Initial commit

.devcontainer/devcontainer.json

@@ -0,0 +1,54 @@
+{
+    "name": "resume-maker-ai-agent",
+    // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+    "image": "mcr.microsoft.com/devcontainers/python:1-3.12-bullseye",
+    "features": {
+        "ghcr.io/devcontainers/features/python:1": {
+            "version": "3.12"
+        },
+        "ghcr.io/devcontainers/features/git:1": {},
+        "ghcr.io/devcontainers-contrib/features/poetry:2": {},
+        "ghcr.io/devcontainers/features/docker-in-docker:2.12.0": {
+            "version": "latest",
+            "moby": true
+        }
+    },
+    // Use 'postCreateCommand' to run commands after the container is created.
+    "postCreateCommand": "./.devcontainer/postCreateCommand.sh",
+    "forwardPorts": [7860, 8000],
+    // Configure tool-specific properties.
+    "customizations": {
+        "vscode": {
+            "extensions": [
+                "ms-python.python",
+                "editorconfig.editorconfig",
+                "ms-azuretools.vscode-docker", // Docker
+                "ms-python.isort", // isort
+                "visualstudioexptteam.vscodeintellicode", // IntelliCode
+                "codeium.codeium", // Codeium AI
+                "ms-vscode.makefile-tools", // Makefile tool
+                "ms-python.python", // Python
+                "ms-python.black-formatter", // Black
+                "ms-python.debugpy", // Debugger for Python
+                "redhat.vscode-yaml" // YAML
+            ],
+            "settings": {
+                "python.testing.pytestArgs": ["tests"],
+                "python.testing.unittestEnabled": false,
+                "python.testing.pytestEnabled": true,
+                "python.defaultInterpreterPath": "/workspaces/resume-maker-ai-agent/.venv/bin/python",
+                "python.testing.pytestPath": "/workspaces/resume-maker-ai-agent/.venv/bin/pytest",
+                "python.languageServer": "Pylance",
+                "editor.formatOnSave": true,
+                "python.analysis.typeCheckingMode": "basic",
+                "python.linting.enabled": true,
+                "python.linting.pylintEnabled": true
+            }
+        }
+    } //,
+    // "hostRequirements": {
+    //     "cpus": 2,
+    //     "memory": "4gb",
+    //     "storage": "10gb"
+    // }
+}

.devcontainer/postCreateCommand.sh

@@ -0,0 +1,12 @@
+#! /usr/bin/env bash
+
+# Install fish terminal
+sudo apt update -y
+sudo apt-get install fish -y
+
+# Repo Initialization
+make init-repo
+git config --global --add safe.directory /workspaces/resume-maker-ai-agent
+
+# Install Dependencies
+make reset-env

.dockerignore

@@ -0,0 +1,71 @@
+# Python cache files
+**/__pycache__/
+*.pyc
+*.pyo
+*.pyd
+
+# Poetry-related files
+.poetry/
+
+# Virtual environments
+**/.venv/
+**/venv/
+
+# Node.js dependencies
+**/node_modules/
+
+# Mypy cache
+**/.mypy_cache/
+
+# Pytest cache
+**/.pytest_cache/
+
+# Ruff cache
+**/.ruff_cache/
+
+# Coverage files
+**/.coverage
+**/coverage.xml
+
+# Development tools and IDE-specific files
+*.idea/
+*.vscode/
+**/.vscode/
+.devcontainer/
+.github/
+
+# Exclude notebooks
+notebooks/
+
+# Exclude test-related files and directories
+tests/
+
+# Build and distribution artifacts
+**/build/
+**/dist/
+*.egg-info/
+.eggs/
+
+# Logs and temporary files
+*.log
+*.tmp
+*.swp
+*.swo
+
+# Site-related files (if applicable)
+**/site/
+
+# Sensitive or configuration files
+.env
+*.pem
+*.key
+
+# Markdown and configuration files
+mkdocs.yml
+tox.ini
+pre-commit-config.yml
+codecove.yml
+.gitignore
+
+# Docker-related files (optional if Docker Compose is used locally but not in the image)
+docker-compose.yml

.editorconfig

@@ -0,0 +1,24 @@
+root = true
+
+[*]
+indent_style = space
+indent_size = 4
+trim_trailing_whitespace = true
+insert_final_newline = true
+charset = utf-8
+end_of_line = lf
+max_line_length = 120
+
+[*.bat]
+indent_style = tab
+end_of_line = crlf
+
+[LICENSE]
+insert_final_newline = false
+
+[Makefile]
+indent_style = tab
+
+[*.json]
+indent_style = space
+indent_size = 4

.github/actions/setup-poetry-env/action.yml

@@ -0,0 +1,42 @@
+name: "setup-poetry-env"
+description: "Composite action to setup the Python and poetry environment."
+
+inputs:
+    python-version:
+        required: false
+        description: "The python version to use"
+        default: "3.12"
+
+runs:
+    using: "composite"
+    steps:
+        - name: Set up python
+          uses: actions/setup-python@v5
+          with:
+              python-version: ${{ inputs.python-version }}
+
+        - name: Install Poetry
+          env:
+              POETRY_VERSION: "1.7.1"
+          run: curl -sSL https://install.python-poetry.org | python - -y
+          shell: bash
+
+        - name: Add Poetry to Path
+          run: echo "$HOME/.local/bin" >> $GITHUB_PATH
+          shell: bash
+
+        - name: Configure Poetry virtual environment in project
+          run: poetry config virtualenvs.in-project true
+          shell: bash
+
+        - name: Load cached venv
+          id: cached-poetry-dependencies
+          uses: actions/cache@v4
+          with:
+              path: .venv
+              key: venv-${{ runner.os }}-${{ inputs.python-version }}-${{ hashFiles('poetry.lock') }}
+
+        - name: Install dependencies
+          if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
+          run: poetry install --no-interaction
+          shell: bash

.github/workflows/deploy-docs.yml

@@ -0,0 +1,22 @@
+name: Deploy Documentation
+
+on:
+    release:
+        types: [published]
+        branches: [main]
+    repository_dispatch:
+        types: [package-release]
+
+jobs:
+    deploy-docs:
+        runs-on: ubuntu-latest
+
+        steps:
+            - name: Check out
+              uses: actions/checkout@v4
+
+            - name: Set up the environment
+              uses: ./.github/actions/setup-poetry-env
+
+            - name: Deploy documentation
+              run: poetry run mkdocs gh-deploy --force

.github/workflows/hugging_face-deploy.yml

@@ -0,0 +1,27 @@
+name: Deploy to Hugging Face Spaces
+
+on:
+    push:
+        branches:
+            - main # or master, depending on your default branch
+
+jobs:
+    deploy:
+        runs-on: ubuntu-latest
+        steps:
+            - name: Checkout repository
+              uses: actions/checkout@v4
+              with:
+                  fetch-depth: 0
+
+            - name: Configure Git
+              run: |
+                  git config --global user.email "github-actions[bot]@users.noreply.github.com"
+                  git config --global user.name "github-actions[bot]"
+
+            - name: Push to Hugging Face Space
+              env:
+                  HF_TOKEN: ${{ secrets.HF_TOKEN }}
+              run: |
+                  git remote add space https://USER:$HF_TOKEN@huggingface.co/spaces/deepakpant/resume-maker-ai-agent
+                  git push --force space main

