tokens: Optional[int] = None
"""Maximum number of tokens to generate."""
class Config:
"""Configuration for this pydantic object."""
allow_population_by_field_name = True
@property
def lc_secrets(self) -> Dict[str, str]:
return {"pplx_api_key": "PPLX_API_KEY"}
@root_validator(pre=True, allow_reuse=True)
def build_extra(cls, values: Dict[str, Any]) -> Dict[str, Any]:
"""Build extra kwargs from additional params that were passed in."""
all_required_field_names = get_pydantic_field_names(cls)
extra = values.get("model_kwargs", {})
for field_name in list(values):
if field_name in extra:
raise ValueError(f"Found {field_name} supplied twice.")
if field_name not in all_required_field_names:
logger.warning(
f"""WARNING! {field_name} is not a default parameter.
{field_name} was transferred to model_kwargs.
Please confirm that {field_name} is what you intended."""
)
extra[field_name] = values.pop(field_name)
invalid_model_kwargs = all_required_field_names.intersection(extra.keys())
if invalid_model_kwargs:
raise ValueError(
f"Parameters {invalid_model_kwargs} should be specified explicitly. "
f"Instead they were passed in as part of `model_kwargs` parameter."
)
values["model_kwargs"] = extra
return values
@root_validator(allow_reuse=True)
def validate_environment(cls, values: Dict) -> Dict:
"""Validate that api key and python package exists in environment."""
values["pplx_api_key"] = get_from_dict_or_env(
values, "pplx_api_key", "PPLX_API_KEY"
)
try:
import openai
except ImportError:
raise ImportError(
"Could not import openai python package. "
"Please install it with `pip install openai`."
)
try:
values["client"] = openai.OpenAI(
api_key=values["pplx_api_key"], base_url="https://api.perplexity.ai"
)
except AttributeError:
raise ValueError(
"`openai` has no `ChatCompletion` attribute, this is likely "
"due to an old version of the openai package. Try upgrading it "
"with `pip install --upgrade openai`."
)
return values
@property
def _default_params(self) -> Dict[str, Any]:
"""Get the default parameters for calling PerplexityChat API."""
return {
"request_timeout": self.request_timeout,
"max_tokens": self.max_tokens,
"stream": self.streaming,
"temperature": self.temperature,
**self.model_kwargs,
}
def _convert_message_to_dict(self, message: BaseMessage) -> Dict[str, Any]:
if isinstance(message, ChatMessage):
message_dict = {"role": message.role, "content": message.content}
elif isinstance(message, SystemMessage):
message_dict = {"role": "system", "content": message.content}
elif isinstance(message, HumanMessage):
message_dict = {"role": "user", "content": message.content}
elif isinstance(message, AIMessage):
message_dict = {"role": "assistant", "content": message.content}
else:
raise TypeError(f"Got unknown type {message}")
return message_dict
def _create_message_dicts(
self, messages: List[BaseMessage], stop: Optional[List[str]]
) -> Tuple[List[Dict[str, Any]], Dict[str, Any]]:
params = dict(self._invocation_params)
if stop is not None:
if "stop" in params:
raise ValueError("`stop` found in both the input and default params.")
params["stop"] = stop
message_dicts = [self._convert_message_to_dict(m) for m in messages]
return message_dicts, params
def _convert_delta_to_message_chunk(
self, _dict: Mapping[str, Any], default_class: Type[BaseMessageChunk]
) -> BaseMessageChunk:
role = _dict.get("role")
content = _dict.get("content") or ""
additional_kwargs: Dict = {}
if _dict.get("function_call"):
function_call = dict(_dict["function_call"])
if "name" in function_call and function_call["name"] is None:
function_call["name"] = ""
additional_kwargs["function_call"] = function_call
if _dict.get("tool_calls"):
additional_kwargs["tool_calls"] = _dict["tool_calls"]
if role == "user" or default_class == HumanMessageChunk:
return HumanMessageChunk(content=content)
elif role == "assistant" or default_class == AIMessageChunk:
return AIMessageChunk(content=content, additional_kwargs=additional_kwargs)
elif role == "system" or default_class == SystemMessageChunk:
return SystemMessageChunk(content=content)
elif role == "function" or default_class == FunctionMessageChunk:
return FunctionMessageChunk(content=content, name=_dict["name"])
elif role == "tool" or default_class == ToolMessageChunk:
return ToolMessageChunk(content=content, tool_call_id=_dict["tool_call_id"])
elif role or default_class == ChatMessageChunk:
return ChatMessageChunk(content=content, role=role) # type: ignore[arg-type]
else:
return default_class(content=content) # type: ignore[call-arg]
def _stream(
self,
messages: List[BaseMessage],
stop: Optional[List[str]] = None,
run_manager: Optional[CallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> Iterator[ChatGenerationChunk]:
message_dicts, params = self._create_message_dicts(messages, stop)
params = {**params, **kwargs}
default_chunk_class = AIMessageChunk
if stop:
params["stop_sequences"] = stop
stream_resp = self.client.chat.completions.create(
model=params["model"], messages=message_dicts, stream=True
)
for chunk in stream_resp:
if not isinstance(chunk, dict):
chunk = chunk.dict()
if len(chunk["choices"]) == 0:
continue
choice = chunk["choices"][0]
chunk = self._convert_delta_to_message_chunk(
choice["delta"], default_chunk_class
)
finish_reason = choice.get("finish_reason")
generation_info = (
dict(finish_reason=finish_reason) if finish_reason is not None else None
)
default_chunk_class = chunk.__class__
chunk = ChatGenerationChunk(message=chunk, generation_info=generation_info)
if run_manager:
run_manager.on_llm_new_token(chunk.text, chunk=chunk)
yield chunk
def _generate(
self,
messages: List[BaseMessage],
stop: Optional[List[str]] = None,
run_manager: Optional[CallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> ChatResult:
if self.streaming:
stream_iter = self._stream(
messages, stop=stop, run_manager=run_manager, **kwargs
)
if stream_iter:
return generate_from_stream(stream_iter)
message_dicts, params = self._create_message_dicts(messages, stop)
params = {**params, **kwargs}
response = self.client.chat.completions.create(
model=params["model"], messages=message_dicts
)
message = AIMessage(content=response.choices[0].message.content)
return ChatResult(generations=[ChatGeneration(message=message)])
@property
def _invocation_params(self) -> Mapping[str, Any]:
"""Get the parameters used to invoke the model."""
pplx_creds: Dict[str, Any] = {
"api_key": self.pplx_api_key,
"api_base": "https://api.perplexity.ai",
"model": self.model,
}
return {**pplx_creds, **self._default_params}
@property
def _llm_type(self) -> str:
"""Return type of chat model."""
return "perplexitychat"
|