From c745641ba103d9f88af01f871f31384f16d02360 Mon Sep 17 00:00:00 2001 From: gadmarkovits Date: Thu, 25 Jul 2024 03:18:06 +0300 Subject: [PATCH] Added ChatQnA example using Qdrant retriever (#384) * Added ChatQnA example using Qdrant retriever Signed-off-by: gadmarkovits * Updated dockerfile path Signed-off-by: gadmarkovits --------- Signed-off-by: gadmarkovits Co-authored-by: chen, suyue --- ChatQnA/docker/xeon/README_qdrant.md | 393 ++++++++++++++++++ .../docker/xeon/docker_compose_qdrant.yaml | 205 +++++++++ ChatQnA/tests/test_chatqna_qdrant_on_xeon.sh | 233 +++++++++++ 3 files changed, 831 insertions(+) create mode 100644 ChatQnA/docker/xeon/README_qdrant.md create mode 100644 ChatQnA/docker/xeon/docker_compose_qdrant.yaml create mode 100644 ChatQnA/tests/test_chatqna_qdrant_on_xeon.sh diff --git a/ChatQnA/docker/xeon/README_qdrant.md b/ChatQnA/docker/xeon/README_qdrant.md new file mode 100644 index 000000000..9149695d2 --- /dev/null +++ b/ChatQnA/docker/xeon/README_qdrant.md @@ -0,0 +1,393 @@ +# Build Mega Service of ChatQnA (with Qdrant) on Xeon + +This document outlines the deployment process for a ChatQnA application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline on Intel Xeon server. The steps include Docker image creation, container deployment via Docker Compose, and service execution to integrate microservices such as `embedding`, `retriever`, `rerank`, and `llm`. We will publish the Docker images to Docker Hub soon, it will simplify the deployment process for this service. + +## 🚀 Apply Xeon Server on AWS + +To apply a Xeon server on AWS, start by creating an AWS account if you don't have one already. Then, head to the [EC2 Console](https://console.aws.amazon.com/ec2/v2/home) to begin the process. Within the EC2 service, select the Amazon EC2 M7i or M7i-flex instance type to leverage the power of 4th Generation Intel Xeon Scalable processors. These instances are optimized for high-performance computing and demanding workloads. + +For detailed information about these instance types, you can refer to this [link](https://aws.amazon.com/ec2/instance-types/m7i/). Once you've chosen the appropriate instance type, proceed with configuring your instance settings, including network configurations, security groups, and storage options. + +After launching your instance, you can connect to it using SSH (for Linux instances) or Remote Desktop Protocol (RDP) (for Windows instances). From there, you'll have full access to your Xeon server, allowing you to install, configure, and manage your applications as needed. + +**Certain ports in the EC2 instance need to opened up in the security group, for the microservices to work with the curl commands** + +> See one example below. Please open up these ports in the EC2 instance based on the IP addresses you want to allow + +``` +qdrant-vector-db +=============== +Port 6333 - Open to 0.0.0.0/0 +Port 6334 - Open to 0.0.0.0/0 + +tei_embedding_service +===================== +Port 6006 - Open to 0.0.0.0/0 + +embedding +========= +Port 6000 - Open to 0.0.0.0/0 + +retriever +========= +Port 7000 - Open to 0.0.0.0/0 + +tei_xeon_service +================ +Port 8808 - Open to 0.0.0.0/0 + +reranking +========= +Port 8000 - Open to 0.0.0.0/0 + +tgi_service +=========== +Port 9009 - Open to 0.0.0.0/0 + +llm +=== +Port 9000 - Open to 0.0.0.0/0 + +chaqna-xeon-backend-server +========================== +Port 8888 - Open to 0.0.0.0/0 + +chaqna-xeon-ui-server +===================== +Port 5173 - Open to 0.0.0.0/0 +``` + +## 🚀 Build Docker Images + +First of all, you need to build Docker Images locally and install the python package of it. + +```bash +git clone https://github.com/opea-project/GenAIComps.git +cd GenAIComps +``` + +### 1. Build Embedding Image + +```bash +docker build --no-cache -t opea/embedding-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/langchain/docker/Dockerfile . +``` + +### 2. Build Retriever Image + +```bash +docker build --no-cache -t opea/retriever-qdrant:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/retrievers/haystack/qdrant/docker/Dockerfile . +``` + +### 3. Build Rerank Image + +```bash +docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/reranks/tei/docker/Dockerfile . +``` + +### 4. Build LLM Image + +```bash +docker build --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/tgi/Dockerfile . +``` + +### 5. Build Dataprep Image + +```bash +docker build --no-cache -t opea/dataprep-qdrant:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/qdrant/docker/Dockerfile . +cd .. +``` + +### 6. Build MegaService Docker Image + +To construct the Mega Service, we utilize the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline within the `chatqna.py` Python script. Build MegaService Docker image via below command: + +```bash +git clone https://github.com/opea-project/GenAIExamples.git +cd GenAIExamples/ChatQnA/docker +docker build --no-cache -t opea/chatqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile . +cd ../../.. +``` + +### 7. Build UI Docker Image + +Build frontend Docker image via below command: + +```bash +cd GenAIExamples/ChatQnA/docker/ui/ +docker build --no-cache -t opea/chatqna-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile . +cd ../../../.. +``` + +### 8. Build Conversational React UI Docker Image (Optional) + +Build frontend Docker image that enables Conversational experience with ChatQnA megaservice via below command: + +**Export the value of the public IP address of your Xeon server to the `host_ip` environment variable** + +```bash +cd GenAIExamples/ChatQnA/docker/ui/ +export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/chatqna" +export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep" +export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get_file" +docker build --no-cache -t opea/chatqna-conversation-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy --build-arg BACKEND_SERVICE_ENDPOINT=$BACKEND_SERVICE_ENDPOINT --build-arg DATAPREP_SERVICE_ENDPOINT=$DATAPREP_SERVICE_ENDPOINT --build-arg DATAPREP_GET_FILE_ENDPOINT=$DATAPREP_GET_FILE_ENDPOINT -f ./docker/Dockerfile.react . +cd ../../../.. +``` + +Then run the command `docker images`, you will have the following 7 Docker Images: + +1. `opea/dataprep-qdrant:latest` +2. `opea/embedding-tei:latest` +3. `opea/retriever-qdrant:latest` +4. `opea/reranking-tei:latest` +5. `opea/llm-tgi:latest` +6. `opea/chatqna:latest` +7. `opea/chatqna-ui:latest` + +## 🚀 Start Microservices + +### Setup Environment Variables + +Since the `docker_compose.yaml` will consume some environment variables, you need to setup them in advance as below. + +**Export the value of the public IP address of your Xeon server to the `host_ip` environment variable** + +> Change the External_Public_IP below with the actual IPV4 value + +``` +export host_ip="External_Public_IP" +``` + +**Export the value of your Huggingface API token to the `your_hf_api_token` environment variable** + +> Change the Your_Huggingface_API_Token below with tyour actual Huggingface API Token value + +``` +export your_hf_api_token="Your_Huggingface_API_Token" +``` + +**Append the value of the public IP address to the no_proxy list** + +``` +export your_no_proxy=${your_no_proxy},"External_Public_IP" +``` + +```bash +export no_proxy=${your_no_proxy} +export http_proxy=${your_http_proxy} +export https_proxy=${your_http_proxy} +export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5" +export RERANK_MODEL_ID="BAAI/bge-reranker-base" +export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3" +export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006" +export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808" +export TGI_LLM_ENDPOINT="http://${host_ip}:9009" +export QDRANT_HOST=${host_ip} +export QDRANT_PORT=6333 +export INDEX_NAME="rag-qdrant" +export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token} +export MEGA_SERVICE_HOST_IP=${host_ip} +export EMBEDDING_SERVICE_HOST_IP=${host_ip} +export RETRIEVER_SERVICE_HOST_IP=${host_ip} +export RERANK_SERVICE_HOST_IP=${host_ip} +export LLM_SERVICE_HOST_IP=${host_ip} +export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/chatqna" +export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep" +export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get_file" +export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete_file" +``` + +Note: Please replace with `host_ip` with you external IP address, do not use localhost. + +### Start all the services Docker Containers + +> Before running the docker compose command, you need to be in the folder that has the docker compose yaml file + +```bash +cd GenAIExamples/ChatQnA/docker/xeon/ +docker compose -f docker_compose.yaml up -d +``` + +### Validate Microservices + +1. TEI Embedding Service + +```bash +curl ${host_ip}:6006/embed \ + -X POST \ + -d '{"inputs":"What is Deep Learning?"