Spaces:
Runtime error
Runtime error
File size: 12,347 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 |
from __future__ import annotations
import importlib
from typing import (
Any,
AsyncIterator,
Dict,
Iterable,
List,
Mapping,
Sequence,
Union,
overload,
)
from langchain_core.chat_sessions import ChatSession
from langchain_core.messages import (
AIMessage,
AIMessageChunk,
BaseMessage,
BaseMessageChunk,
ChatMessage,
FunctionMessage,
HumanMessage,
SystemMessage,
ToolMessage,
)
from langchain_core.pydantic_v1 import BaseModel
from typing_extensions import Literal
async def aenumerate(
iterable: AsyncIterator[Any], start: int = 0
) -> AsyncIterator[tuple[int, Any]]:
"""Async version of enumerate function."""
i = start
async for x in iterable:
yield i, x
i += 1
class IndexableBaseModel(BaseModel):
"""Allows a BaseModel to return its fields by string variable indexing."""
def __getitem__(self, item: str) -> Any:
return getattr(self, item)
class Choice(IndexableBaseModel):
"""Choice."""
message: dict
class ChatCompletions(IndexableBaseModel):
"""Chat completions."""
choices: List[Choice]
class ChoiceChunk(IndexableBaseModel):
"""Choice chunk."""
delta: dict
class ChatCompletionChunk(IndexableBaseModel):
"""Chat completion chunk."""
choices: List[ChoiceChunk]
def convert_dict_to_message(_dict: Mapping[str, Any]) -> BaseMessage:
"""Convert a dictionary to a LangChain message.
Args:
_dict: The dictionary.
Returns:
The LangChain message.
"""
role = _dict.get("role")
if role == "user":
return HumanMessage(content=_dict.get("content", ""))
elif role == "assistant":
# Fix for azure
# Also OpenAI returns None for tool invocations
content = _dict.get("content", "") or ""
additional_kwargs: Dict = {}
if function_call := _dict.get("function_call"):
additional_kwargs["function_call"] = dict(function_call)
if tool_calls := _dict.get("tool_calls"):
additional_kwargs["tool_calls"] = tool_calls
return AIMessage(content=content, additional_kwargs=additional_kwargs)
elif role == "system":
return SystemMessage(content=_dict.get("content", ""))
elif role == "function":
return FunctionMessage(content=_dict.get("content", ""), name=_dict.get("name")) # type: ignore[arg-type]
elif role == "tool":
additional_kwargs = {}
if "name" in _dict:
additional_kwargs["name"] = _dict["name"]
return ToolMessage(
content=_dict.get("content", ""),
tool_call_id=_dict.get("tool_call_id"), # type: ignore[arg-type]
additional_kwargs=additional_kwargs,
)
else:
return ChatMessage(content=_dict.get("content", ""), role=role) # type: ignore[arg-type]
def convert_message_to_dict(message: BaseMessage) -> dict:
"""Convert a LangChain message to a dictionary.
Args:
message: The LangChain message.
Returns:
The dictionary.
"""
message_dict: Dict[str, Any]
if isinstance(message, ChatMessage):
message_dict = {"role": message.role, "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}
if "function_call" in message.additional_kwargs:
message_dict["function_call"] = message.additional_kwargs["function_call"]
# If function call only, content is None not empty string
if message_dict["content"] == "":
message_dict["content"] = None
if "tool_calls" in message.additional_kwargs:
message_dict["tool_calls"] = message.additional_kwargs["tool_calls"]
# If tool calls only, content is None not empty string
if message_dict["content"] == "":
message_dict["content"] = None
elif isinstance(message, SystemMessage):
message_dict = {"role": "system", "content": message.content}
elif isinstance(message, FunctionMessage):
message_dict = {
"role": "function",
"content": message.content,
"name": message.name,
}
elif isinstance(message, ToolMessage):
message_dict = {
"role": "tool",
"content": message.content,
"tool_call_id": message.tool_call_id,
}
else:
raise TypeError(f"Got unknown type {message}")
if "name" in message.additional_kwargs:
message_dict["name"] = message.additional_kwargs["name"]
return message_dict
def convert_openai_messages(messages: Sequence[Dict[str, Any]]) -> List[BaseMessage]:
"""Convert dictionaries representing OpenAI messages to LangChain format.
Args:
messages: List of dictionaries representing OpenAI messages
Returns:
List of LangChain BaseMessage objects.
"""
return [convert_dict_to_message(m) for m in messages]
def _convert_message_chunk(chunk: BaseMessageChunk, i: int) -> dict:
_dict: Dict[str, Any] = {}
if isinstance(chunk, AIMessageChunk):
if i == 0:
# Only shows up in the first chunk
_dict["role"] = "assistant"
if "function_call" in chunk.additional_kwargs:
_dict["function_call"] = chunk.additional_kwargs["function_call"]
# If the first chunk is a function call, the content is not empty string,
# not missing, but None.
if i == 0:
_dict["content"] = None
else:
_dict["content"] = chunk.content
else:
raise ValueError(f"Got unexpected streaming chunk type: {type(chunk)}")
# This only happens at the end of streams, and OpenAI returns as empty dict
if _dict == {"content": ""}:
_dict = {}
return _dict
def _convert_message_chunk_to_delta(chunk: BaseMessageChunk, i: int) -> Dict[str, Any]:
_dict = _convert_message_chunk(chunk, i)
return {"choices": [{"delta": _dict}]}
class ChatCompletion:
"""Chat completion."""
