Support ChatQnA pipeline without rerank microservice (#643)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

ChatQnA/docker/Dockerfile_without_rerank

@@ -0,0 +1,33 @@
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+FROM python:3.11-slim
+
+RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
+    libgl1-mesa-glx \
+    libjemalloc-dev \
+    vim \
+    git
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user/
+
+WORKDIR /home/user/
+RUN git clone https://github.com/opea-project/GenAIComps.git
+
+WORKDIR /home/user/GenAIComps
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r /home/user/GenAIComps/requirements.txt
+
+COPY ./chatqna_without_rerank.py /home/user/chatqna_without_rerank.py
+
+ENV PYTHONPATH=$PYTHONPATH:/home/user/GenAIComps
+
+USER user
+
+WORKDIR /home/user
+
+ENTRYPOINT ["python", "chatqna_without_rerank.py"]

ChatQnA/docker/chatqna_without_rerank.py

@@ -0,0 +1,57 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+import os
+
+from comps import ChatQnAGateway, MicroService, ServiceOrchestrator, ServiceType
+
+MEGA_SERVICE_HOST_IP = os.getenv("MEGA_SERVICE_HOST_IP", "0.0.0.0")
+MEGA_SERVICE_PORT = int(os.getenv("MEGA_SERVICE_PORT", 8888))
+EMBEDDING_SERVICE_HOST_IP = os.getenv("EMBEDDING_SERVICE_HOST_IP", "0.0.0.0")
+EMBEDDING_SERVICE_PORT = int(os.getenv("EMBEDDING_SERVICE_PORT", 6000))
+RETRIEVER_SERVICE_HOST_IP = os.getenv("RETRIEVER_SERVICE_HOST_IP", "0.0.0.0")
+RETRIEVER_SERVICE_PORT = int(os.getenv("RETRIEVER_SERVICE_PORT", 7000))
+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 ChatQnAService:
+    def __init__(self, host="0.0.0.0", port=8000):
+        self.host = host
+        self.port = port
+        self.megaservice = ServiceOrchestrator()
+
+    def add_remote_service(self):
+        embedding = MicroService(
+            name="embedding",
+            host=EMBEDDING_SERVICE_HOST_IP,
+            port=EMBEDDING_SERVICE_PORT,
+            endpoint="/v1/embeddings",
+            use_remote_service=True,
+            service_type=ServiceType.EMBEDDING,
+        )
+        retriever = MicroService(
+            name="retriever",
+            host=RETRIEVER_SERVICE_HOST_IP,
+            port=RETRIEVER_SERVICE_PORT,
+            endpoint="/v1/retrieval",
+            use_remote_service=True,
+            service_type=ServiceType.RETRIEVER,
+        )
+        llm = MicroService(
+            name="llm",
+            host=LLM_SERVICE_HOST_IP,
+            port=LLM_SERVICE_PORT,
+            endpoint="/v1/chat/completions",
+            use_remote_service=True,
+            service_type=ServiceType.LLM,
+        )
+        self.megaservice.add(embedding).add(retriever).add(llm)
+        self.megaservice.flow_to(embedding, retriever)
+        self.megaservice.flow_to(retriever, llm)
+        self.gateway = ChatQnAGateway(megaservice=self.megaservice, host="0.0.0.0", port=self.port)
+
+
+if __name__ == "__main__":
+    chatqna = ChatQnAService(host=MEGA_SERVICE_HOST_IP, port=MEGA_SERVICE_PORT)
+    chatqna.add_remote_service()

ChatQnA/docker/docker_build_compose.yaml

@@ -15,6 +15,11 @@ services:
       dockerfile: ./Dockerfile_guardrails
     extends: chatqna
     image: ${REGISTRY:-opea}/chatqna-guardrails:${TAG:-latest}
+  chatqna-without-rerank:
+    build:
+      dockerfile: ./Dockerfile_without_rerank
+    extends: chatqna
+    image: ${REGISTRY:-opea}/chatqna-without-rerank:${TAG:-latest}
   chatqna-ui:
     build:
       context: ui

ChatQnA/docker/gaudi/compose_without_rerank.yaml

@@ -0,0 +1,157 @@
+# 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"
+  dataprep-redis-service:
+    image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
+    container_name: dataprep-redis-server
+    depends_on:
+      - redis-vector-db
+      - tei-embedding-service
+    ports:
+      - "6007:6007"
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      REDIS_URL: ${REDIS_URL}
+      INDEX_NAME: ${INDEX_NAME}
+      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+  tei-embedding-service:
+    image: ${REGISTRY:-opea}/tei-gaudi:${TAG:-latest}
+    container_name: tei-embedding-gaudi-server
+    ports:
+      - "8090:80"
+    volumes:
+      - "./data:/data"
+    runtime: habana
+    cap_add:
+      - SYS_NICE
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HABANA_VISIBLE_DEVICES: all
+      OMPI_MCA_btl_vader_single_copy_mechanism: none
+      MAX_WARMUP_SEQUENCE_LENGTH: 512
+      INIT_HCCL_ON_ACQUIRE: 0
+      ENABLE_EXPERIMENTAL_FLAGS: true
+    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
+  embedding:
+    image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
+    container_name: embedding-tei-server
+    depends_on:
+      - tei-embedding-service
+    ports:
+      - "6000:6000"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
+    restart: unless-stopped
+  retriever:
+    image: ${REGISTRY:-opea}/retriever-redis:${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_URL}
+      INDEX_NAME: ${INDEX_NAME}
+    restart: unless-stopped
+  tgi-service:
+    image: ghcr.io/huggingface/tgi-gaudi:2.0.1
+    container_name: tgi-gaudi-server
+    ports:
+      - "8005:80"
+    volumes:
+      - "./data:/data"
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_HUB_DISABLE_PROGRESS_BARS: 1
+      HF_HUB_ENABLE_HF_TRANSFER: 0
+      HABANA_VISIBLE_DEVICES: all
+      OMPI_MCA_btl_vader_single_copy_mechanism: none
+    runtime: habana
+    cap_add:
+      - SYS_NICE
+    ipc: host
+    command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
+  llm:
+    image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
+    container_name: llm-tgi-gaudi-server
+    depends_on:
+      - tgi-service
+    ports:
+      - "9000:9000"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_HUB_DISABLE_PROGRESS_BARS: 1
+      HF_HUB_ENABLE_HF_TRANSFER: 0
+    restart: unless-stopped
+  chaqna-gaudi-backend-server:
+    image: ${REGISTRY:-opea}/chatqna-without-rerank:${TAG:-latest}
+    container_name: chatqna-gaudi-backend-server
+    depends_on:
+      - redis-vector-db
+      - tei-embedding-service
+      - embedding
+      - retriever
+      - tgi-service
+      - llm
+    ports:
+      - "8888:8888"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
+      - EMBEDDING_SERVICE_HOST_IP=${EMBEDDING_SERVICE_HOST_IP}
+      - RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
+      - LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
+    ipc: host
+    restart: always
+  chaqna-gaudi-ui-server:
+    image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
+    container_name: chatqna-gaudi-ui-server
+    depends_on:
+      - chaqna-gaudi-backend-server
+    ports:
+      - "5173:5173"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
+      - UPLOAD_FILE_BASE_URL=${DATAPREP_SERVICE_ENDPOINT}
+      - GET_FILE=${DATAPREP_GET_FILE_ENDPOINT}
+      - DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
+    ipc: host
+    restart: always
+
+networks:
+  default:
+    driver: bridge