}' \ + -H 'Content-Type: application/json' +``` + +2. Embedding Microservice + +```bash +curl http://${host_ip}:6000/v1/embeddings\ + -X POST \ + -d '{"text":"hello"}' \ + -H 'Content-Type: application/json' +``` + +3. Retriever Microservice + To validate the retriever microservice, you need to generate a mock embedding vector of length 768 in Python script: + +```Python +import random +embedding = [random.uniform(-1, 1) for _ in range(768)] +print(embedding) +``` + +Then substitute your mock embedding vector for the `${your_embedding}` in the following cURL command: + +```bash +curl http://${host_ip}:7000/v1/retrieval \ + -X POST \ + -d '{"text":"What is the revenue of Nike in 2023?","embedding":"'"${your_embedding}"'"}' \ + -H 'Content-Type: application/json' +``` + +4. TEI Reranking Service + +```bash +curl http://${host_ip}:8808/rerank \ + -X POST \ + -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \ + -H 'Content-Type: application/json' +``` + +5. Reranking Microservice + +```bash +curl http://${host_ip}:8000/v1/reranking\ + -X POST \ + -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}' \ + -H 'Content-Type: application/json' +``` + +6. TGI Service + +```bash +curl http://${host_ip}:9009/generate \ + -X POST \ + -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \ + -H 'Content-Type: application/json' +``` + +7. LLM Microservice + +```bash +curl http://${host_ip}:9000/v1/chat/completions\ + -X POST \ + -d '{"query":"What is Deep Learning?","max_new_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"streaming":true}' \ + -H 'Content-Type: application/json' +``` + +8. MegaService + +```bash +curl http://${host_ip}:8888/v1/chatqna -H "Content-Type: application/json" -d '{ + "messages": "What is the revenue of Nike in 2023?" + }' +``` + +9. Dataprep Microservice（Optional） + +If you want to update the default knowledge base, you can use the following commands: + +Update Knowledge Base via Local File Upload: + +```bash +curl -X POST "http://${host_ip}:6007/v1/dataprep" \ + -H "Content-Type: multipart/form-data" \ + -F "files=@./nke-10k-2023.pdf" +``` + +This command updates a knowledge base by uploading a local file for processing. Update the file path according to your environment. + +Add Knowledge Base via HTTP Links: + +```bash +curl -X POST "http://${host_ip}:6007/v1/dataprep" \ + -H "Content-Type: multipart/form-data" \ + -F 'link_list=["https://opea.dev"]' +``` + +This command updates a knowledge base by submitting a list of HTTP links for processing. + +Also, you are able to get the file list that you uploaded: + +```bash +curl -X POST "http://${host_ip}:6008/v1/dataprep/get_file" \ + -H "Content-Type: application/json" +``` + +To delete the file/link you uploaded: + +```bash +# delete link +curl -X POST "http://${host_ip}:6009/v1/dataprep/delete_file" \ + -d '{"file_path": "https://opea.dev"}' \ + -H "Content-Type: application/json" + +# delete file +curl -X POST "http://${host_ip}:6009/v1/dataprep/delete_file" \ + -d '{"file_path": "nke-10k-2023.pdf"}' \ + -H "Content-Type: application/json" + +# delete all uploaded files and links +curl -X POST "http://${host_ip}:6009/v1/dataprep/delete_file" \ + -d '{"file_path": "all"}' \ + -H "Content-Type: application/json" +``` + +## Enable LangSmith for Monotoring Application (Optional) + +LangSmith offers tools to debug, evaluate, and monitor language models and intelligent agents. It can be used to assess benchmark data for each microservice. Before launching your services with `docker compose -f docker_compose.yaml up -d`, you need to enable LangSmith tracing by setting the `LANGCHAIN_TRACING_V2` environment variable to true and configuring your LangChain API key. + +Here's how you can do it: + +1. Install the latest version of LangSmith: + +```bash +pip install -U langsmith +``` + +2. Set the necessary environment variables: + +```bash +export