jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Remote inference support for examples in Productivity suite (#1818)

Browse Source 
Signed-off-by: Srinarayan Srikanthan <srinarayan.srikanthan@intel.com>
This commit is contained in:
sri-intel
2025-04-18 02:36:57 -04:00
committed by GitHub
parent c793dd0b51
commit c63e2cd067
4 changed files with 279 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ChatQnA/chatqna.py
View File

@@ -58,6 +58,7 @@ RERANK_SERVER_PORT = int(os.getenv("RERANK_SERVER_PORT", 80))
LLM_SERVER_HOST_IP = os.getenv("LLM_SERVER_HOST_IP", "0.0.0.0")
LLM_SERVER_PORT = int(os.getenv("LLM_SERVER_PORT", 80))
LLM_MODEL = os.getenv("LLM_MODEL", "meta-llama/Meta-Llama-3-8B-Instruct")
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY", None)
def align_inputs(self, inputs, cur_node, runtime_graph, llm_parameters_dict, **kwargs):
@@ -239,6 +240,7 @@ class ChatQnAService:
name="llm",
host=LLM_SERVER_HOST_IP,
port=LLM_SERVER_PORT,
api_key=OPENAI_API_KEY,
endpoint="/v1/chat/completions",
use_remote_service=True,
service_type=ServiceType.LLM,
@@ -272,6 +274,7 @@ class ChatQnAService:
name="llm",
host=LLM_SERVER_HOST_IP,
port=LLM_SERVER_PORT,
api_key=OPENAI_API_KEY,
endpoint="/v1/chat/completions",
use_remote_service=True,
service_type=ServiceType.LLM,
@@ -317,6 +320,7 @@ class ChatQnAService:
name="llm",
host=LLM_SERVER_HOST_IP,
port=LLM_SERVER_PORT,
api_key=OPENAI_API_KEY,
endpoint="/v1/chat/completions",
use_remote_service=True,
service_type=ServiceType.LLM,

148
ChatQnA/docker_compose/intel/cpu/xeon/compose_remote.yaml Normal file
View File

@@ -0,0 +1,148 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
services:
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
container_name: redis-vector-db
ports:
- "6379:6379"
- "8001:8001"
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 5s
timeout: 3s
retries: 10
dataprep-redis-service:
image: ${REGISTRY:-opea}/dataprep:${TAG:-latest}
container_name: dataprep-redis-server
depends_on:
redis-vector-db:
condition: service_healthy
tei-embedding-service:
condition: service_started
ports:
- "6007:5000"
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: redis://redis-vector-db:6379
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-server
ports:
- "6006:80"
volumes:
- "${MODEL_CACHE:-./data}:/data"
shm_size: 1g
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
retriever:
image: ${REGISTRY:-opea}/retriever:${TAG:-latest}
container_name: retriever-redis-server
depends_on:
- redis-vector-db
ports:
- "7000:7000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: redis://redis-vector-db:6379
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped
tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-reranking-server
ports:
- "8808:80"
volumes:
- "${MODEL_CACHE:-./data}:/data"
shm_size: 1g
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
chatqna-xeon-backend-server:
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-xeon-backend-server
depends_on:
- redis-vector-db
- tei-embedding-service
- retriever
- tei-reranking-service
ports:
- "8888:8888"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=chatqna-xeon-backend-server
- EMBEDDING_SERVER_HOST_IP=tei-embedding-service
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80}
- RETRIEVER_SERVICE_HOST_IP=retriever
- RERANK_SERVER_HOST_IP=tei-reranking-service
- RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-80}
- LLM_SERVER_HOST_IP=${REMOTE_ENDPOINT}
- OPENAI_API_KEY= ${OPENAI_API_KEY}
- LLM_SERVER_PORT=80
- LLM_MODEL=${LLM_MODEL_ID}
- LOGFLAG=${LOGFLAG}
ipc: host
restart: always
chatqna-xeon-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-xeon-ui-server
depends_on:
- chatqna-xeon-backend-server
ports:
- "5173:5173"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
ipc: host
restart: always
chatqna-xeon-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: chatqna-xeon-nginx-server
depends_on:
- chatqna-xeon-backend-server
- chatqna-xeon-ui-server
ports:
- "${NGINX_PORT:-80}:80"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- FRONTEND_SERVICE_IP=chatqna-xeon-ui-server
- FRONTEND_SERVICE_PORT=5173
- BACKEND_SERVICE_NAME=chatqna
- BACKEND_SERVICE_IP=chatqna-xeon-backend-server
- BACKEND_SERVICE_PORT=8888
- DATAPREP_SERVICE_IP=dataprep-redis-service
- DATAPREP_SERVICE_PORT=5000
ipc: host
restart: always
networks:
default:
driver: bridge

