[Feat] Upgrade yt-whisper bot to use serverless pinecone client

yt-whisper/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 yt_whisper /usr/src/app/yt_whisper
-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 requirements.txt 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=yt_whisper,target=yt_whisper \
+    --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 8503
 
 HEALTHCHECK CMD curl --fail http://localhost:8503/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "yt_whisper/app.py", "--server.port=8503", "--server.address=0.0.0.0"]
+# Run the application.
+CMD streamlit run yt_whisper/app.py --server.port=8503 --server.address=0.0.0.0

yt-whisper/pyproject.toml

@@ -6,12 +6,12 @@ authors = ["David Cardozo <[email protected]>"]
 readme = "README.md"
 
 [tool.poetry.dependencies]
-python = "^3.11"
+python = ">=3.11,<3.13"
 streamlit = "^1.29.0"
 python-dotenv = "^1.0.0"
 pytube = "^15.0.0"
 openai = "^1.7.0"
-pinecone-client = "^2.2.4"
+pinecone-client = "^3.0.2"
 
 
 [tool.poetry.group.dev.dependencies]

yt-whisper/scripts/run_with_docker.sh

@@ -1,3 +1,5 @@
 #!/bin/bash
 set -euf -o pipefail
-docker run -p 8503:8503 --env-file .env  demo 
+declare -r docker_image_name="yt-whisper:demo"
+docker build -t ${docker_image_name} .
+docker run -it --rm -p 8503:8503 --env-file .env ${docker_image_name}

yt-whisper/yt_whisper/app.py

@@ -3,10 +3,10 @@
 from pathlib import Path
 from tempfile import mkdtemp
 
-import pinecone
 import streamlit as st
 from dotenv import load_dotenv
 from openai import OpenAI
+from pinecone import Pinecone, ServerlessSpec
 from pytube import YouTube
 from pytube.exceptions import RegexMatchError
 from streamlit.logger import get_logger
@@ -23,14 +23,16 @@
 @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():
+        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
 
 
@@ -48,7 +50,7 @@ def process_video(video_url: str) -> dict[str, str]:
             audio_stream = yt_handler.streams.filter(only_audio=True).first()
             audio_file = audio_stream.download(tmp_dir)
             file_stats = os.stat(audio_file)
-            logger.info(f"File size: {file_stats.st_size}")
+            logger.info(f"File size(bytes): {file_stats.st_size}")
             logger.info(f"File name: {audio_file}")
             if file_stats.st_size > 24 * 1024 * 1024:  # 25 MB Limit check
                 # TODO(davidnet): Split and process the video in chunks
@@ -127,7 +129,7 @@ def disable(b):
 
 
 def main():
-    logger.info("Rendering app")
+    logger.debug("Rendering app")
     if "tempfolder" not in st.session_state:
         st.session_state.tempfolder = Path(mkdtemp(prefix="yt_transcription_"))
     if "videos" not in st.session_state: