Spaces:
Runtime error
Runtime error
File size: 8,447 Bytes
20076b6 |
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 |
import asyncio
import json
import os
from contextlib import asynccontextmanager
from typing import Any, Dict, Sequence
from pydantic import BaseModel
from ..chat import ChatModel
from ..data import Role as DataRole
from ..extras.misc import torch_gc
from ..extras.packages import is_fastapi_availble, is_starlette_available, is_uvicorn_available
from .protocol import (
ChatCompletionMessage,
ChatCompletionRequest,
ChatCompletionResponse,
ChatCompletionResponseChoice,
ChatCompletionResponseStreamChoice,
ChatCompletionResponseUsage,
ChatCompletionStreamResponse,
Finish,
Function,
FunctionCall,
ModelCard,
ModelList,
Role,
ScoreEvaluationRequest,
ScoreEvaluationResponse,
)
if is_fastapi_availble():
from fastapi import FastAPI, HTTPException, status
from fastapi.middleware.cors import CORSMiddleware
if is_starlette_available():
from sse_starlette import EventSourceResponse
if is_uvicorn_available():
import uvicorn
@asynccontextmanager
async def lifespan(app: "FastAPI"): # collects GPU memory
yield
torch_gc()
def dictify(data: "BaseModel") -> Dict[str, Any]:
try: # pydantic v2
return data.model_dump(exclude_unset=True)
except AttributeError: # pydantic v1
return data.dict(exclude_unset=True)
def jsonify(data: "BaseModel") -> str:
try: # pydantic v2
return json.dumps(data.model_dump(exclude_unset=True), ensure_ascii=False)
except AttributeError: # pydantic v1
return data.json(exclude_unset=True, ensure_ascii=False)
def create_app(chat_model: "ChatModel") -> "FastAPI":
app = FastAPI(lifespan=lifespan)
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
semaphore = asyncio.Semaphore(int(os.environ.get("MAX_CONCURRENT", 1)))
@app.get("/v1/models", response_model=ModelList)
async def list_models():
model_card = ModelCard(id="gpt-3.5-turbo")
return ModelList(data=[model_card])
@app.post("/v1/chat/completions", response_model=ChatCompletionResponse, status_code=status.HTTP_200_OK)
async def create_chat_completion(request: ChatCompletionRequest):
if not chat_model.can_generate:
raise HTTPException(status_code=status.HTTP_405_METHOD_NOT_ALLOWED, detail="Not allowed")
if len(request.messages) == 0 or request.messages[-1].role not in [Role.USER, Role.TOOL]:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid length")
messages = [dictify(message) for message in request.messages]
if len(messages) and messages[0]["role"] == Role.SYSTEM:
system = messages.pop(0)["content"]
else:
system = None
if len(messages) % 2 == 0:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Only supports u/a/u/a/u...")
for i in range(len(messages)):
if i % 2 == 0 and messages[i]["role"] not in [Role.USER, Role.TOOL]:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid role")
elif i % 2 == 1 and messages[i]["role"] not in [Role.ASSISTANT, Role.FUNCTION]:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid role")
elif messages[i]["role"] == Role.TOOL:
messages[i]["role"] = DataRole.OBSERVATION
tool_list = request.tools
if len(tool_list):
try:
tools = json.dumps([tool_list[0]["function"]], ensure_ascii=False)
except Exception:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid tools")
else:
tools = ""
async with semaphore:
loop = asyncio.get_running_loop()
return await loop.run_in_executor(None, chat_completion, messages, system, tools, request)
def chat_completion(messages: Sequence[Dict[str, str]], system: str, tools: str, request: ChatCompletionRequest):
if request.stream:
generate = stream_chat_completion(messages, system, tools, request)
return EventSourceResponse(generate, media_type="text/event-stream")
responses = chat_model.chat(
messages,
system,
tools,
do_sample=request.do_sample,
temperature=request.temperature,
top_p=request.top_p,
max_new_tokens=request.max_tokens,
num_return_sequences=request.n,
)
prompt_length, response_length = 0, 0
choices = []
for i, response in enumerate(responses):
if tools:
result = chat_model.template.format_tools.extract(response.response_text)
else:
result = response.response_text
if isinstance(result, tuple):
name, arguments = result
function = Function(name=name, arguments=arguments)
response_message = ChatCompletionMessage(
role=Role.ASSISTANT, tool_calls=[FunctionCall(function=function)]
)
finish_reason = Finish.TOOL
else:
response_message = ChatCompletionMessage(role=Role.ASSISTANT, content=result)
finish_reason = Finish.STOP if response.finish_reason == "stop" else Finish.LENGTH
choices.append(
ChatCompletionResponseChoice(index=i, message=response_message, finish_reason=finish_reason)
)
prompt_length = response.prompt_length
response_length += response.response_length
usage = ChatCompletionResponseUsage(
prompt_tokens=prompt_length,
completion_tokens=response_length,
total_tokens=prompt_length + response_length,
)
return ChatCompletionResponse(model=request.model, choices=choices, usage=usage)
def stream_chat_completion(
messages: Sequence[Dict[str, str]], system: str, tools: str, request: ChatCompletionRequest
):
choice_data = ChatCompletionResponseStreamChoice(
index=0, delta=ChatCompletionMessage(role=Role.ASSISTANT, content=""), finish_reason=None
)
chunk = ChatCompletionStreamResponse(model=request.model, choices=[choice_data])
yield jsonify(chunk)
for new_text in chat_model.stream_chat(
messages,
system,
tools,
do_sample=request.do_sample,
temperature=request.temperature,
top_p=request.top_p,
max_new_tokens=request.max_tokens,
):
if len(new_text) == 0:
continue
choice_data = ChatCompletionResponseStreamChoice(
index=0, delta=ChatCompletionMessage(content=new_text), finish_reason=None
)
chunk = ChatCompletionStreamResponse(model=request.model, choices=[choice_data])
yield jsonify(chunk)
choice_data = ChatCompletionResponseStreamChoice(
index=0, delta=ChatCompletionMessage(), finish_reason=Finish.STOP
)
chunk = ChatCompletionStreamResponse(model=request.model, choices=[choice_data])
yield jsonify(chunk)
yield "[DONE]"
@app.post("/v1/score/evaluation", response_model=ScoreEvaluationResponse, status_code=status.HTTP_200_OK)
async def create_score_evaluation(request: ScoreEvaluationRequest):
if chat_model.can_generate:
raise HTTPException(status_code=status.HTTP_405_METHOD_NOT_ALLOWED, detail="Not allowed")
if len(request.messages) == 0:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid request")
async with semaphore:
loop = asyncio.get_running_loop()
return await loop.run_in_executor(None, get_score, request)
def get_score(request: ScoreEvaluationRequest):
scores = chat_model.get_scores(request.messages, max_length=request.max_length)
return ScoreEvaluationResponse(model=request.model, scores=scores)
return app
if __name__ == "__main__":
chat_model = ChatModel()
app = create_app(chat_model)
uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("API_PORT", 8000)), workers=1)
|