Add docker for ChatQnA Mega Service on Xeon

ChatQnA/microservice/xeon/README.md

@@ -17,8 +17,6 @@ First of all, you need to build Docker Images locally and install the python pac
 ```bash
 git clone https://github.com/opea-project/GenAIComps.git
 cd GenAIComps
-pip install -r requirements.txt
-pip install .
 ```
 
 ### 1. Build Embedding Image
@@ -36,7 +34,7 @@ docker build -t opea/gen-ai-comps:retriever-redis-server --build-arg https_proxy
 ### 3. Build Rerank Image
 
 ```bash
-docker build -t opea/gen-ai-comps:reranking-tei-xeon-server --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/reranks/docker/Dockerfile .
+docker build -t opea/gen-ai-comps:reranking-tei-xeon-server --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/reranks/langchain/docker/Dockerfile .
 ```
 
 ### 4. Build LLM Image
@@ -148,7 +146,7 @@ curl http://${host_ip}:9009/generate \
 ```bash
 curl http://${host_ip}:9000/v1/chat/completions\
   -X POST \
-  -d '{"text":"What is Deep Learning?"}' \
+  -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'
 ```
 
@@ -160,6 +158,29 @@ Modify the `initial_inputs` of line 34 in `chatqna.py`, then you will get the Ch
 
 All of the intermediate results will be printed for each microservices. Users can check the accuracy of the results to make targeted modifications.
 
+### Run Mega Service with Python
+
 ```bash
+# install packages
+cd /GenAIComps
+pip install -r requirements.txt
+pip install .
+# run chatqna service
+cd /GenAIExamples/ChatQnA/microservice/xeon
 python chatqna.py
 ```
+
+### Run Mega Service with Docker
+
+To run ChatQnA service with Docker, remember to pass the `${micro_service_host_ip}` variable into docker container, which is the real host ip of your microservices.
+
+```bash
+docker build -t opea/gen-ai-comps:chatqna-xeon-server --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f docker/Dockerfile .
+docker run -d --name="chatqna-xeon-server" -p 8888:8888 --ipc=host -e https_proxy=$https_proxy -e http_proxy=$http_proxy -e SERVICE_SERVICE_HOST_IP=${micro_service_host_ip} opea/gen-ai-comps:chatqna-xeon-server
+```
+
+Then you can check the result of your chatqna service with the command below.
+
+```bash
+docker logs chatqna-xeon-server
+```

ChatQnA/microservice/xeon/chatqna.py

@@ -13,25 +13,29 @@
 # limitations under the License.
 
 
+import os
+
 from comps import MicroService, ServiceOrchestrator
 
+SERVICE_HOST_IP = os.getenv("SERVICE_SERVICE_HOST_IP", "0.0.0.0")
+
 
 class ChatQnAService:
     def __init__(self, port=8000):
         self.service_builder = ServiceOrchestrator(host="0.0.0.0", port=port, endpoint="/v1/chatqna")
 
     def add_remote_service(self):
         embedding = MicroService(
-            name="embedding", host="0.0.0.0", port=6000, expose_endpoint="/v1/embeddings", use_remote_service=True
+            name="embedding", host=SERVICE_HOST_IP, port=6000, expose_endpoint="/v1/embeddings", use_remote_service=True
         )
         retriever = MicroService(
-            name="retriever", host="0.0.0.0", port=7000, expose_endpoint="/v1/retrieval", use_remote_service=True
+            name="retriever", host=SERVICE_HOST_IP, port=7000, expose_endpoint="/v1/retrieval", use_remote_service=True
         )
         rerank = MicroService(
-            name="rerank", host="0.0.0.0", port=8000, expose_endpoint="/v1/reranking", use_remote_service=True
+            name="rerank", host=SERVICE_HOST_IP, port=8000, expose_endpoint="/v1/reranking", use_remote_service=True
         )
         llm = MicroService(
-            name="llm", host="0.0.0.0", port=9000, expose_endpoint="/v1/chat/completions", use_remote_service=True
+            name="llm", host=SERVICE_HOST_IP, port=9000, expose_endpoint="/v1/chat/completions", use_remote_service=True
         )
         self.service_builder.add(embedding).add(retriever).add(rerank).add(llm)
         self.service_builder.flow_to(embedding, retriever)

ChatQnA/microservice/xeon/docker/Dockerfile

@@ -0,0 +1,41 @@
+# 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.
+
+
+FROM langchain/langchain:latest
+
+RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
+    libgl1-mesa-glx \
+    libjemalloc-dev \
+    vim
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user/
+
+RUN cd /home/user/ && \
+    git clone https://github.com/opea-project/GenAIComps.git
+
+RUN cd /home/user/GenAIComps && pip install --no-cache-dir --upgrade pip && \
+    pip install -r requirements.txt && pip install .
+
+COPY ../chatqna.py /home/user/chatqna.py
+
+ENV PYTHONPATH=$PYTHONPATH:/home/user
+
+USER user
+
+WORKDIR /home/user
+
+ENTRYPOINT ["python", "chatqna.py"]