2
CodeGen/codegen.py
View File

@@ -29,6 +29,7 @@ RETRIEVAL_SERVICE_HOST_IP = os.getenv("RETRIEVAL_SERVICE_HOST_IP", "0.0.0.0")
REDIS_RETRIEVER_PORT = int(os.getenv("REDIS_RETRIEVER_PORT", 7000))
TEI_EMBEDDING_HOST_IP = os.getenv("TEI_EMBEDDING_HOST_IP", "0.0.0.0")
EMBEDDER_PORT = int(os.getenv("EMBEDDER_PORT", 6000))
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY", None)
grader_prompt = """You are a grader assessing relevance of a retrieved document to a user question. \n
Here is the user question: {question} \n
@@ -113,6 +114,7 @@ class CodeGenService:
name="llm",
host=LLM_SERVICE_HOST_IP,
port=LLM_SERVICE_PORT,
api_key=OPENAI_API_KEY,
endpoint="/v1/chat/completions",
use_remote_service=True,
service_type=ServiceType.LLM,

125
CodeGen/docker_compose/intel/cpu/xeon/compose_remote.yaml Normal file
View File

@@ -0,0 +1,125 @@
# Copyright (C) 2025 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
services:
codegen-xeon-backend-server:
image: ${REGISTRY:-opea}/codegen:${TAG:-latest}
container_name: codegen-xeon-backend-server
ports:
- "7778:7778"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- LLM_SERVICE_HOST_IP=${REMOTE_ENDPOINT}
- OPENAI_API_KEY= ${OPENAI_API_KEY}
- RETRIEVAL_SERVICE_HOST_IP=${RETRIEVAL_SERVICE_HOST_IP}
- REDIS_RETRIEVER_PORT=${REDIS_RETRIEVER_PORT}
- TEI_EMBEDDING_HOST_IP=${TEI_EMBEDDING_HOST_IP}
- EMBEDDER_PORT=${EMBEDDER_PORT}
ipc: host
restart: always
codegen-xeon-ui-server:
image: ${REGISTRY:-opea}/codegen-gradio-ui:${TAG:-latest}
container_name: codegen-xeon-ui-server
depends_on:
- codegen-xeon-backend-server
ports:
- "5173:5173"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- BASIC_URL=${BACKEND_SERVICE_ENDPOINT}
- MEGA_SERVICE_PORT=${MEGA_SERVICE_PORT}
- host_ip=${host_ip}
- DATAPREP_ENDPOINT=${DATAPREP_ENDPOINT}
- DATAPREP_REDIS_PORT=${DATAPREP_REDIS_PORT}
ipc: host
restart: always
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
container_name: redis-vector-db
ports:
- "${REDIS_DB_PORT}:${REDIS_DB_PORT}"
- "${REDIS_INSIGHTS_PORT}:${REDIS_INSIGHTS_PORT}"
dataprep-redis-server:
image: ${REGISTRY:-opea}/dataprep:${TAG:-latest}
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
ports:
- "${DATAPREP_REDIS_PORT}:5000"
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_HOST: ${host_ip}
INDEX_NAME: ${INDEX_NAME}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: true
restart: unless-stopped
tei-embedding-serving:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
container_name: tei-embedding-serving
entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate"
ports:
- "${TEI_EMBEDDER_PORT:-12000}:80"
volumes:
- "./data:/data"
shm_size: 1g
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
host_ip: ${host_ip}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
healthcheck:
test: ["CMD", "curl", "-f", "http://${host_ip}:${TEI_EMBEDDER_PORT}/health"]
interval: 10s
timeout: 6s
retries: 48
tei-embedding-server:
image: ${REGISTRY:-opea}/embedding:${TAG:-latest}
container_name: tei-embedding-server
ports:
- "${EMBEDDER_PORT:-10201}:6000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
EMBEDDING_COMPONENT_NAME: "OPEA_TEI_EMBEDDING"
depends_on:
tei-embedding-serving:
condition: service_healthy
restart: unless-stopped
retriever-redis:
image: ${REGISTRY:-opea}/retriever:${TAG:-latest}
container_name: retriever-redis
depends_on:
- redis-vector-db
ports:
- "${REDIS_RETRIEVER_PORT}:${REDIS_RETRIEVER_PORT}"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_DB_PORT: ${REDIS_DB_PORT}
REDIS_INSIGHTS_PORT: ${REDIS_INSIGHTS_PORT}
REDIS_RETRIEVER_PORT: ${REDIS_RETRIEVER_PORT}
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
RETRIEVER_COMPONENT_NAME: ${RETRIEVER_COMPONENT_NAME:-OPEA_RETRIEVER_REDIS}
restart: unless-stopped
networks:
default:
driver: bridge