Updated poetry setup

.devcontainer/devcontainer.json

@@ -15,7 +15,10 @@
     },
     // Use 'postCreateCommand' to run commands after the container is created.
     "postCreateCommand": "./.devcontainer/postCreateCommand.sh",
-    "forwardPorts": [7860, 8000],
+    "forwardPorts": [
+        7860,
+        8000
+    ],
     // Configure tool-specific properties.
     "customizations": {
         "vscode": {
@@ -30,10 +33,13 @@
                 "ms-python.python", // Python
                 "ms-python.black-formatter", // Black
                 "ms-python.debugpy", // Debugger for Python
-                "redhat.vscode-yaml" // YAML
+                "redhat.vscode-yaml", // YAML
+                "tamasfe.even-better-toml" // TOML
             ],
             "settings": {
-                "python.testing.pytestArgs": ["tests"],
+                "python.testing.pytestArgs": [
+                    "tests"
+                ],
                 "python.testing.unittestEnabled": false,
                 "python.testing.pytestEnabled": true,
                 "python.defaultInterpreterPath": "/workspaces/resume-maker-ai-agent/.venv/bin/python",

.vscode/settings.json

@@ -12,5 +12,6 @@
         "**/coverage.xml": true,
         "**/build": true,
         "**/dist": true
-    }
+    },
+    "makefile.makefilePath": "/workspaces/resume-maker-ai-agent/Makefile"
 }

Makefile

@@ -39,7 +39,7 @@ help: ## Display this help message
 .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 install --all-extras
 	@poetry run pre-commit install || true
 	@max_retries=3; count=0; \
 	while ! make lint; do \
@@ -73,58 +73,6 @@ init-repo: ## Initialize git repository
 	@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
@@ -184,7 +132,7 @@ bake-and-publish: bake publish ## Build and publish to PyPI
 .PHONY: update
 update: ## Update project dependencies
 	@echo "🚀 Updating project dependencies"
-	@poetry update
+	@poetry update --all-extras
 	@poetry run pre-commit install --overwrite
 	@echo "Dependencies updated successfully"
 
@@ -194,7 +142,7 @@ update: ## Update project dependencies
 .PHONY: run
 run: ## Run the project's main application
 	@echo "🚀 Running the project"
-	@poetry run streamlit run $(PROJECT_SLUG)/app.py
+	@poetry run streamlit run $(PROJECT_SLUG)/app2.py --server.port 7860
 
 .PHONY: docs-test
 docs-test: ## Test if documentation can be built without warnings or errors
@@ -263,4 +211,4 @@ teardown: clean-bake clean-container ## Clean up temporary files and directories
 	@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
+teardown-all: teardown ## Clean up temporary files and directories and destroy the virtual environment, Docker image, and Cloud resources

README.md

@@ -1,6 +1,6 @@
 ---
 title: Resume Maker AI
-emoji: 🎵
+emoji: 📄
 colorFrom: blue
 colorTo: purple
 sdk: docker