.github/workflows/test-check-build.yml

@@ -0,0 +1,60 @@
+name: Test, check and build pipeline
+
+on:
+    push:
+        branches:
+            - main
+    pull_request:
+        types: [opened, synchronize, reopened, ready_for_review]
+
+jobs:
+    quality:
+        runs-on: ubuntu-latest
+        steps:
+            - name: Check out
+              uses: actions/checkout@v4
+
+            - uses: actions/cache@v4
+              with:
+                  path: ~/.cache/pre-commit
+                  key: pre-commit-${{ hashFiles('.pre-commit-config.yaml') }}
+
+            - name: Set up the environment
+              uses: ./.github/actions/setup-poetry-env
+
+            - name: Run checks
+              run: make lint
+
+    build:
+        runs-on: ubuntu-latest
+        needs: [quality]
+        strategy:
+            matrix:
+                python-version: ["3.12"]
+            fail-fast: false
+        defaults:
+            run:
+                shell: bash
+        steps:
+            - name: Check out
+              uses: actions/checkout@v4
+
+            - name: Set up the environment
+              uses: ./.github/actions/setup-poetry-env
+              with:
+                  python-version: ${{ matrix.python-version }}
+
+            - name: Build
+              run: make bake
+
+    check-docs:
+        runs-on: ubuntu-latest
+        steps:
+            - name: Check out
+              uses: actions/checkout@v4
+
+            - name: Set up the environment
+              uses: ./.github/actions/setup-poetry-env
+
+            - name: Check if documentation can be built
+              run: poetry run mkdocs build -s

.github/workflows/version-bump-and-release.yml

@@ -0,0 +1,60 @@
+name: Version Bump and Create Release
+
+on:
+    workflow_dispatch:
+        inputs:
+            bump_type:
+                description: "Type of version bump"
+                required: true
+                type: choice
+                options:
+                    - patch
+                    - minor
+                    - major
+
+permissions:
+    contents: write
+
+jobs:
+    bump-version:
+        runs-on: ubuntu-latest
+        steps:
+            - name: Checkout code
+              uses: actions/checkout@v4
+              with:
+                  fetch-depth: 0
+                  token: ${{ secrets.GITHUB_TOKEN }}
+
+            - name: Set up the environment
+              uses: ./.github/actions/setup-poetry-env
+              with:
+                  python-version: "3.12"
+
+            - name: Configure Git
+              run: |
+                  git config --global user.name 'GitHub Actions'
+                  git config --global user.email 'actions@github.com'
+
+            - name: Bump Version
+              id: bump
+              run: |
+                  poetry run bump-my-version bump ${{ github.event.inputs.bump_type }}
+                  echo "NEW_TAG=$(git describe --tags --abbrev=0)" >> $GITHUB_OUTPUT
+
+            - name: Push changes
+              run: |
+                  git push
+                  git push --tags
+
+            - name: Create Release
+              uses: softprops/action-gh-release@v2
+              with:
+                  generate_release_notes: true
+                  tag_name: ${{ steps.bump.outputs.NEW_TAG }}
+
+            - name: Trigger Package Publish
+              uses: peter-evans/repository-dispatch@v3
+              with:
+                  token: ${{ secrets.GITHUB_TOKEN }}
+                  event-type: package-release
+                  client-payload: '{"version": "${{ steps.bump.outputs.NEW_TAG }}"}'

.gitignore

@@ -0,0 +1,174 @@
+docs/source
+
+# From https://raw.githubusercontent.com/github/gitignore/main/Python.gitignore
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# Vscode config files
+# .vscode/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# artifect/
+dvc-service-account-key.json
+
+
+# MacOS
+.DS_Store

.pre-commit-config.yaml

@@ -0,0 +1,40 @@
+repos:
+    - repo: https://github.com/pre-commit/pre-commit-hooks
+      rev: "v4.4.0"
+      hooks:
+          - id: check-case-conflict
+          - id: check-merge-conflict
+          - id: end-of-file-fixer
+          - id: trailing-whitespace
+          - id: check-yaml
+          - id: check-toml
+
+    - repo: https://github.com/astral-sh/ruff-pre-commit
+      rev: "v0.5.2"
+      hooks:
+          - id: ruff
+            args: [--exit-non-zero-on-fix, --config=pyproject.toml]
+          - id: ruff-format
+            args: [--config=pyproject.toml]
+
+    - repo: https://github.com/pre-commit/mirrors-prettier
+      rev: "v3.0.3"
+      hooks:
+          - id: prettier
+
+    # - repo: https://github.com/psf/black
+    #   rev: 23.9.0
+    #   hooks:
+    #       - id: black
+
+    # - repo: https://github.com/timothycrosley/isort
+    #   rev: 5.12.0
+    #   hooks:
+    #       - id: isort
+    #         args: [--settings-path=pyproject.toml]
+
+    - repo: https://github.com/PyCQA/pydocstyle
+      rev: 6.3.0
+      hooks:
+          - id: pydocstyle
+            args: [--config=pyproject.toml]

.vscode/launch.json

@@ -0,0 +1,15 @@
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python Debugger: resume_maker_ai_agent",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "${workspaceFolder}/resume_maker_ai_agent/app.py",
+            "args": ["run"],
+            "console": "integratedTerminal",
+            "justMyCode": true,
+            "jinja": true
+        }
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,16 @@
+{
+    "files.exclude": {
+        "**/.mypy_cache": true,
+        "**/__pycache__": true,
+        "**/.pytest_cache": true,
+        "**/.ruff_cache": true,
+        "**/.venv": true,
+        "**/venv": true,
+        "**/node_modules": true,
+        "**/site": true,
+        "**/.coverage": true,
+        "**/coverage.xml": true,
+        "**/build": true,
+        "**/dist": true
+    }
+}

Dockerfile

@@ -0,0 +1,61 @@
+# Builder Stage
+FROM python:3.12-slim AS builder
+
+RUN useradd -m -u 1000 user
+
+# Set environment variables for Poetry
+ENV POETRY_VERSION=1.6.1 \
+    POETRY_HOME="/opt/poetry" \
+    PATH="/opt/poetry/bin:$PATH"
+
+# Install Poetry and necessary tools
+RUN apt-get update && apt-get install -y --no-install-recommends curl \
+    && curl -sSL https://install.python-poetry.org | python3 - \
+    && apt-get remove -y curl && apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# Set working directory
+WORKDIR /app
+
+# Copy only the dependency files first to leverage Docker caching
+COPY --chown=user pyproject.toml poetry.lock /app/
+
+# Install dependencies (only for building the wheel)
+RUN poetry config virtualenvs.create false \
+    && poetry install --no-root --only main
+
+# Copy the rest of the application code
+COPY --chown=user . /app
+
+# Build the wheel file
+RUN poetry build -f wheel
+
+# Runtime Stage
+FROM python:3.12-slim AS runtime
+
+RUN useradd -m -u 1000 user
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+
+# Install runtime dependencies for Chromium and Selenium
+RUN apt-get update && apt-get install -y \
+    libgconf-2-4 \
+    libnss3 \
+    && rm -rf /var/lib/apt/lists/*
+
+
+# Set working directory
+WORKDIR /app
+
+# Copy the built wheel file from the builder stage
+COPY --chown=user --from=builder /app/dist/*.whl /app/
+
+
+# Install the wheel file
+RUN pip install --no-cache-dir /app/*.whl
+
+# Expose application port
+EXPOSE 7860
+
+# Command to run the application
+CMD ["resume_maker_ai_agent"]

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025, Deepak pant
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Makefile

@@ -0,0 +1,266 @@
+# =============================
+# Variable Documentation
+# =============================
+
+# PYPI_TOKEN: Authentication token for PyPI publishing
+# Usage: make publish PYPI_TOKEN=your_pypi_token
+
+# PACKAGE_NAME: Name of the Python package for dependency tree
+# Usage: make print-dependency-tree PACKAGE_NAME=your_package_name
+
+
+# =============================
+# Project Configuration
+# =============================
+PROJECT_NAME = resume-maker-ai-agent
+GITHUB_USERNAME = DeepakPant93
+GITHUB_REPO = $(PROJECT_NAME)
+PROJECT_SLUG = resume_maker_ai_agent
+CLOUD_REGION = eastus
+TAG = latest
+IMAGE_NAME = deepak93p/$(PROJECT_SLUG)
+RESOURCE_GROUP = $(PROJECT_NAME)-rg
+APP_NAME = $(PROJECT_NAME)-app
+APP_ENV_NAME = $(APP_NAME)-env
+BUMP_TYPE = patch
+
+# =============================
+# Help (Default Target)
+# =============================
+.PHONY: help
+help: ## Display this help message
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-25s\033[0m %s\n", $$1, $$2}'
+
+.DEFAULT_GOAL := help
+
+# =============================
+# Installation and Setup
+# =============================
+.PHONY: bake-env
+bake-env: clean-env ## Install the poetry environment and set up pre-commit hooks
+	@echo "🚀 Creating virtual environment using pyenv and poetry"
+	@poetry install
+	@poetry run pre-commit install || true
+	@max_retries=3; count=0; \
+	while ! make lint; do \
+		count=$$((count + 1)); \
+		if [ $$count -ge $$max_retries ]; then \
+			echo "Max retries reached. Exiting."; \
+			exit 1; \
+		fi; \
+		echo "Retrying make lint ($$count/$$max_retries)..."; \
+	done
+	@poetry shell
+
+.PHONY: clean-env
+clean-env: ## Remove the poetry environment
+	@echo "🚀 Removing virtual environment"
+	@rm -rf .venv
+
+.PHONY: reset-env
+reset-env: clean-env bake-env ## Install the poetry environment and set up pre-commit hooks
+
+.PHONY: init-repo
+init-repo: ## Initialize git repository
+	@echo "🚀 Initializing git repository"
+	@git init
+	@echo "🚀 Creating initial commit"
+	@git add .
+	@git commit -m "Initial commit"
+	@echo "🚀 Adding remote repository"
+	@git branch -M main
+	@git remote add origin git@github.com:$(GITHUB_USERNAME)/$(GITHUB_REPO).git
+	@echo "🚀 Pushing initial commit"
+	@git push -u origin main
+
+.PHONY: setup-cloud-env
+setup-cloud-env: ## Create resource group, container app environment, and service principal
+	@echo "🚀 Creating resource group: $(RESOURCE_GROUP)"
+	@az group create --name $(RESOURCE_GROUP) --location $(CLOUD_REGION)
+
+	@echo "🚀 Creating container app environment: $(APP_ENV_NAME)"
+	@az containerapp env create --name $(APP_ENV_NAME) --resource-group $(RESOURCE_GROUP) --location $(CLOUD_REGION)
+
+	@echo "🚀 Fetching subscription ID"
+	@subscription_id=$$(az account show --query "id" -o tsv) && \
+	echo "Subscription ID: $$subscription_id" && \
+	echo "🚀 Creating service principal for: $(APP_NAME)" && \
+	az ad sp create-for-rbac --name "$(APP_NAME)-service-principal" --role contributor --scopes /subscriptions/$$subscription_id --sdk-auth
+
+	@echo "🚀 Creating container app: $(APP_NAME)"
+	@az containerapp create --name $(APP_NAME) --resource-group $(RESOURCE_GROUP) --environment $(APP_ENV_NAME) --image 'nginx:latest' --target-port 80 --ingress 'external' --query "properties.configuration.ingress.fqdn"
+
+.PHONY: clean-cloud-env
+clean-cloud-env: ## Delete resource group, container app environment, and service principal
+	@echo "🚀 Deleting service principal for: $(APP_NAME)-service-principal"
+	@sp_object_id=$$(az ad sp list --display-name "$(APP_NAME)-service-principal" --query "[0].id" -o tsv) && \
+	if [ -n "$$sp_object_id" ]; then \
+		az ad sp delete --id $$sp_object_id; \
+		echo "Service principal deleted"; \
+	else \
+		echo "Service principal not found, skipping deletion"; \
+	fi
+
+	@echo "🚀 Deleting container app: $(APP_NAME)"
+	@az containerapp delete --name $(APP_NAME) --resource-group $(RESOURCE_GROUP) --yes --no-wait || echo "Container app not found, skipping deletion"
+
+	@echo "🚀 Deleting container app environment: $(APP_ENV_NAME)"
+	@az containerapp env delete --name $(APP_ENV_NAME) --resource-group $(RESOURCE_GROUP) --yes --no-wait || echo "Container app environment not found, skipping deletion"
+
+	@echo "🚀 Deleting resource group: $(RESOURCE_GROUP)"
+	@az group delete --name $(RESOURCE_GROUP) --yes --no-wait || echo "Resource group not found, skipping deletion"
+
+.PHONY: install-prerequisites
+install-prerequisites: ## Install system prerequisites
+	@echo "Updating package lists..."
+	@sudo apt-get update
+	@echo "Installing system prerequisites..."
+	@sudo apt-get install -y \
+        chromium \
+        chromium-driver \
+        gnupg \
+        libgconf-2-4 \
+        libnss3 \
+        unzip \
+        wget \
+		sqlite3
+
+
+# =============================
+# Code Quality and Testing
+# =============================
+.PHONY: lint
+lint: ## Run code quality tools
+	@echo "🚀 Checking Poetry lock file consistency with 'pyproject.toml'"
+	@poetry check --lock
+	@echo "🚀 Linting code with pre-commit"
+	@poetry run pre-commit run -a
+	@echo "🚀 Static type checking with mypy"
+	# @echo "🚀 Sorting imports with isort"
+	# @poetry run isort resume_maker_ai_agent/
+	# @echo "🚀 Linting code with Ruff"
+	# @poetry run ruff format resume_maker_ai_agent/
+	@poetry run mypy
+	@echo "🚀 Checking for obsolete dependencies with deptry"
+	@poetry run deptry .
+	@echo "🚀 Checking for security vulnerabilities with bandit"
+	@poetry run bandit -c pyproject.toml -r resume_maker_ai_agent/ -ll
+
+
+.PHONY: test
+test: ## Run tests with pytest
+	@echo "🚀 Running tests with pytest"
+	@poetry run pytest --cov --cov-config=pyproject.toml --cov-report=term-missing
+
+
+# =============================
+# Build and Release
+# =============================
+.PHONY: bake
+bake: clean-bake ## Build wheel file using poetry
+	@echo "🚀 Creating wheel file"
+	@poetry build
+
+.PHONY: clean-bake
+clean-bake: ## Clean build artifacts
+	@rm -rf dist
+
+.PHONY: bump
+bump: ## Bump project version
+	@echo "🚀 Bumping version"
+	@poetry run bump-my-version bump $(BUMP_TYPE)
+
+.PHONY: publish
+publish: ## Publish a release to PyPI
+	@echo "🚀 Publishing: Dry run"
+	@poetry config pypi-token.pypi $(PYPI_TOKEN)
+	@poetry publish --dry-run
+	@echo "🚀 Publishing"
+	@poetry publish
+
+.PHONY: bake-and-publish
+bake-and-publish: bake publish ## Build and publish to PyPI
+
+.PHONY: update
+update: ## Update project dependencies
+	@echo "🚀 Updating project dependencies"
+	@poetry update
+	@poetry run pre-commit install --overwrite
+	@echo "Dependencies updated successfully"
+
+# =============================
+# Run and Documentation
+# =============================
+.PHONY: run
+run: ## Run the project's main application
+	@echo "🚀 Running the project"
+	@poetry run streamlit run $(PROJECT_SLUG)/app.py
+
+.PHONY: docs-test
+docs-test: ## Test if documentation can be built without warnings or errors
+	@poetry run mkdocs build -s
+
+.PHONY: docs
+docs: ## Build and serve the documentation
+	@poetry run mkdocs serve
+
+# =============================
+# Docker
+# =============================
+.PHONY: bake-container
+bake-container: ## Build Docker image
+	@echo "🚀 Building Docker image"
+	docker build -t $(IMAGE_NAME):$(TAG) -f Dockerfile .
+
+.PHONY: container-push
+container-push: ## Push Docker image to Docker Hub
+	@echo "🚀 Pushing Docker image to Docker Hub"
+	docker push $(IMAGE_NAME):$(TAG)
+
+.PHONY: bake-container-and-push
+bake-container-and-push: bake-container container-push ## Build and push Docker image to Docker Hub
+
+.PHONY: clean-container
+clean-container: ## Clean up Docker resources related to the app
+	@echo "🚀 Deleting Docker image for app: $(IMAGE_NAME)"
+	@docker images $(IMAGE_NAME) --format "{{.Repository}}:{{.Tag}}" | xargs -r docker rmi -f || echo "No image to delete"
+
+	@echo "🚀 Deleting unused Docker volumes"
+	@docker volume ls -qf dangling=true | xargs -r docker volume rm || echo "No unused volumes to delete"
+
+	@echo "🚀 Deleting unused Docker networks"
+	@docker network ls -q --filter "dangling=true" | xargs -r docker network rm || echo "No unused networks to delete"
+
+	@echo "🚀 Cleaning up stopped containers"
+	@docker ps -aq --filter "status=exited" | xargs -r docker rm || echo "No stopped containers to clean up"
+
+
+# =============================
+# Debug
+# =============================
+
+.PHONY: print-dependency-tree
+print-dependency-tree: ## Print dependency tree
+	@echo "Printing dependency tree..."
+	@poetry run pipdeptree -p $(PACKAGE_NAME)
+
+
+# =============================
+# Cleanup
+# =============================
+.PHONY: teardown
+teardown: clean-bake clean-container ## Clean up temporary files and directories and destroy the virtual environment, Docker image from your local machine
+	@echo "🚀 Cleaning up temporary files and directories"
+	@rm -rf .pytest_cache || true
+	@rm -rf dist || true
+	@rm -rf build || true
+	@rm -rf htmlcov || true
+	@rm -rf .venv || true
+	@rm -rf .mypy_cache || true
+	@rm -rf site || true
+	@find . -type d -name "__pycache__" -exec rm -rf {} + || true
+	@rm -rf .ruff_cache || true
+	@echo "🚀 Clean up completed."
+
+.PHONY: teardown-all
+teardown-all: teardown clean-cloud-env ## Clean up temporary files and directories and destroy the virtual environment, Docker image, and Cloud resources