LANGCHAIN_TRACING_V2=true +export LANGCHAIN_API_KEY=ls_... +``` + +## 🚀 Launch the UI + +To access the frontend, open the following URL in your browser: http://{host_ip}:5173. By default, the UI runs on port 5173 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `docker_compose.yaml` file as shown below: + +```yaml + chaqna-gaudi-ui-server: + image: opea/chatqna-ui:latest + ... + ports: + - "80:5173" +``` + +## 🚀 Launch the Conversational UI (react) + +To access the Conversational UI frontend, open the following URL in your browser: http://{host_ip}:5174. By default, the UI runs on port 80 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `docker_compose.yaml` file as shown below: + +```yaml + chaqna-xeon-conversation-ui-server: + image: opea/chatqna-conversation-ui:latest + ... + ports: + - "80:80" +``` + +![project-screenshot](../../assets/img/chat_ui_init.png) + +Here is an example of running ChatQnA: + +![project-screenshot](../../assets/img/chat_ui_response.png) + +Here is an example of running ChatQnA with Conversational UI (React): + +![project-screenshot](../../assets/img/conversation_ui_response.png) diff --git a/ChatQnA/docker/xeon/docker_compose_qdrant.yaml b/ChatQnA/docker/xeon/docker_compose_qdrant.yaml new file mode 100644 index 000000000..9a0a0e170 --- /dev/null +++ b/ChatQnA/docker/xeon/docker_compose_qdrant.yaml @@ -0,0 +1,205 @@ + +# Copyright (C) 2024 Intel Corporation +# SPDX-License-Identifier: Apache-2.0 + +version: "3.8" + +services: + qdrant-vector-db: + image: qdrant/qdrant + container_name: qdrant-vector-db + ports: + - "6333:6333" + - "6334:6334" + dataprep-qdrant-service: + image: opea/dataprep-qdrant:latest + container_name: dataprep-qdrant-server + depends_on: + - qdrant-vector-db + ports: + - "6000:6000" + environment: + no_proxy: ${no_proxy} + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + QDRANT: ${host_ip} + QDRANT_PORT: 6333 + COLLECTION_NAME: ${INDEX_NAME} + tei-embedding-service: + image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.2 + container_name: tei-embedding-server + ports: + - "6006:80" + volumes: + - "./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 + embedding: + image: opea/embedding-tei: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} + LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY} + LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2} + LANGCHAIN_PROJECT: "opea-embedding-service" + restart: unless-stopped + retriever: + image: opea/retriever-qdrant:latest + container_name: retriever-qdrant-server + depends_on: + - qdrant-vector-db + ports: + - "7000:7000" + ipc: host + environment: + no_proxy: ${no_proxy} + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + QDRANT_HOST: ${host_ip} + QDRANT_PORT: 6333 + INDEX_NAME: ${INDEX_NAME} + TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT} + restart: unless-stopped + tei-reranking-service: + image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.2 + container_name: tei-reranking-server + ports: + - "8808:80" + volumes: + - "./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 + reranking: + image: opea/reranking-tei:latest + container_name: reranking-tei-xeon-server + depends_on: + - tei-reranking-service + ports: + - "8000:8000" + ipc: host + environment: + no_proxy: ${no_proxy} + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + TEI_RERANKING_ENDPOINT: ${TEI_RERANKING_ENDPOINT} + HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + HF_HUB_DISABLE_PROGRESS_BARS: 1 + HF_HUB_ENABLE_HF_TRANSFER: 0 + LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY} + LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2} + LANGCHAIN_PROJECT: "opea-reranking-service" + restart: unless-stopped + tgi_service: + image: ghcr.io/huggingface/text-generation-inference:2.1.0 + container_name: tgi-service + ports: + - "9009:80" + volumes: + - "./data:/data" + shm_size: 1g + 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 + command: --model-id ${LLM_MODEL_ID} + llm: + image: opea/llm-tgi:latest + container_name: llm-tgi-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 + LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY} + LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2} + LANGCHAIN_PROJECT: "opea-llm-service" + restart: unless-stopped + chaqna-xeon-backend-server: + image: opea/chatqna:latest + container_name: chatqna-xeon-backend-server + depends_on: + - qdrant-vector-db + - tei-embedding-service + - embedding + - retriever + - tei-reranking-service + - reranking + - tgi_service + - llm + ports: + - "8888:8888" + environment: + - no_proxy=${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=${RETRIEVER_SERVICE_HOST_IP} + - RERANK_SERVICE_HOST_IP=${RERANK_SERVICE_HOST_IP} + - LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP} + ipc: host + restart: always + chaqna-xeon-ui-server: + image: opea/chatqna-ui:latest + container_name: chatqna-xeon-ui-server + depends_on: + - chaqna-xeon-backend-server + ports: + - "5173:5173" + environment: + - no_proxy=${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 + chaqna-xeon-conversation-ui-server: + image: opea/chatqna-conversation-ui:latest + container_name: chatqna-xeon-conversation-ui-server + environment: + - no_proxy=${no_proxy} + - https_proxy=${https_proxy} + - http_proxy=${http_proxy} + ports: + - 5174:80 + depends_on: + - chaqna-xeon-backend-server + ipc: host + restart: always + +networks: + default: + driver: bridge diff --git a/ChatQnA/tests/test_chatqna_qdrant_on_xeon.sh b/ChatQnA/tests/test_chatqna_qdrant_on_xeon.sh new file mode 100644 index 000000000..54c946321 --- /dev/null +++ b/ChatQnA/tests/test_chatqna_qdrant_on_xeon.sh @@ -0,0 +1,233 @@ +#!/bin/bash +# Copyright (C) 2024 Intel Corporation +# SPDX-License-Identifier: Apache-2.0 + +set -e +echo "IMAGE_REPO=${IMAGE_REPO}" + +WORKPATH=$(dirname "$PWD") +LOG_PATH="$WORKPATH/tests" +ip_address=$(hostname -I | awk '{print $1}') + +function build_docker_images() { + cd $WORKPATH + git clone https://github.com/opea-project/GenAIComps.git + cd GenAIComps + + docker build -t opea/embedding-tei:latest -f comps/embeddings/langchain/docker/Dockerfile . + docker build -t opea/retriever-qdrant:latest -f comps/retrievers/haystack/qdrant/docker/Dockerfile . + docker build -t opea/reranking-tei:latest -f comps/reranks/langchain/docker/Dockerfile . + docker build -t opea/llm-tgi:latest -f comps/llms/text-generation/tgi/Dockerfile . + docker build -t opea/dataprep-qdrant:latest -f comps/dataprep/qdrant/docker/Dockerfile . + + cd $WORKPATH/docker + docker build --no-cache -t opea/chatqna:latest -f Dockerfile . + + cd $WORKPATH/docker/ui + docker build --no-cache -t opea/chatqna-ui:latest -f docker/Dockerfile . + + docker images +} + +function start_services() { + cd $WORKPATH/docker/xeon + + export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5" + export RERANK_MODEL_ID="BAAI/bge-reranker-base" + export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3" + export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:6006" + export TEI_RERANKING_ENDPOINT="http://${ip_address}:8808" + export TGI_LLM_ENDPOINT="http://${ip_address}:9009" + export QDRANT_HOST=${ip_address} + export QDRANT_PORT=6333 + export INDEX_NAME="rag-qdrant" + export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} + export MEGA_SERVICE_HOST_IP=${ip_address} + export EMBEDDING_SERVICE_HOST_IP=${ip_address} + export RETRIEVER_SERVICE_HOST_IP=${ip_address} + export RERANK_SERVICE_HOST_IP=${ip_address} + export LLM_SERVICE_HOST_IP=${ip_address} + export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna" + export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep" + + sed -i "s/backend_address/$ip_address/g" $WORKPATH/docker/ui/svelte/.env + + if [[ "$IMAGE_REPO" != "" ]]; then + # Replace the container name with a test-specific name + echo "using image repository $IMAGE_REPO and image tag $IMAGE_TAG" + sed -i "s#image: opea/chatqna:latest#image: opea/chatqna:${IMAGE_TAG}#g" docker_compose.yaml + sed -i "s#image: opea/chatqna-ui:latest#image: opea/chatqna-ui:${IMAGE_TAG}#g" docker_compose.yaml + sed -i "s#image: opea/chatqna-conversation-ui:latest#image: opea/chatqna-conversation-ui:${IMAGE_TAG}#g" docker_compose.yaml + sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" docker_compose.yaml + fi + + # Start Docker Containers + docker compose -f docker_compose.yaml up -d + n=0 + until [[ "$n" -ge 200 ]]; do + docker logs tgi-service > tgi_service_start.log + if grep -q Connected tgi_service_start.log; then + break + fi + sleep 1s + n=$((n+1)) + done +} + +function validate_services() { + local URL="$1" + local EXPECTED_RESULT="$2" + local SERVICE_NAME="$3" + local DOCKER_NAME="$4" + local INPUT_DATA="$5" + + local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL") + if [ "$HTTP_STATUS" -eq 200 ]; then + echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..." + + local CONTENT=$(curl -s -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL" | tee ${LOG_PATH}/${SERVICE_NAME}.log) + + if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then + echo "[ $SERVICE_NAME ] Content is as expected." + else + echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT" + docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log + exit 1 + fi + else + echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS" + docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log + exit 1 + fi + sleep 1s +} + +function validate_microservices() { + # Check if the microservices are running correctly. + + # tei for embedding service + validate_services \ + "${ip_address}:6006/embed" \ + "\[\[" \ + "tei-embedding" \ + "tei-embedding-server" \ + '{"inputs":"What is Deep Learning?"}' + + # embedding microservice + validate_services \ + "${ip_address}:6000/v1/embeddings" \ + '"text":"What is Deep Learning?","embedding":\[' \ + "embedding" \ + "embedding-tei-server" \ + '{"text":"What is Deep Learning?"}' + + sleep 1m # retrieval can't curl as expected, try to wait for more time + + # retrieval microservice + test_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)") + validate_services \ + "${ip_address}:7000/v1/retrieval" \ + " " \ + "retrieval" \ + "retriever-qdrant-server" \ + "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${test_embedding}}" + + # tei for rerank microservice + validate_services \ + "${ip_address}:8808/rerank" \ + '{"index":1,"score":' \ + "tei-rerank" \ + "tei-reranking-server" \ + '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' + + # rerank microservice + validate_services \ + "${ip_address}:8000/v1/reranking" \ + "Deep learning is..." \ + "rerank" \ + "reranking-tei-xeon-server" \ + '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}' + + # tgi for llm service + validate_services \ + "${ip_address}:9009/generate" \ + "generated_text" \ + "tgi-llm" \ + "tgi-service" \ + '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' + + # llm microservice + validate_services \ + "${ip_address}:9000/v1/chat/completions" \ + "data: " \ + "llm" \ + "llm-tgi-server" \ + '{"query":"What is Deep Learning?"}' + +} + +function validate_megaservice() { + # Curl the Mega Service + validate_services \ + "${ip_address}:8888/v1/chatqna" \ + "billion" \ + "mega-chatqna" \ + "chatqna-xeon-backend-server" \ + '{"messages": "What is the revenue of Nike in 2023?"}' + +} + +function validate_frontend() { + cd $WORKPATH/docker/ui/svelte + local conda_env_name="OPEA_e2e" + export PATH=${HOME}/miniforge3/bin/:$PATH +# conda remove -n ${conda_env_name} --all -y +# conda create -n ${conda_env_name} python=3.12 -y + source activate ${conda_env_name} + + sed -i "s/localhost/$ip_address/g" playwright.config.ts + +# conda install -c conda-forge nodejs -y + npm install && npm ci && npx playwright install --with-deps + node -v && npm -v && pip list + + exit_status=0 + npx playwright test || exit_status=$? + + if [ $exit_status -ne 0 ]; then + echo "[TEST INFO]: ---------frontend test failed---------" + exit $exit_status + else + echo "[TEST INFO]: ---------frontend test passed---------" + fi +} + +function stop_docker() { + cd $WORKPATH/docker/xeon + container_list=$(cat docker_compose.yaml | grep container_name | cut -d':' -f2) + for container_name in $container_list; do + cid=$(docker ps -aq --filter "name=$container_name") + if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid && sleep 1s; fi + done +} + +function main() { + + stop_docker + if [[ "$IMAGE_REPO" == "" ]]; then build_docker_images; fi + start_time=$(date +%s) + start_services + end_time=$(date +%s) + duration=$((end_time-start_time)) + echo "Mega service start duration is $duration s" && sleep 1s + + validate_microservices + validate_megaservice + validate_frontend + + stop_docker + echo y | docker system prune + +} + +main