pyproject.toml

@@ -1,68 +1,65 @@
-[tool.poetry]
+[project]
 name = "resume_maker_ai_agent"
 version = "0.0.1"
 description = "This app will download Jio-Savan music."
-authors = ["Deepak pant <deepak.93p@gmail.com>"]
+readme = "README.md"
+authors = [{ name = "Deepak Pant", email = "deepak.93p@gmail.com" }]
+requires-python = ">=3.10,<=3.13"
+dependencies = [
+    "crewai[tools]>=0.86.0,<1.0.0",
+    "streamlit >=1.41.1",
+    # "PyPDF2 >=3.0.1",
+    # "python-docx >=1.1.2",
+]
+
+[project.urls]
 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"}
+
+
+[project.optional-dependencies]
+dev = [
+    "deptry==0.16.2",
+    "mypy==1.5.1",
+    "pre-commit==3.4.0",
+    "tox==4.11.1",
+    "ipykernel==6.25.0",
+    "black==23.9.0",
+    "build==1.2.2",
+    "bump-my-version==0.28.2",
+    "codespell==2.2.5",
+    "wheel==0.41.0",
+    "twine==4.0.0",
+    "bandit==1.8.0",
+    "pylint==3.0.0",
+    "pydocstyle==6.3.0",
+]
+docs = [
+    "mkdocs==1.5.0",
+    "sphinx==7.2.0",
+    "mkdocs-git-revision-date-plugin==0.3.2",
+    "mkdocs-git-revision-date-localized-plugin==1.3.0",
+    "mkdocs-jupyter>=0.25.1",
+    "mkdocs-pdf-export-plugin==0.5.10",
+    "mkdocs-material>=9.1.3",
+    "mkdocstrings-crystal==0.3.7",
+    "pygments==2.16.0",
+    "pymdown-extensions==10.0",
+    "nbconvert==7.16.5",
+    "nbformat==5.9.0",
+    "livereload==2.6.3",
+    "watchdog==3.0.0",
+    "mkdocstrings[python]==0.27.0",
+    "mkdocs-minify-plugin==0.8.0",
 ]
 
-[tool.poetry.scripts]
+[project.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"]
+requires = ["poetry-core>=2.0.0"]
 build-backend = "poetry.core.masonry.api"
 
-
 [tool.mypy]
 files = ["resume_maker_ai_agent"]
 disallow_untyped_defs = true
@@ -85,7 +82,7 @@ module = [
     "crewai.*",
     "crewai_tools.*",
     "bs4.*",
-    "resume_maker_ai_agent.crew"
+    "resume_maker_ai_agent.crew",
 ]
 ignore_missing_imports = true
 ignore_errors = true
@@ -99,7 +96,7 @@ python_classes = ["Test*"]
 python_functions = ["test_*"]
 filterwarnings = [
     "ignore:.*general_plain_validator_function.*:DeprecationWarning",
-    "ignore:.*with_info_plain_validator_function.*:DeprecationWarning"
+    "ignore:.*with_info_plain_validator_function.*:DeprecationWarning",
 ]
 
 
@@ -127,7 +124,8 @@ select = [
     # mccabe
     "C90",
     # pycodestyle
-    "E", "W",
+    "E",
+    "W",
     # pyflakes
     "F",
     # pygrep-hooks
@@ -145,7 +143,7 @@ ignore = [
     # DoNotAssignLambda
     "E731",
     # Possible binding to all interfaces - Require for Docker container
-    "S104"
+    "S104",
 ]
 
 [tool.ruff.format]
@@ -161,10 +159,10 @@ source = ["resume_maker_ai_agent"]
 # parallel = true
 # concurrency = ["thread"]
 omit = [
-    "**/__init__.py", # Exclude all init files
+    "**/__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
+    "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]
@@ -181,7 +179,26 @@ 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"]
+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]

resume_maker_ai_agent/app2.py

@@ -0,0 +1,64 @@
+import streamlit as st
+# import PyPDF2
+import io
+# from docx import Document
+# from docx.shared import Inches
+import openai
+# import tempfile
+
+from resume_maker_ai_agent.services.app_service import run, create_docx
+
+
+def main():
+    print("main......")
+    st.set_page_config(page_title="Resume Maker AI", page_icon="📄")
+
+    st.title("Resume Maker AI")
+    st.write("Customize your resume for specific job descriptions using AI")
+
+    # File upload
+    uploaded_file = st.file_uploader("Upload your resume (PDF)", type="pdf")
+
+    # Job description input
+    job_description = st.text_area("Enter the job description:", height=200)
+
+    if st.button("Customize Resume") and uploaded_file is not None and job_description:
+        with st.spinner("Customizing your resume..."):
+            try:
+                # Customize resume
+                customized_resume = run(
+                    uploaded_file, job_description)
+
+                # Display customized resume
+                st.subheader("Customized Resume")
+                st.write(customized_resume)
+
+                # Create download button
+                doc_buffer = create_docx(customized_resume)
+                st.download_button(
+                    label="Download Customized Resume",
+                    data=doc_buffer,
+                    file_name="customized_resume.docx",
+                    mime="application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+                )
+
+            except Exception as e:
+                st.error(f"An error occurred: {str(e)}")
+
+    # Add instructions and tips
+    with st.expander("How to use"):
+        st.write("""
+        1. Upload your current resume in PDF format
+        2. Paste the job description you're targeting
+        3. Click 'Customize Resume' to generate a tailored version
+        4. Review the customized resume
+        5. Download the result as a Word document
+        """)
+
+    # Footer
+    st.markdown("---")
+    st.markdown("Built with Streamlit and Crew AI")
+
+
+if __name__ == "__main__":
+    main()