README.md

@@ -0,0 +1,44 @@
+---
+title: Resume Maker AI
+emoji: 🎵
+colorFrom: blue
+colorTo: purple
+sdk: docker
+app_port: 7860
+short_description: AI service for making resumes.
+---
+
+# resume-maker-ai-agent
+
+This app will download Jio-Savan music.
+
+-   **Github repository**: <https://github.com/DeepakPant93/resume-maker-ai-agent/>
+-   **Documentation** <https://DeepakPant93.github.io/resume-maker-ai-agent/>
+
+## Getting started with your project
+
+First, create a repository on GitHub with the same name as this project, and then run the following commands:
+
+## Installation
+
+1. Initialize the repository if it's your first time:
+
+    ```bash
+    cd resume-maker-ai-agent
+    make init-repo
+    ```
+
+2. Install dependencies using Poetry:
+
+    ```bash
+    make bake-env
+    ```
+
+3. Run the FastAPI server:
+
+    ```bash
+    make run
+    ```
+
+You are now ready to start development on your project!
+The CI/CD pipeline will be triggered when you open a pull request, merge to main, or when you create a new release.

codecov.yaml

@@ -0,0 +1,9 @@
+coverage:
+    range: 70..100
+    round: down
+    precision: 1
+    status:
+        project:
+            default:
+                target: 90%
+                threshold: 0.5%

docker-compose.yml

@@ -0,0 +1,16 @@
+version: "3.9"
+
+services:
+    resume_maker_ai_agent:
+        build:
+            context: .
+            dockerfile: Dockerfile
+        container_name: resume_maker_ai_agent
+        ports:
+            - "7860:7860"
+        volumes:
+            - .:/app
+        environment:
+            - PYTHONUNBUFFERED=1
+        command: >
+            resume_maker_ai_agent

docs/index.md

@@ -0,0 +1,88 @@
+# resume-maker-ai-agent
+
+[![Release](https://img.shields.io/github/v/release/DeepakPant93/resume-maker-ai-agent)](https://img.shields.io/github/v/release/DeepakPant93/resume-maker-ai-agent)
+[![Build status](https://img.shields.io/github/actions/workflow/status/DeepakPant93/resume-maker-ai-agent/test-check-build.yml?branch=main)](https://github.com/DeepakPant93/resume-maker-ai-agent/actions/workflows/test-check-build.yml?query=branch%3Amain)
+[![Commit activity](https://img.shields.io/github/commit-activity/m/DeepakPant93/resume-maker-ai-agent)](https://img.shields.io/github/commit-activity/m/DeepakPant93/resume-maker-ai-agent)
+[![License](https://img.shields.io/github/license/DeepakPant93/resume-maker-ai-agent)](https://img.shields.io/github/license/DeepakPant93/resume-maker-ai-agent)
+
+This app will download Jio-Savan music.
+This repository contains a sample Data Science application built with FastAPI, designed to streamline model training and prediction processes via RESTful APIs. The application leverages **Poetry** for dependency management, ensuring a robust and scalable development environment.
+
+---
+
+## Features
+
+### FastAPI Endpoints:
+
+-   `/upload-docs`: API endpoint to upload documents for creating embeddings.
+-   `/ask`: API endpoint for querying the system and receiving context-aware answers.
+
+### Poetry for Dependency Management:
+
+-   Simplifies package installation and management.
+-   Ensures compatibility and reproducibility of the project environment.
+
+### Scalable Architecture:
+
+-   Modular design with clear separation of concerns.
+-   Easy integration of new features or pipelines.
+
+---
+
+## Prerequisites
+
+-   Python >= 3.12
+-   Poetry installed (`pip install poetry`)
+
+---
+
+## Installation
+
+1. Clone the repository:
+
+    ```bash
+    git clone https://github.com/DeepakPant93/resume-maker-ai-agent.
+    cd resume-maker-ai-agent
+    ```
+
+1. Initialize the repository if it's your first time:
+
+    ```bash
+    cd resume-maker-ai-agent
+    make init-repo
+    ```
+
+1. Install dependencies using Poetry:
+
+    ```bash
+    make bake-env
+    ```
+
+1. Run the FastAPI server:
+
+    ```bash
+    make run
+    ```
+
+---
+
+## Project Structure
+
+```plaintext
+──resume-maker-ai-agent/
+    ├── api         # API route definitions
+    ├── config      # Configuration files and settings
+    ├── constants   # Static constants and enumerations
+    ├── core        # Core logic for the application
+    ├── entity      # Definitions of data models and schemas
+    ├── exception   # Custom exception classes for error handling
+    ├── logger      # Logging setup for the application
+    ├── models      # Request and response models
+    ├── services    # Business logic and service layer
+    ├── utils       # Utility functions (e.g., file handling, data encoding)
+    └── main.py     # Entry point for the FastAPI application
+```
+
+---
+
+Enjoy building with this RAG FastAPI application! 🚀

