GenAIExample code structure reorg (#207)
Signed-off-by: Tian, Feng <feng.tian@intel.com> Signed-off-by: chensuyue <suyue.chen@intel.com>
This commit is contained in:
@@ -1,57 +0,0 @@
|
||||
# Copyright (c) 2024 Intel Corporation
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
|
||||
from comps import DocSumGateway, MicroService, ServiceOrchestrator, ServiceType
|
||||
|
||||
MEGA_SERVICE_HOST_IP = os.getenv("MEGA_SERVICE_HOST_IP", "0.0.0.0")
|
||||
MEGA_SERVICE_PORT = os.getenv("MEGA_SERVICE_PORT", 8888)
|
||||
LLM_SERVICE_HOST_IP = os.getenv("LLM_SERVICE_HOST_IP", "0.0.0.0")
|
||||
LLM_SERVICE_PORT = os.getenv("LLM_SERVICE_PORT", 9000)
|
||||
|
||||
|
||||
class DocSumService:
|
||||
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/docsum",
|
||||
use_remote_service=True,
|
||||
service_type=ServiceType.LLM,
|
||||
)
|
||||
self.megaservice.add(llm)
|
||||
self.gateway = DocSumGateway(megaservice=self.megaservice, host="0.0.0.0", port=self.port)
|
||||
|
||||
async def schedule(self):
|
||||
await self.megaservice.schedule(
|
||||
initial_inputs={
|
||||
"text": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
|
||||
}
|
||||
)
|
||||
result_dict = self.megaservice.result_dict
|
||||
print(result_dict)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
docsum = DocSumService(host=MEGA_SERVICE_HOST_IP, port=MEGA_SERVICE_PORT)
|
||||
docsum.add_remote_service()
|
||||
asyncio.run(docsum.schedule())
|
||||
Reference in New Issue
Block a user