@overload
@staticmethod
def create(
messages: Sequence[Dict[str, Any]],
*,
provider: str = "ChatOpenAI",
stream: Literal[False] = False,
**kwargs: Any,
) -> dict:
...
@overload
@staticmethod
def create(
messages: Sequence[Dict[str, Any]],
*,
provider: str = "ChatOpenAI",
stream: Literal[True],
**kwargs: Any,
) -> Iterable:
...
@staticmethod
def create(
messages: Sequence[Dict[str, Any]],
*,
provider: str = "ChatOpenAI",
stream: bool = False,
**kwargs: Any,
) -> Union[dict, Iterable]:
models = importlib.import_module("langchain.chat_models")
model_cls = getattr(models, provider)
model_config = model_cls(**kwargs)
converted_messages = convert_openai_messages(messages)
if not stream:
result = model_config.invoke(converted_messages)
return {"choices": [{"message": convert_message_to_dict(result)}]}
else:
return (
_convert_message_chunk_to_delta(c, i)
for i, c in enumerate(model_config.stream(converted_messages))
)
@overload
@staticmethod
async def acreate(
messages: Sequence[Dict[str, Any]],
*,
provider: str = "ChatOpenAI",
stream: Literal[False] = False,
**kwargs: Any,
) -> dict:
...
@overload
@staticmethod
async def acreate(
messages: Sequence[Dict[str, Any]],
*,
provider: str = "ChatOpenAI",
stream: Literal[True],
**kwargs: Any,
) -> AsyncIterator:
...
@staticmethod
async def acreate(
messages: Sequence[Dict[str, Any]],
*,
provider: str = "ChatOpenAI",
stream: bool = False,
**kwargs: Any,
) -> Union[dict, AsyncIterator]:
models = importlib.import_module("langchain.chat_models")
model_cls = getattr(models, provider)
model_config = model_cls(**kwargs)
converted_messages = convert_openai_messages(messages)
if not stream:
result = await model_config.ainvoke(converted_messages)
return {"choices": [{"message": convert_message_to_dict(result)}]}
else:
return (
_convert_message_chunk_to_delta(c, i)
async for i, c in aenumerate(model_config.astream(converted_messages))
)
def _has_assistant_message(session: ChatSession) -> bool:
"""Check if chat session has an assistant message."""
return any([isinstance(m, AIMessage) for m in session["messages"]])
def convert_messages_for_finetuning(
sessions: Iterable[ChatSession],
) -> List[List[dict]]:
"""Convert messages to a list of lists of dictionaries for fine-tuning.
Args:
sessions: The chat sessions.
Returns:
The list of lists of dictionaries.
"""
return [
[convert_message_to_dict(s) for s in session["messages"]]
for session in sessions
if _has_assistant_message(session)
]
class Completions:
"""Completions."""
@overload
@staticmethod
def create(
messages: Sequence[Dict[str, Any]],
*,
provider: str = "ChatOpenAI",
stream: Literal[False] = False,
**kwargs: Any,
) -> ChatCompletions:
...
@overload
@staticmethod
def create(
messages: Sequence[Dict[str, Any]],
*,
provider: str = "ChatOpenAI",
stream: Literal[True],
**kwargs: Any,
) -> Iterable:
...
@staticmethod
def create(
messages: Sequence[Dict[str, Any]],
*,
provider: str = "ChatOpenAI",
stream: bool = False,
**kwargs: Any,
) -> Union[ChatCompletions, Iterable]:
models = importlib.import_module("langchain.chat_models")
model_cls = getattr(models, provider)
model_config = model_cls(**kwargs)
converted_messages = convert_openai_messages(messages)
if not stream:
result = model_config.invoke(converted_messages)
return ChatCompletions(
choices=[Choice(message=convert_message_to_dict(result))]
)
else:
return (
ChatCompletionChunk(
choices=[ChoiceChunk(delta=_convert_message_chunk(c, i))]
)
for i, c in enumerate(model_config.stream(converted_messages))
)
@overload
@staticmethod
async def acreate(
messages: Sequence[Dict[str, Any]],
*,
provider: str = "ChatOpenAI",
stream: Literal[False] = False,
**kwargs: Any,
) -> ChatCompletions:
...
@overload
@staticmethod
async def acreate(
messages: Sequence[Dict[str, Any]],
*,
provider: str = "ChatOpenAI",
stream: Literal[True],
**kwargs: Any,
) -> AsyncIterator:
...
@staticmethod
async def acreate(
messages: Sequence[Dict[str, Any]],
*,
provider: str = "ChatOpenAI",
stream: bool = False,
**kwargs: Any,
) -> Union[ChatCompletions, AsyncIterator]:
models = importlib.import_module("langchain.chat_models")
model_cls = getattr(models, provider)
model_config = model_cls(**kwargs)
converted_messages = convert_openai_messages(messages)
if not stream:
result = await model_config.ainvoke(converted_messages)
return ChatCompletions(
choices=[Choice(message=convert_message_to_dict(result))]
)
else:
return (
ChatCompletionChunk(
choices=[ChoiceChunk(delta=_convert_message_chunk(c, i))]
)
async for i, c in aenumerate(model_config.astream(converted_messages))
)
class Chat:
"""Chat."""
def __init__(self) -> None:
self.completions = Completions()
chat = Chat()
|