docs/modules.md

@@ -0,0 +1,9 @@
+::: resume_maker_ai_agent
+
+## Models
+
+::: resume_maker_ai_agent.models
+
+## Services
+
+::: resume_maker_ai_agent.services

mkdocs.yml

@@ -0,0 +1,89 @@
+site_name: resume-maker-ai-agent
+repo_url: https://github.com/DeepakPant93/resume-maker-ai-agent
+site_url: https://DeepakPant93.github.io/resume-maker-ai-agent
+site_description: This app will download Jio-Savan music.
+site_author: Deepak pant
+edit_uri: edit/main/docs/
+repo_name: DeepakPant93/resume-maker-ai-agent
+copyright: Maintained by <a href="https://github.com/DeepakPant93/">Deepak pant</a>.
+
+nav:
+    - Home: index.md
+    - Modules: modules.md
+
+plugins:
+    - search
+    - tags
+    - mkdocstrings:
+          handlers:
+              python:
+                  setup_commands:
+                      show_source: false
+                      show_root_heading: true
+                      show_root_full_path: false
+                      heading_level: 3
+                      enable_inventory: true
+                      # - import sys
+                      # - sys.path.append('../')
+    # - git-revision-date-localized:  # Shows last updated date
+    #     enable_creation_date: true
+    - minify: # Minifies HTML and JS
+          minify_html: true
+          minify_js: true
+
+theme:
+    name: material
+    logo: assets/logo.png # Optional custom logo
+    favicon: assets/favicon.ico # Optional favicon
+    features:
+        - navigation.tabs # Top-level sections as tabs
+        - navigation.sections # Sections are expanded
+        - navigation.top # Back to top button
+        - search.suggest # Search suggestions
+        - search.highlight # Highlight search results
+        - content.tabs.link # Link code tabs
+        - content.code.annotate # Code block annotations
+        - content.copy.code # Copy code button
+    palette:
+        - media: "(prefers-color-scheme: light)"
+          scheme: default
+          primary: indigo
+          accent: deep orange
+          toggle:
+              icon: material/brightness-7
+              name: Switch to dark mode
+        - media: "(prefers-color-scheme: dark)"
+          scheme: slate
+          primary: black
+          accent: deep orange
+          toggle:
+              icon: material/brightness-4
+              name: Switch to light mode
+    icon:
+        repo: fontawesome/brands/github
+
+extra:
+    social:
+        - icon: fontawesome/brands/github
+          link: https://github.com/DeepakPant93/resume-maker-ai-agent
+        - icon: fontawesome/brands/python
+          link: https://pypi.org/project/resume-maker-ai-agent
+    # analytics:  # Optional Google Analytics
+    #   provider: google
+    #   property: G-XXXXXXXXXX  # Replace with your tracking ID
+
+markdown_extensions:
+    - toc:
+          permalink: true
+    - pymdownx.arithmatex:
+          generic: true
+    - pymdownx.highlight: # Advanced code highlighting
+          anchor_linenums: true
+          line_spans: __span
+          pygments_lang_class: true
+    - pymdownx.inlinehilite
+    - pymdownx.snippets
+    - pymdownx.superfences
+    - pymdownx.tabbed
+    - attr_list
+    - md_in_html

