chore(release): initial commit

.cloud9/resize.sh

@@ -0,0 +1,120 @@
+#!/bin/bash
+
+# Specify the desired volume size in GiB as a command line argument. If not specified, default to 20 GiB.
+SIZE=${1:-120}
+
+# Get the ID of the environment host Amazon EC2 instance.
+INSTANCEID=$(curl -m 5 http://169.254.169.254/latest/meta-data/instance-id 2>/dev/null)
+REGION=$(curl -s -m 5 http://169.254.169.254/latest/meta-data/placement/availability-zone | sed 's/\(.*\)[a-z]/\1/' 2> /dev/null)
+
+if [ -z "${INSTANCEID}" ]; then
+    echo "Unable to get the ID of the environment host Amazon EC2 instance."
+    exit 1;
+fi
+
+if [ -z "${REGION}" ]; then
+    echo "Unable to get the region of the environment host Amazon EC2 instance."
+    exit 1;
+fi
+
+echo ""
+echo "┌──────────────────────────┐"
+echo "|                          |"
+echo "|    EBS Volume Resizer    |"
+echo "|                          |"
+echo "|   $INSTANCEID    |"
+echo "|                          |"
+echo "|        $REGION         |"
+echo "|                          |"
+echo "└──────────────────────────┘"
+echo ""
+
+# List the EBS volumes attached to the instance.
+# Get the ID of the Amazon EBS volume associated with the instance.
+VOLUMES=$(aws ec2 describe-instances \
+    --instance-id "$INSTANCEID" \
+    --query "Reservations[0].Instances[0].BlockDeviceMappings[*].Ebs.VolumeId" \
+    --output text \
+    --region "$REGION")
+
+# Prompt for the volume to use.
+echo "EBS Volumes:"
+PS3='Please select the EBS volume to resize (e.g 1) : '
+select VOLUME_ID in $VOLUMES; do 
+    break
+done
+
+# Verifying whether a valid EBS volume was selected.
+if [ -z "${VOLUME_ID}" ]; then
+    echo "The selected volume is invalid.";
+    exit 1;
+fi
+
+# Prompting for the size in GiB to resize the EBS volume.
+read -r -p "Enter new EBS Storage in GiB (e.g '$SIZE') for '$VOLUME_ID': " SIZE
+
+# Verify whether the input is a number.
+if [[ -n ${SIZE//[0-9]/} ]]; then
+    echo "Invalid input. Enter a valid numerical value."
+    exit 1
+fi
+
+# Ensure the new size is superior or equal to 8 GB.
+if [ "$SIZE" -lt "8" ]; then
+    echo "The new size must be superior or equal to 8 GiB."
+    exit 1
+fi
+
+# Confirm the input.
+read -r -p "Resizing EBS Storage to $SIZE (GiB), continue? (Y/N): " confirm
+if [[ $confirm != [yY] && $confirm != [yY][eE][sS] ]]; then
+    echo "Exiting..."
+    exit 1
+fi
+
+# Resize the EBS volume.
+echo "Resizing volume $VOLUME_ID to $SIZE GiB..."
+if ! aws ec2 modify-volume --volume-id "$VOLUME_ID" --size "$SIZE" 2>&1; then
+    echo "Failed to modify the volume."
+    exit 1
+fi
+
+# Wait for the resize to finish.
+while [ \
+    "$(aws ec2 describe-volumes-modifications \
+      --volume-id "$VOLUME_ID" \
+      --filters Name=modification-state,Values="optimizing,completed" \
+      --query "length(VolumesModifications)"\
+      --output text)" != "1" ]; do
+sleep 1
+done
+
+#Check if we're on an NVMe filesystem
+if [[ -e "/dev/xvda" && $(readlink -f /dev/xvda) = "/dev/xvda" ]]; then
+    # Rewrite the partition table so that the partition takes up all the space that it can.
+    sudo growpart /dev/xvda 1
+
+    # Check if we're on AL2
+    STR=$(cat /etc/os-release)
+    SUB="VERSION_ID=\"2\""
+    if [[ "$STR" == *"$SUB"* ]]
+    then
+      sudo xfs_growfs -d /
+    else
+      sudo resize2fs /dev/xvda1
+    fi
+else
+    # Rewrite the partition table so that the partition takes up all the space that it can.
+    sudo growpart /dev/nvme0n1 1
+
+    # Expand the size of the file system.
+    # Check if we're on AL2
+    STR=$(cat /etc/os-release)
+    SUB="VERSION_ID=\"2\""
+    if [[ "$STR" == *"$SUB"* ]]
+    then
+      sudo xfs_growfs -d /
+    else
+      sudo resize2fs /dev/nvme0n1p1
+    fi
+fi

