[ChatQnA] Add no_wrapper benchmarking and update legacy manifests

ChatQnA/Dockerfile.no_wrapper

@@ -31,6 +31,4 @@ USER user
 
 WORKDIR /home/user
 
-RUN echo 'ulimit -S -n 999999' >> ~/.bashrc
-
 ENTRYPOINT ["python", "chatqna_no_wrapper.py"]

ChatQnA/Dockerfile.no_wrapper_without_rerank

@@ -0,0 +1,34 @@
+
+
+# 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 && \
+    pip install --no-cache-dir langchain_core
+
+COPY ./chatqna_no_wrapper.py /home/user/chatqna_no_wrapper.py
+
+ENV PYTHONPATH=$PYTHONPATH:/home/user/GenAIComps
+
+USER user
+
+WORKDIR /home/user
+
+ENTRYPOINT ["python", "chatqna_no_wrapper.py", "--without-rerank"]

ChatQnA/benchmark/README.md

@@ -37,6 +37,17 @@ Results will be displayed in the terminal and saved as CSV file named `1_stats.c
 - Set up kubectl on the master node with access to the Kubernetes cluster.
 - Install Python 3.8+ on the master node for running the stress tool.
 - Ensure all nodes have a local /mnt/models folder, which will be mounted by the pods.
+- Ensure that the container's ulimit can meet the the number of requests.
+
+```bash
+# The way to modify the containered ulimit:
+sudo systemctl edit containerd
+# Add two lines:
+[Service]
+LimitNOFILE=65536:1048576
+
+sudo systemctl daemon-reload; sudo systemctl restart containerd
+```
 
 ### Kubernetes Cluster Example