poetry.toml

@@ -0,0 +1,2 @@
+[virtualenvs]
+in-project = true

pyproject.toml

@@ -0,0 +1,195 @@
+[tool.poetry]
+name = "resume_maker_ai_agent"
+version = "0.0.1"
+description = "This app will download Jio-Savan music."
+authors = ["Deepak pant <deepak.93p@gmail.com>"]
+repository = "https://github.com/DeepakPant93/resume-maker-ai-agent"
+documentation = "https://DeepakPant93.github.io/resume-maker-ai-agent/"
+readme = "README.md"
+packages = [
+  {include = "resume_maker_ai_agent"}
+]
+
+[tool.poetry.scripts]
+resume_maker_ai_agent = "resume_maker_ai_agent.__main__:main"
+
+[tool.poetry.dependencies]
+python = ">=3.11,<3.13"
+crewai = {version = ">=0.86.0,<1.0.0", extras = ["tools"]}
+streamlit = "^1.41.1"
+selenium = "^4.27.1"
+# chromedriver_autoinstaller = "^0.6.4"
+# webdriver-manager = "*"
+bs4 = "*"
+
+[tool.poetry.group.dev.dependencies]
+deptry = "^0.16.2"  # For dependency management
+mypy = "^1.5.1"  # Static type checking
+pre-commit = "^3.4.0"  # Pre-commit hooks
+tox = "^4.11.1"  # Testing in multiple environments
+ipykernel = "^6.25.0"  # Jupyter kernel
+black = "^23.9.0"  # Code formatter
+build = "^1.0.0"  # Build management
+bump-my-version = "^0.28.2"  # Bump versions automatically
+codespell = "^2.2.5"  # Spell checking in code
+wheel = "^0.41.0"  # Build wheels
+twine = "^4.0.0"  # Publish packages
+bandit = "^1.8.0"  # Security check
+pylint = "^3.0.0"  # Powerful linter
+pydocstyle = "^6.3.0"  # Enforce PEP 257 docstring conventions
+# isort = "^5.12.0"  # Sort imports
+# ruff = "^0.8.6"  # Linting tool
+
+[tool.poetry.group.docs.dependencies]
+mkdocs = "^1.5.0"  # Documentation site generator
+sphinx = "^7.2.0"  # Documentation tool
+mkdocs-git-revision-date-plugin = "^0.3.2"  # Show revision dates
+mkdocs-git-revision-date-localized-plugin = "^1.3.0"  # Localized dates
+mkdocs-jupyter = ">=0.25.1"  # For Jupyter Notebook integration
+mkdocs-pdf-export-plugin = "^0.5.10"  # PDF export
+mkdocs-material = ">=9.1.3"  # MkDocs Material theme
+mkdocstrings-crystal = "^0.3.0"  # Mkdocstrings for Crystal
+pygments = "^2.16.0"  # Syntax highlighting
+pymdown-extensions = "^10.0"  # Markdown extensions
+nbconvert = "^7.7.0"  # Convert notebooks to other formats
+nbformat = "^5.9.0"  # Notebook format support
+livereload = "^2.6.3"  # Live reload for MkDocs
+watchdog = "^3.0.0"  # File monitoring
+mkdocstrings = {extras = ["python"], version = "^0.27.0"}  # Auto-generate documentation from docstrings
+mkdocs-minify-plugin = "^0.8.0"  # Minify HTML
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+
+[tool.mypy]
+files = ["resume_maker_ai_agent"]
+disallow_untyped_defs = true
+disallow_any_unimported = true
+no_implicit_optional = true
+check_untyped_defs = true
+warn_return_any = true
+warn_unused_ignores = true
+show_error_codes = true
+pretty = true
+show_traceback = true
+
+
+[[tool.mypy.overrides]]
+module = [
+    "joblib.*",
+    "yaml.*",
+    "ensure.*",
+    "fastapi_health.*",
+    "crewai.*",
+    "crewai_tools.*",
+    "bs4.*",
+    "resume_maker_ai_agent.crew"
+]
+ignore_missing_imports = true
+ignore_errors = true
+
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+norecursedirs = "legacy_tests"
+python_files = ["test_*.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+filterwarnings = [
+    "ignore:.*general_plain_validator_function.*:DeprecationWarning",
+    "ignore:.*with_info_plain_validator_function.*:DeprecationWarning"
+]
+
+
+[tool.ruff]
+target-version = "py39"
+line-length = 120
+fix = true
+select = [
+    # flake8-2020
+    "YTT",
+    # flake8-bandit
+    "S",
+    # flake8-bugbear
+    "B",
+    # flake8-builtins
+    "A",
+    # flake8-comprehensions
+    "C4",
+    # flake8-debugger
+    "T10",
+    # flake8-simplify
+    "SIM",
+    # isort
+    "I",
+    # mccabe
+    "C90",
+    # pycodestyle
+    "E", "W",
+    # pyflakes
+    "F",
+    # pygrep-hooks
+    "PGH",
+    # pyupgrade
+    "UP",
+    # ruff
+    "RUF",
+    # tryceratops
+    "TRY",
+]
+ignore = [
+    # LineTooLong
+    "E501",
+    # DoNotAssignLambda
+    "E731",
+    # Possible binding to all interfaces - Require for Docker container
+    "S104"
+]
+
+[tool.ruff.format]
+preview = true
+
+[tool.coverage.report]
+skip_empty = true
+
+
+[tool.coverage.run]
+branch = true
+source = ["resume_maker_ai_agent"]
+# parallel = true
+# concurrency = ["thread"]
+omit = [
+    "**/__init__.py", # Exclude all init files
+    "resume_maker_ai_agent/crew.py",  # Exclude crew.py file
+    "resume_maker_ai_agent/config/*",  # Exclude all files in config folder
+    "resume_maker_ai_agent/models/*",  # Exclude all files in model folder
+]
+
+[tool.ruff.per-file-ignores]
+"tests/*" = ["S101"]
+
+[tool.bumpversion]
+current_version = "0.0.1"
+commit = true
+tag = true
+
+[[tool.bumpversion.files]]
+glob = "pyproject.toml"
+search = 'version = "{current_version}"'
+replace = 'version = "{new_version}"'
+
+[tool.deptry]
+exclude = ["research","artifacts", "notebooks", "tests", "docs", ".venv", "venv", "__pycache__", ".ruff_cache", ".pytest_cache", ".mypy_cache", ".coverage", ".git", "build", "dist", ".github", "site", "config"]
+ignore = ["DEP003"]
+
+[tool.pydocstyle]
+select = ["D101", "D102"]
+
+[tool.isort]
+profile = "black"
+known_third_party = ["requests", "bs4", "pydantic", "crewai_tools"]
+default_section = "THIRDPARTY"
+force_sort_within_sections = true
+line_length = 120

resume_maker_ai_agent/__init__.py

@@ -0,0 +1,28 @@
+"""
+
+This is the initialization file for the RAG (Retrieval-Augmented Generation) application,
+designed to provide context-aware responses by combining document embeddings with large
+language model (LLM) capabilities. The application is modular, scalable, and maintains
+a clear separation of concerns across its components.
+
+Modules:
+    api: Exposes endpoints for document upload and querying the system.
+    config: Manages application settings and environment variables.
+    core: Implements embedding generation, LLM integration, and workflow orchestration.
+    models: Defines schemas for API request validation and response structuring.
+    service: Provides document management and vector database interaction services.
+    exception: Contains custom exceptions for handling application-specific errors.
+    utils: Offers utility functions for common operations and data manipulation.
+    logger: Implements centralized logging with customizable levels.
+    constants: Stores application-wide constants for consistency and maintainability.
+
+Features:
+    - **Retrieval-Augmented Generation**: Combines document embeddings with LLMs to deliver accurate, context-aware answers.
+    - **Modular Design**: Ensures scalability, maintainability, and ease of testing.
+    - **Error Handling and Logging**: Enhances debugging and monitoring with structured logs and custom exceptions.
+    - **Seamless Integration**: Connects document management, vector database, and LLM workflows efficiently.
+    - **User-Friendly API**: Simplifies user interaction with the application's core functionalities.
+
+This package serves as the backbone of the RAG application, ensuring a seamless pipeline
+from document ingestion to intelligent query resolution.
+"""

resume_maker_ai_agent/__main__.py

@@ -0,0 +1,30 @@
+# __main__.py
+import sys
+from pathlib import Path
+
+import streamlit.web.cli as stcli
+
+
+def main() -> None:
+    """
+    Sets up the environment to run a Streamlit application by modifying
+    system arguments and initiating the Streamlit CLI.
+
+    This function determines the current directory of the script, constructs
+    the path to the Streamlit app, updates the system arguments to run the
+    app, and then executes the Streamlit command-line interface to start the
+    application.
+
+    Exits the program when the Streamlit application exits, passing the
+    appropriate exit code.
+    """
+
+    current_dir = Path(__file__).parent
+    streamlit_app_path = current_dir / "app.py"
+
+    sys.argv = ["streamlit", "run", str(streamlit_app_path), "--server.port", "7860"]
+    sys.exit(stcli.main())
+
+
+if __name__ == "__main__":
+    main()