.cspell/dictionary.txt

@@ -0,0 +1,138 @@
+lakechain
+astro
+astrojs
+powertools
+pydub
+suno
+nltk
+numba
+ndjson
+codespaces
+quickstart
+etag
+flac
+webm
+subrip
+runtimes
+pandoc
+gzipped
+untar
+grayscale
+greyscale
+libvips
+exif
+sshuttle
+USEREXAMPLE
+specversion
+fargate
+inferentia
+transformative
+Tiktoken
+langchain
+langchain's
+vectorizer
+keybert
+moderations
+xlarge
+todos
+autoscaler
+mediainfo
+quicktime
+msvideo
+matroska
+eventsources
+openxmlformats
+officedocument
+wordprocessingml
+openxmlformats
+presentationml
+spreadsheetml
+epub
+opendocument
+ipynb
+troff
+piis
+exifr
+opensearch
+abstractive
+sshleifer
+distilbart
+dailymail
+mpnet
+hkunlp
+intfloat
+unflatten
+normalise
+colourspace
+Clahe
+bandbool
+colourspace
+streamz
+unzipper
+xvda
+cuda
+userpool
+opensearchservice
+sigv
+kinesisfirehose
+amazonopensearchservice
+deliverystream
+autodrain
+KHTML
+hnsw
+nmslib
+faiss
+innerproduct
+cosinesimil
+linf
+sdxl
+inpainting
+dsl
+decorrelated
+stopwords
+opensearchserverless
+aoss
+timeseries
+vectorsearch
+redrive
+wontfix
+libmediainfo
+outpainting
+dokuwiki
+icml
+jats
+phpextra
+markua
+texinfo
+xwiki
+zimwiki
+gibibytes
+bibtex
+fictionbook
+docbook
+commonmark
+csljson
+stepfunctions
+JMES
+jmespath
+Celine
+pypandoc
+pdfminer
+huggingface
+arxiv
+bigbird
+uksb
+tupboc
+panns
+pann
+webserver
+mfccs
+cepstral
+mailparser
+typeof
+hailey
+outpainted
+feedparser
+onezone
+denoising
+synergize

.devcontainer/Dockerfile

@@ -0,0 +1,5 @@
+FROM mcr.microsoft.com/devcontainers/javascript-node:20
+
+# This section to install additional OS packages.
+RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
+    && apt-get -y install --no-install-recommends bash-completion

.devcontainer/devcontainer.json

@@ -0,0 +1,26 @@
+{
+  "name": "Node.js",
+  "build": {
+    "dockerfile": "Dockerfile"
+  },
+  "customizations": {
+    "extensions": [
+      "dbaeumer.vscode-eslint",
+      "esbenp.prettier-vscode",
+      "firsttris.vscode-jest-runner",
+      "amazonwebservices.aws-toolkit-vscode"
+    ],
+    "vscode": {
+      "git.enableCommitSigning": true
+    }
+  },
+  "features": {
+    "ghcr.io/devcontainers/features/node:1": {
+      "version": "20"
+    },
+    "ghcr.io/devcontainers/features/aws-cli:1": {},
+    "ghcr.io/devcontainers-contrib/features/typescript:2": {},
+    "ghcr.io/devcontainers/features/docker-in-docker:2": {}
+  },
+  "postCreateCommand": "npm install"
+}

.eslintignore

@@ -0,0 +1,4 @@
+*.js
+*.d.ts
+coverage
+node_modules

.eslintrc.json

@@ -0,0 +1,21 @@
+{
+  "env": {
+    "es2022": true,
+    "node": true
+  },
+  "extends": [
+    "eslint:recommended",
+    "plugin:@typescript-eslint/recommended",
+    "prettier"
+  ],
+  "parser": "@typescript-eslint/parser",
+  "parserOptions": {
+    "ecmaVersion": 12
+  },
+  "plugins": ["@typescript-eslint"],
+  "rules": {
+    "@typescript-eslint/no-explicit-any": "off",
+    "@typescript-eslint/no-unused-vars": "warn",
+    "@typescript-eslint/ban-ts-comment": "off"
+  }
+}

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,76 @@
+name: Bug Report
+description: Report a reproducible bug to help us improve the project
+title: 'Bug: TITLE'
+labels: ['type/bug', 'triage']
+projects: ['project-lakechain']
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for submitting a bug report.
+
+        Please add as much information as possible to help us reproduce, and remove any potential sensitive data.
+  - type: textarea
+    id: expected_behaviour
+    attributes:
+      label: Expected Behaviour
+      description: Please share details on the behaviour you expected
+    validations:
+      required: true
+  - type: textarea
+    id: current_behaviour
+    attributes:
+      label: Current Behaviour
+      description: Please share details on the current issue
+    validations:
+      required: true
+  - type: textarea
+    id: code_snippet
+    attributes:
+      label: Code snippet
+      description: Please share a code snippet to help us reproduce the issue
+      placeholder: |
+        ```typescript
+        some code here
+        ```
+    validations:
+      required: true
+  - type: textarea
+    id: steps
+    attributes:
+      label: Steps to Reproduce
+      description: Please share how we might be able to reproduce this issue
+      placeholder: |
+        1. In this environment...
+        2. With this config...
+        3. Run '...'
+        4. See error...
+    validations:
+      required: true
+  - type: textarea
+    id: solution
+    attributes:
+      label: Possible Solution
+      description: If known, please suggest a potential resolution
+    validations:
+      required: false
+  - type: input
+    id: version
+    attributes:
+      label: Project Lakechain version
+      placeholder: 'latest, 1.0.0'
+      value: latest
+    validations:
+      required: true
+  - type: textarea
+    id: logs
+    attributes:
+      label: Execution logs
+      description: If available, please share some logs making sure to remove any sensitive data
+      render: Shell
+    validations:
+      required: false
+  - type: markdown
+    attributes:
+      value: |
+        ---