[Feat] Updating pinecone client to use serverless-index, adding best …

…Dockerfile practices.

Adding example .env

.env.example

@@ -0,0 +1,9 @@
+#----------------------------------------------------------------------------
+# OpenAI
+#----------------------------------------------------------------------------
+OPENAI_TOKEN=your-api-key # Replace your-api-key with your personal API key
+
+#----------------------------------------------------------------------------
+# Pinecone
+#----------------------------------------------------------------------------
+PINECONE_TOKEN=your-api-key # Replace your-api-key with your personal API key

docker-bot/Dockerfile

@@ -1,15 +1,53 @@
-FROM python:3.11-bullseye
+# syntax=docker/dockerfile:1
 
-WORKDIR /usr/src/app
+# Comments are provided throughout this file to help you get started.
+# If you need more help, visit the Dockerfile reference guide at
+# https://docs.docker.com/go/dockerfile-reference/
 
-COPY docker_bot /usr/src/app/docker_bot
-COPY pyproject.toml /usr/src/app/pyproject.toml
-COPY README.md /usr/src/app/README.md
+ARG PYTHON_VERSION=3.11
+FROM python:${PYTHON_VERSION}-slim as base
 
-RUN pip install -e .
+# Prevents Python from writing pyc files.
+ENV PYTHONDONTWRITEBYTECODE=1
 
+# Keeps Python from buffering stdout and stderr to avoid situations where
+# the application crashes without emitting any logs due to buffering.
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+# Create a non-privileged user that the app will run under.
+# See https://docs.docker.com/go/dockerfile-user-best-practices/
+ARG UID=10001
+RUN adduser \
+    --disabled-password \
+    --gecos "" \
+    --home "/nonexistent" \
+    --shell "/sbin/nologin" \
+    --no-create-home \
+    --uid "${UID}" \
+    appuser
+
+# Download dependencies as a separate step to take advantage of Docker's caching.
+# Leverage a cache mount to /root/.cache/pip to speed up subsequent builds.
+# Leverage a bind mount to pyproject.toml to avoid having to copy them into
+# into this layer.
+RUN --mount=type=cache,target=/root/.cache/pip \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    --mount=type=bind,source=poetry.lock,target=poetry.lock \
+    --mount=type=bind,source=docker_bot,target=docker_bot \
+    --mount=type=bind,source=README.md,target=README.md \
+    python -m pip install .
+
+# Switch to the non-privileged user to run the application.
+USER appuser
+
+# Copy the source code into the container.
+COPY . .
+
+# Expose the port that the application listens on.
 EXPOSE 8504
 
 HEALTHCHECK CMD curl --fail http://localhost:8504/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "docker_bot/bot.py", "--server.port=8504", "--server.address=0.0.0.0"]
+# Run the application.
+CMD streamlit run docker_bot/bot.py --server.port=8504 --server.address=0.0.0.0

docker-bot/docker_bot/bot.py

@@ -1,9 +1,9 @@
 import os
 
-import pinecone
 import streamlit as st
 from dotenv import load_dotenv
 from openai import OpenAI
+from pinecone import Pinecone, ServerlessSpec
 from streamlit.logger import get_logger
 
 load_dotenv(".env")
@@ -16,14 +16,17 @@
 @st.cache_resource
 def load_pinecone(index_name="docker-genai"):
     # initialize pinecone
-    pinecone.init(
-        api_key=os.getenv("PINECONE_TOKEN"),
-        environment=os.getenv("PINECONE_ENVIRONMENT"),
-    )
-    if index_name not in pinecone.list_indexes():
-        # we create a new index
-        pinecone.create_index(name=index_name, metric="cosine", dimension=1536)
-    index = pinecone.Index(index_name)
+    pc = Pinecone(api_key=os.getenv("PINECONE_TOKEN"))
+
+    if index_name not in pc.list_indexes().names():
+        logger.info(f"Creating index {index_name}, therefore there are no videos yet.")
+        pc.create_index(
+            name=index_name,
+            dimension=1536,
+            metric="cosine",
+            spec=ServerlessSpec(cloud="aws", region="us-west-2"),
+        )
+    index = pc.Index(index_name)
     return index