resume_maker_ai_agent/app.py

@@ -0,0 +1,53 @@
+import warnings
+
+import streamlit as st
+
+from resume_maker_ai_agent.services.app_service import search_music
+
+warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
+
+
+# Set page config
+st.set_page_config(page_title="Music Search", page_icon="🎵", layout="wide")
+
+# App title
+st.title("🎵 Music Search Results")
+
+search_query = st.sidebar.text_input("Enter song name or artist")
+
+if search_query:
+    # Show loading spinner
+    with st.spinner("Searching for music..."):
+        music_data = search_music(search_query)
+
+    if music_data is None or len(music_data) == 0:
+        st.warning("No music found. Please try again.")
+
+    for item in music_data:
+        try:
+            song_id = item["song_info"]["song_url"].split("/")[-1]  # Get unique ID from URL
+            song_title = item["song_info"]["title"].split(" - ")[0]
+            musicians = item["song_info"]["musician"]
+            artists = ", ".join(musicians[:2])
+            release_date = item["song_info"]["release_date"]
+
+            # Display song information in a row
+            with st.container():
+                # Create columns
+                col1, col2, col3, col4 = st.columns([1, 2, 2, 2])
+
+                # Column 1: Image
+                with col1:
+                    st.image(item["album_image_url"], width=100)
+
+                # Column 2: Title and Artists
+                with col2:
+                    st.markdown(f"**{song_title}**")
+                    st.markdown(f"*{artists} | {release_date}*")
+
+                # Column 4: Audio Player
+                with col4:
+                    st.audio(item["song_info"]["downloadable_url"])
+        except Exception as e:
+            print(f"An error occurred: {e!s}")
+            continue

resume_maker_ai_agent/config/agents.yaml

@@ -0,0 +1,9 @@
+music_researcher:
+    role: >
+        Senior Music Researcher at {website}
+    goal: >
+        Discover the latest music from {website} on {topic}
+    backstory: >
+        You're a seasoned music researcher with a passion for discovering new
+        music from {website}. Known for your ability to find the most relevant
+        information and present it in a clear and concise manner.

resume_maker_ai_agent/config/tasks.yaml

@@ -0,0 +1,7 @@
+music_research_task:
+    description: >
+        Find the latest music from  internet for {website} on {topic}. make sure you find the most
+        relevant information and present it in a clear and concise manner.
+    expected_output: >
+        A list of atleast 5 latest music links in a JSON with (title, link) format from internet on {topic}. Search the music in internet and get the most relevent {website} link.
+    agent: music_researcher

resume_maker_ai_agent/crew.py

@@ -0,0 +1,53 @@
+from crewai import Agent, Crew, Process, Task
+from crewai.project import CrewBase, agent, crew, task
+
+from resume_maker_ai_agent.models.response_models import MusicDetails
+from resume_maker_ai_agent.tools.custom_tool import search_tool
+
+
+@CrewBase
+class JioSavanMusicDownloaderAgent:
+    """JioSavanMusicDownloaderAgent crew"""
+
+    agents_config = "config/agents.yaml"
+    tasks_config = "config/tasks.yaml"
+
+    @agent
+    def music_researcher(self) -> Agent:
+        """
+        Creates a music researcher agent.
+
+        This agent is responsible for searching for the specified music on JioSaavn
+        and returning the results in a structured format.
+
+        :return: An instance of the Agent class
+        """
+        return Agent(config=self.agents_config["music_researcher"], verbose=True)
+
+    @task
+    def music_research_task(self) -> Task:
+        """
+        Creates the music research task.
+
+        This task is responsible for searching for the specified music on JioSaavn
+        and returning the results in a structured format.
+
+        :return: An instance of the Task class
+        """
+
+        return Task(
+            config=self.tasks_config["music_research_task"],
+            tools=[search_tool],
+            output_json=MusicDetails,
+        )
+
+    @crew
+    def crew(self) -> Crew:
+        """Creates the JioSavanMusicDownloaderAgent crew"""
+
+        return Crew(
+            agents=self.agents,  # Automatically created by the @agent decorator
+            tasks=self.tasks,  # Automatically created by the @task decorator
+            process=Process.sequential,
+            verbose=False,
+        )

resume_maker_ai_agent/models/__init__.py

@@ -0,0 +1,11 @@
+"""
+
+This module defines the data models used for API request and response handling.
+
+Components:
+    - Request Models: Defines the structure and validation rules for incoming API requests.
+    - Response Models: Specifies the format and schema for outgoing API responses.
+
+Purpose:
+    - Ensures consistent data validation and serialization across the application, adhering to defined schemas.
+"""

resume_maker_ai_agent/models/response_models.py

@@ -0,0 +1,16 @@
+from pydantic import BaseModel
+
+
+class MusicLink(BaseModel):
+    """
+    A class representing a music link."""
+
+    title: str
+    link: str
+
+
+class MusicDetails(BaseModel):
+    """
+    A class representing music details."""
+
+    links: list[MusicLink]

resume_maker_ai_agent/services/__init__.py

@@ -0,0 +1,11 @@
+"""
+
+This module provides the core services for managing documents and vector database operations.
+
+Components:
+    - Document Service: Handles document-related operations such as storage, retrieval, and preprocessing.
+    - Vector DB Service: Manages interactions with the vector database, including storing and querying embeddings.
+
+Purpose:
+    - Implements the business logic and service layer to support the application's RAG functionality.
+"""

resume_maker_ai_agent/services/app_service.py

@@ -0,0 +1,41 @@
+import warnings
+
+from resume_maker_ai_agent.crew import JioSavanMusicDownloaderAgent
+from resume_maker_ai_agent.services.web_scarapper_service import scrape_pages
+
+warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
+
+
+def search_music(query: str) -> list[dict]:
+    music_details = []
+    try:
+        # Search the internet for music
+        print(f"Searching for music: {query}")
+        search_results = search_internet(query)
+        print(f"Found {len(search_results)} results")
+
+        # Get music details
+        print("Getting music details")
+        music_details = get_music_details(search_results)
+        print(f"Got details for {len(music_details)} songs")
+        print(f"Music details: {music_details}")
+        print("Done")
+    except Exception as e:
+        print(f"An error occurred: {e!s}")
+
+    return music_details
+
+
+def search_internet(query: str) -> list[dict]:
+    # Run the crew
+    inputs = {"website": "https://www.jiosaavn.com", "topic": query}
+    result = JioSavanMusicDownloaderAgent().crew().kickoff(inputs=inputs)
+    links = result.to_dict().get("links", [])
+    return links if isinstance(links, list) else []
+
+
+def get_music_details(songs: list[dict]) -> list[dict]:
+    # Get music details by scrapping the pages
+
+    links: list[str] = [album["link"] for album in songs]
+    return scrape_pages(links)

