Ettore Di Giacinto 8abecb4a18
Some checks failed
Explorer deployment / build-linux (push) Has been cancelled
GPU tests / ubuntu-latest (1.21.x) (push) Has been cancelled
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.1.0-0-devel-ubuntu22.04, linux/amd64, ubuntu-latest) (push) Has been cancelled
build container images / hipblas-jobs (-aio-gpu-hipblas, rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, extras, latest-gpu-hipblas, latest-aio-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -hipblas-ffmpeg) (push) Has been cancelled
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, false, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas-core) (push) Has been cancelled
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, false, ubuntu:22.04, extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas) (push) Has been cancelled
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, core, latest-gpu-hipblas-core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas-ffmpeg-core) (push) Has been cancelled
build container images / self-hosted-jobs (-aio-gpu-intel-f16, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, extras, latest-gpu-intel-f16, latest-aio-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -sycl-f16-ffmpeg) (push) Has been cancelled
build container images / self-hosted-jobs (-aio-gpu-intel-f32, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, extras, latest-gpu-intel-f32, latest-aio-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -sycl-f32-ffmpeg) (push) Has been cancelled
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-11, ubuntu:22.04, cublas, 11, 7, true, extras, latest-gpu-nvidia-cuda-11, latest-aio-gpu-nvidia-cuda-11, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -cublas-cuda11-ffmpeg) (push) Has been cancelled
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-12, ubuntu:22.04, cublas, 12, 0, true, extras, latest-gpu-nvidia-cuda-12, latest-aio-gpu-nvidia-cuda-12, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -cublas-cuda12-ffmpeg) (push) Has been cancelled
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, false, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16-core) (push) Has been cancelled
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, core, latest-gpu-intel-f16-core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16-ffmpeg-core) (push) Has been cancelled
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, false, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32-core) (push) Has been cancelled
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, core, latest-gpu-intel-f32-core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32-ffmpeg-core) (push) Has been cancelled
build container images / self-hosted-jobs (ubuntu:22.04, , , extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, ) (push) Has been cancelled
build container images / self-hosted-jobs (ubuntu:22.04, , true, extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -ffmpeg) (push) Has been cancelled
build container images / self-hosted-jobs (ubuntu:22.04, cublas, 11, 7, , extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda11) (push) Has been cancelled
build container images / self-hosted-jobs (ubuntu:22.04, cublas, 12, 0, , extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda12) (push) Has been cancelled
build container images / core-image-build (-aio-cpu, ubuntu:22.04, , true, core, latest-cpu, latest-aio-cpu, --jobs=4 --output-sync=target, linux/amd64,linux/arm64, arc-runner-set, false, auto, -ffmpeg-core) (push) Has been cancelled
build container images / core-image-build (ubuntu:22.04, cublas, 11, 7, , core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11-core) (push) Has been cancelled
build container images / core-image-build (ubuntu:22.04, cublas, 11, 7, true, core, latest-gpu-nvidia-cuda-12-core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11-ffmpeg-core) (push) Has been cancelled
build container images / core-image-build (ubuntu:22.04, cublas, 12, 0, , core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12-core) (push) Has been cancelled
build container images / core-image-build (ubuntu:22.04, cublas, 12, 0, true, core, latest-gpu-nvidia-cuda-12-core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12-ffmpeg-core) (push) Has been cancelled
build container images / core-image-build (ubuntu:22.04, vulkan, true, core, latest-gpu-vulkan-core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -vulkan-ffmpeg-core) (push) Has been cancelled
build container images / gh-runner (nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, 12, 0, true, core, latest-nvidia-l4t-arm64-core, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, true, false, -nvidia-l4t-arm64-core) (push) Has been cancelled
Security Scan / tests (push) Has been cancelled
Tests extras backends / tests-transformers (push) Has been cancelled
Tests extras backends / tests-rerankers (push) Has been cancelled
Tests extras backends / tests-diffusers (push) Has been cancelled
Tests extras backends / tests-coqui (push) Has been cancelled
tests / tests-linux (1.21.x) (push) Has been cancelled
tests / tests-aio-container (push) Has been cancelled
tests / tests-apple (1.21.x) (push) Has been cancelled
chore: bump grpc limits to 50MB (#5212)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-04-19 08:53:24 +02:00

129 lines
4.5 KiB
Python
Executable File

#!/usr/bin/env python3
"""
Extra gRPC server for Rerankers models.
