bde285dfce
Co-authored-by: root <root@idc708073.jf.intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Sihan Chen <39623753+Spycsh@users.noreply.github.com>
94 lines
3.1 KiB
Python
94 lines
3.1 KiB
Python
# Copyright (C) 2024 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
import asyncio
|
|
import os
|
|
|
|
from comps import Gateway, MegaServiceEndpoint, MicroService, ServiceOrchestrator, ServiceType
|
|
from comps.cores.proto.api_protocol import (
|
|
ChatCompletionRequest,
|
|
ChatCompletionResponse,
|
|
ChatCompletionResponseChoice,
|
|
ChatMessage,
|
|
UsageInfo,
|
|
)
|
|
from fastapi import Request
|
|
from fastapi.responses import StreamingResponse
|
|
|
|
MEGA_SERVICE_PORT = int(os.getenv("MEGA_SERVICE_PORT", 7777))
|
|
LLM_SERVICE_HOST_IP = os.getenv("LLM_SERVICE_HOST_IP", "0.0.0.0")
|
|
LLM_SERVICE_PORT = int(os.getenv("LLM_SERVICE_PORT", 9000))
|
|
|
|
|
|
class CodeTransService(Gateway):
|
|
def __init__(self, host="0.0.0.0", port=8000):
|
|
self.host = host
|
|
self.port = port
|
|
self.megaservice = ServiceOrchestrator()
|
|
|
|
def add_remote_service(self):
|
|
llm = MicroService(
|
|
name="llm",
|
|
host=LLM_SERVICE_HOST_IP,
|
|
port=LLM_SERVICE_PORT,
|
|
endpoint="/v1/chat/completions",
|
|
use_remote_service=True,
|
|
)
|
|
self.megaservice.add(llm)
|
|
|
|
async def handle_request(self, request: Request):
|
|
data = await request.json()
|
|
language_from = data["language_from"]
|
|
language_to = data["language_to"]
|
|
source_code = data["source_code"]
|
|
prompt_template = """
|
|
### System: Please translate the following {language_from} codes into {language_to} codes.
|
|
|
|
### Original codes:
|
|
'''{language_from}
|
|
|
|
{source_code}
|
|
|
|
'''
|
|
|
|
### Translated codes:
|
|
"""
|
|
prompt = prompt_template.format(language_from=language_from, language_to=language_to, source_code=source_code)
|
|
result_dict, runtime_graph = await self.megaservice.schedule(initial_inputs={"query": prompt})
|
|
for node, response in result_dict.items():
|
|
# Here it suppose the last microservice in the megaservice is LLM.
|
|
if (
|
|
isinstance(response, StreamingResponse)
|
|
and node == list(self.megaservice.services.keys())[-1]
|
|
and self.megaservice.services[node].service_type == ServiceType.LLM
|
|
):
|
|
return response
|
|
last_node = runtime_graph.all_leaves()[-1]
|
|
response = result_dict[last_node]["text"]
|
|
choices = []
|
|
usage = UsageInfo()
|
|
choices.append(
|
|
ChatCompletionResponseChoice(
|
|
index=0,
|
|
message=ChatMessage(role="assistant", content=response),
|
|
finish_reason="stop",
|
|
)
|
|
)
|
|
return ChatCompletionResponse(model="codetrans", choices=choices, usage=usage)
|
|
|
|
def start(self):
|
|
super().__init__(
|
|
megaservice=self.megaservice,
|
|
host=self.host,
|
|
port=self.port,
|
|
endpoint=str(MegaServiceEndpoint.CODE_TRANS),
|
|
input_datatype=ChatCompletionRequest,
|
|
output_datatype=ChatCompletionResponse,
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
service_ochestrator = CodeTransService(port=MEGA_SERVICE_PORT)
|
|
service_ochestrator.add_remote_service()
|
|
service_ochestrator.start()
|