resume_maker_ai_agent/services/web_scarapper_service.py

@@ -0,0 +1,226 @@
+import time
+from datetime import datetime
+from typing import Any
+from urllib.parse import urlparse
+
+import requests
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.common.exceptions import TimeoutException
+from selenium.webdriver.chrome.service import Service
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.ui import WebDriverWait
+
+
+def _setup_driver() -> webdriver.Chrome:
+    # Setup Chrome WebDriver (or other driver)
+    options = webdriver.ChromeOptions()
+
+    # Essential container arguments
+    options.add_argument("--headless=new")
+    options.add_argument("--disable-gpu")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+
+    # JavaScript-specific configurations
+    options.add_argument("--enable-javascript")
+    options.add_argument("--disable-web-security")
+    options.add_argument("--allow-running-insecure-content")
+
+    # Performance optimizations
+    options.add_argument("--window-size=1920,1080")
+    options.add_argument("--disable-extensions")
+    options.add_argument("--disable-setuid-sandbox")
+
+    # Memory management
+    options.add_argument("--disable-dev-tools")
+    options.add_argument("--no-zygote")
+    options.add_argument("--single-process")
+
+    # Handle Chrome Driver installation
+    try:
+        # For container environments, specify the Chrome version
+        print("Setting up Chrome WebDriver")
+        chrome_service = Service("/usr/bin/chromedriver")
+        driver = webdriver.Chrome(service=chrome_service, options=options)
+        driver = webdriver.Chrome(options=options)
+    except Exception as e:
+        # Fallback to direct path if ChromeDriverManager fails
+        print(f"An error occurred: {e!s}")
+        print("Falling back to direct path")
+
+        driver = webdriver.Chrome(options=options)
+    return driver
+
+
+def _get_downloadable_audio_link(url: str) -> str:
+    if not url:
+        return ""
+
+    # Extract the album ID and file ID from the URL
+    parsed_url = urlparse(url)
+    path_parts = parsed_url.path.split("/")
+    album_id = path_parts[-2]
+    file_id = path_parts[-1].split(".")[0]
+
+    # Construct the downloadable audio link
+    return f"https://aac.saavncdn.com/{album_id}/{file_id}.mp4"
+
+
+def _extract_musician_name(url: str) -> str:
+    return url.split("/")[-2].replace("-songs", "").replace("-", " ").title()
+
+
+def scrape_dynamic_page(url: str, wait_time: int = 5) -> dict[str, Any]:
+    """
+    Scrape a webpage including content loaded by JavaScript
+
+    Parameters:
+    url (str): The URL to scrape
+    wait_time (int): Maximum time to wait for dynamic content to load
+
+    Returns:
+    dict: Dictionary containing various elements from the page
+    """
+    driver = _setup_driver()
+
+    try:
+        # Load the page
+        driver.get(url)
+
+        # Wait for the button to be present
+        button = WebDriverWait(driver, wait_time).until(
+            EC.presence_of_element_located((By.CSS_SELECTOR, 'a.c-btn.c-btn--primary[data-btn-icon="q"]'))
+        )
+
+        # Check visibility and enablement
+        is_displayed = button.is_displayed()
+        is_enabled = button.is_enabled()
+        print(f"Button displayed: {is_displayed}, Button enabled: {is_enabled}")
+
+        if is_displayed and is_enabled:
+            # Click the button
+            driver.execute_script("arguments[0].scrollIntoView(true);", button)
+            driver.execute_script("arguments[0].click();", button)
+        else:
+            print("Button is not interactable!")
+
+        # Wait a moment for any JavaScript updates
+        time.sleep(5)
+
+        # Get the updated HTML
+        html_content = driver.page_source
+        soup = BeautifulSoup(html_content, "html.parser")
+
+        # Extract elements
+        details = {
+            "album_title": soup.title.text if soup.title else "",
+            "description": soup.find("meta", {"name": "description"})["content"]
+            if soup.find("meta", {"name": "description"})
+            else "",
+            "album_description": soup.find("meta", {"property": "og:description"})["content"]
+            if soup.find("meta", {"property": "og:description"})
+            else "",
+            "album_url": soup.find("meta", {"property": "music:album"})["content"]
+            if soup.find("meta", {"property": "music:album"})
+            else "",
+            "album_image_url": soup.find("meta", {"property": "twitter:image"})["content"]
+            if soup.find("meta", {"property": "twitter:image"})
+            else "",
+            "song_info": {
+                "name": soup.title.text if soup.title else "",
+                "title": soup.find("meta", {"property": "twitter:title"})["content"]
+                if soup.find("meta", {"property": "twitter:title"})
+                else "",
+                "musician": [
+                    _extract_musician_name(musician["content"])
+                    for musician in soup.find_all("meta", {"property": "music:musician"})
+                ],
+                "release_date": datetime.strptime(
+                    soup.find("meta", {"property": "music:release_date"})["content"],
+                    "%Y-%m-%d",
+                ).strftime("%B %d, %Y")
+                if soup.find("meta", {"property": "music:release_date"})
+                else "",
+                "song_url": soup.find("meta", {"property": "twitter:url"})["content"]
+                if soup.find("meta", {"property": "twitter:url"})
+                else "",
+                "description": soup.find("meta", {"property": "twitter:description"})["content"]
+                if soup.find("meta", {"property": "twitter:description"})
+                else "",
+                "downloadable_url": _get_downloadable_audio_link(
+                    soup.find("audio").find("source")["src"] if soup.find("audio").find("source") else ""
+                ),
+                "song_lyrics_url": "https://www.jiosaavn.com" + soup.find("a", title="Song Lyrics")["href"]
+                if soup.find("a", title="Song Lyrics")
+                else "",
+            },
+        }
+    except TimeoutException:
+        print(f"Timeout waiting for page to load: {url}")
+        return {}
+    except Exception as e:
+        print(f"An error occurred: {e!s}")
+        return {}
+    else:
+        return details
+    finally:
+        driver.quit()
+
+
+def scrape_pages(urls: list[str]) -> list[dict]:
+    """
+    Scrape multiple webpages and return a list of elements
+
+    Parameters:
+    urls (list of str): List of URLs to scrape
+    wait_time (int): Maximum time to wait for dynamic content to load
+
+    Returns:
+    list of dict: List of dictionaries containing various elements from each page
+    """
+    results = []
+    for url in urls:
+        details = scrape_dynamic_page(url)
+        if details:
+            results.append(details)
+    return results
+
+
+def download_file(url: str) -> None:
+    """
+    Download a file from a URL and save it to a local file
+
+    Parameters:
+    url (str): URL of the file to be downloaded
+
+    Returns:
+    None
+    """
+    try:
+        response = requests.get(url, stream=True, timeout=10)
+
+        # Check if the request was successful
+        if response.status_code == 200:
+            # Open a local file with the specified filename in binary write mode
+            filename = _get_filename_name(url)
+            filename = f"downloads/{filename}.mp4"
+
+            with open(filename, "wb") as file:
+                # Write the content of the response to the file in chunks
+                for chunk in response.iter_content(chunk_size=8192):
+                    file.write(chunk)
+            print(f"File downloaded successfully as '{filename}'")
+        else:
+            print(f"Failed to download file. HTTP Status Code: {response.status_code}")
+    except requests.exceptions.Timeout:
+        print(f"Request to {url} timed out.")
+    except requests.exceptions.RequestException as e:
+        print(f"Request to {url} failed: {e}")
+
+
+def _get_filename_name(url: str) -> str:
+    parsed_url = urlparse(url)
+    path_parts = parsed_url.path.split("/")
+    return path_parts[2]

resume_maker_ai_agent/tools/custom_tool.py

@@ -0,0 +1,9 @@
+from crewai_tools import FileWriterTool, ScrapeWebsiteTool, SerperDevTool
+
+jio_savan_scapper_tool = ScrapeWebsiteTool(website_url="https://www.jiosaavn.com")
+file_writer_tool = FileWriterTool()
+search_tool = SerperDevTool(
+    country="in",  # Set to 'in' for India
+    locale="en",  # Set locale to English
+    n_results=5,  # You can adjust the number of results as needed
+)

tox.ini

@@ -0,0 +1,16 @@
+[tox]
+skipsdist = true
+envlist = py311, py312
+
+[gh-actions]
+python =
+    3.11: py311
+    3.12: py312
+
+[testenv]
+passenv = PYTHON_VERSION
+allowlist_externals = poetry
+commands =
+    poetry install -v
+    pytest --doctest-modules tests --cov --cov-config=pyproject.toml --cov-report=xml
+    mypy