"""
from concurrent import futures
import argparse
import signal
import sys
import os
import time
import backend_pb2
import backend_pb2_grpc
import grpc
from rerankers import Reranker
_ONE_DAY_IN_SECONDS = 60 * 60 * 24
# If MAX_WORKERS are specified in the environment use it, otherwise default to 1
MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
# Implement the BackendServicer class with the service methods
class BackendServicer(backend_pb2_grpc.BackendServicer):
"""
A gRPC servicer for the backend service.
This class implements the gRPC methods for the backend service, including Health, LoadModel, and Embedding.
"""
def Health(self, request, context):
"""
A gRPC method that returns the health status of the backend service.
Args:
request: A HealthRequest object that contains the request parameters.
context: A grpc.ServicerContext object that provides information about the RPC.
Returns:
A Reply object that contains the health status of the backend service.
"""
return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
def LoadModel(self, request, context):
"""
A gRPC method that loads a model into memory.
Args:
request: A LoadModelRequest object that contains the request parameters.
context: A grpc.ServicerContext object that provides information about the RPC.
Returns:
A Result object that contains the result of the LoadModel operation.
"""
model_name = request.Model
try:
kwargs = {}
if request.Type != "":
kwargs['model_type'] = request.Type
if request.PipelineType != "": # Reuse the PipelineType field for language
kwargs['lang'] = request.PipelineType
self.model_name = model_name
self.model = Reranker(model_name, **kwargs)
except Exception as err:
return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
# Implement your logic here for the LoadModel service
# Replace this with your desired response
return backend_pb2.Result(message="Model loaded successfully", success=True)
def Rerank(self, request, context):
documents = []
for idx, doc in enumerate(request.documents):
documents.append(doc)
ranked_results=self.model.rank(query=request.query, docs=documents, doc_ids=list(range(len(request.documents))))
# Prepare results to return
results = [
backend_pb2.DocumentResult(
index=res.doc_id,
text=res.text,
relevance_score=res.score
) for res in ranked_results.results
]
# Calculate the usage and total tokens
# TODO: Implement the usage calculation with reranker
total_tokens = sum(len(doc.split()) for doc in request.documents) + len(request.query.split())
prompt_tokens = len(request.query.split())
usage = backend_pb2.Usage(total_tokens=total_tokens, prompt_tokens=prompt_tokens)
return backend_pb2.RerankResult(usage=usage, results=results)
def serve(address):
server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
options=[
('grpc.max_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_send_message_length', 50 * 1024 * 1024), # 50MB
('grpc.max_receive_message_length', 50 * 1024 * 1024), # 50MB
])
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
server.add_insecure_port(address)
server.start()
print("Server started. Listening on: " + address, file=sys.stderr)
# Define the signal handler function
def signal_handler(sig, frame):
print("Received termination signal. Shutting down...")
server.stop(0)
sys.exit(0)
# Set the signal handlers for SIGINT and SIGTERM
signal.signal(signal.SIGINT, signal_handler)
signal.signal(signal.SIGTERM, signal_handler)
try:
while True:
time.sleep(_ONE_DAY_IN_SECONDS)
except KeyboardInterrupt:
server.stop(0)
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Run the gRPC server.")
parser.add_argument(
"--addr", default="localhost:50051", help="The address to bind the server to."
)
args = parser.parse_args()
serve(args.addr)