From 5b826c84afab65f7f51f8aeee30c66e08d29630a Mon Sep 17 00:00:00 2001
From: SarveshAtawane <sarveshatawane03@gmail.com>
Date: Fri, 2 Aug 2024 01:36:58 +0530
Subject: [PATCH] added multistage docker file

Signed-off-by: SarveshAtawane <sarveshatawane03@gmail.com>
---
 src/DockerFile           | 46 ++++++++++++++++++++++++++++++++++++++++
 src/Readme.md            |  7 ++++++
 src/core/conversation.py | 23 ++++++++++----------
 src/entrypoint.sh        |  8 +++++++
 4 files changed, 73 insertions(+), 11 deletions(-)
 create mode 100644 src/DockerFile
 create mode 100644 src/Readme.md
 create mode 100644 src/entrypoint.sh

diff --git a/src/DockerFile b/src/DockerFile
new file mode 100644
index 0000000..7642486
--- /dev/null
+++ b/src/DockerFile
@@ -0,0 +1,46 @@
+FROM node:20-alpine AS frontend-build
+WORKDIR /app/frontend
+COPY frontend .
+RUN yarn install && yarn build
+
+
+FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04 AS backend-build
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PYTHONUNBUFFERED=1
+ENV PATH="/usr/local/bin:${PATH}"
+RUN apt-get update && \
+    apt-get install -y python3-pip python3-dev && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+WORKDIR /app/core
+COPY core/requirements.txt .
+RUN pip3 install --no-cache-dir -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cu118
+
+
+FROM nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu22.04
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PYTHONUNBUFFERED=1
+ENV PATH="/usr/local/bin:${PATH}"
+ENV NODE_VERSION=20.x
+RUN apt-get update && apt-get install -y \
+    python3-pip \
+    wget \
+    curl \
+    && curl -fsSL https://deb.nodesource.com/setup_${NODE_VERSION} | bash - \
+    && apt-get install -y nodejs \
+    && npm install -g yarn \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+COPY --from=backend-build /usr/local/lib/python3.10/dist-packages /usr/local/lib/python3.10/dist-packages
+COPY core ./core
+COPY --from=frontend-build /app/frontend ./frontend
+COPY frontend/package.json frontend/yarn.lock ./frontend/
+WORKDIR /app/frontend
+RUN yarn install --production
+WORKDIR /app
+COPY entrypoint.sh .
+RUN chmod +x entrypoint.sh
+EXPOSE 3000 8080
+ENTRYPOINT ["./entrypoint.sh"]
\ No newline at end of file
diff --git a/src/Readme.md b/src/Readme.md
new file mode 100644
index 0000000..26a4a3a
--- /dev/null
+++ b/src/Readme.md
@@ -0,0 +1,7 @@
+```bash
+docker build -t aifaq .
+```
+Now run this image from this command
+```bash
+docker run --gpus all -p 3000:3000 -p 8080:8080 aifaq
+```
\ No newline at end of file
diff --git a/src/core/conversation.py b/src/core/conversation.py
index 8448392..75cfaea 100644
--- a/src/core/conversation.py
+++ b/src/core/conversation.py
@@ -32,17 +32,18 @@ def get_conversation():
 
     # build huggingface pipeline for using zephyr-7b-beta
     llm_pipeline = pipeline(
-        "text-generation",
-        model=model,
-        tokenizer=tokenizer,
-        use_cache=True,
-        device_map="auto",
-        max_length=4096,  # 4096
-        do_sample=True,
-        top_k=5,
-        num_return_sequences=1,
-        eos_token_id=tokenizer.eos_token_id,
-        pad_token_id=tokenizer.eos_token_id,
+            "text-generation",
+            model=model,
+            tokenizer=tokenizer,
+            use_cache=True,
+            device_map="auto",
+            max_length=4096, # 4096
+            truncation=True,
+            do_sample=True,
+            top_k=5,
+            num_return_sequences=1,
+            eos_token_id=tokenizer.eos_token_id,
+            pad_token_id=tokenizer.eos_token_id,
     )
 
     # specify the llm
diff --git a/src/entrypoint.sh b/src/entrypoint.sh
new file mode 100644
index 0000000..f74bb3b
--- /dev/null
+++ b/src/entrypoint.sh
@@ -0,0 +1,8 @@
+#!/bin/bash
+
+cd /app/core
+python3 fetch_and_organize_data.py
+python3 api.py &
+
+cd /app/frontend
+yarn start
\ No newline at end of file