resume_maker_ai_agent/config/agents.yaml

@@ -1,9 +1,39 @@
-music_researcher:
+job_researcher:
     role: >
-        Senior Music Researcher at {website}
+        Job Researcher
     goal: >
-        Discover the latest music from {website} on {topic}
+        Make sure to do amazing analysis on
+        job posting to help job applicants
     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.
+        As a Job Researcher, your prowess in
+        navigating and extracting critical
+        information from job postings is unmatched.
+        Your skills help pinpoint the necessary
+        qualifications and skills sought
+        by employers, forming the foundation for
+        effective application tailoring.
+
+profiler:
+    role: >
+        Personal Profiler for Engineers
+    goal: >
+        Make sure to do amazing analysis on
+        job posting to help job applicants
+    backstory: >
+        Equipped with analytical prowess, you dissect
+        and synthesize information
+        from diverse sources to craft comprehensive
+        personal and professional profiles, laying the
+        groundwork for personalized resume enhancements.
+
+resume_strategist:
+    role: >
+        Resume Strategist
+    goal: >
+        Find all the best ways to make a
+        resume stand out in the job market.
+    backstory: >
+        With a strategic mind and an eye for detail, you
+        excel at refining resumes to highlight the most
+        relevant skills and experiences, ensuring they
+        resonate perfectly with the job's requirements.

resume_maker_ai_agent/config/tasks.yaml

@@ -1,7 +1,45 @@
-music_research_task:
+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.
+        Analyze the job description to extract key skills, experiences, and qualifications
+        required. Use the tools to gather content and identify
+        and categorize the requirements.
+
+        Job Description:
+        ---
+        ({job_description})
+        ---
     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
+        A structured list of job requirements, including necessary
+        skills, qualifications, and experiences.
+    agent: job_researcher
+
+profile_task:
+    description: >
+        Compile a detailed personal and professional profile
+        using provided resume:
+
+        Resume:
+        ---
+        ({resume_text})
+        ---
+        Utilize tools to extract and synthesize information from these sources.
+    expected_output: >
+        A comprehensive profile document that includes skills,
+        project experiences, contributions, interests, and
+        communication style.
+    agent: profiler
+
+resume_strategy_task:
+    description: >
+        Using the profile and job requirements obtained from
+        previous tasks, tailor the resume to highlight the most
+        relevant areas. Employ tools to adjust and enhance the
+        resume content. Make sure this is the best resume even but
+        don't make up any information. Update every section,
+        inlcuding the initial summary, work experience, skills,
+        and education. All to better reflrect the candidates
+        abilities and how it matches the job posting.
+    expected_output: >
+        An updated resume that effectively highlights the candidate's
+        qualifications and experiences relevant to the job.
+    agent: resume_strategist

resume_maker_ai_agent/crew.py

@@ -3,42 +3,105 @@ 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
+import warnings
+
+warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
 
 
 @CrewBase
-class JioSavanMusicDownloaderAgent:
-    """JioSavanMusicDownloaderAgent crew"""
+class ResumeMakerAIAgent:
+    """ResumeMakerAIAgent crew"""
 
     agents_config = "config/agents.yaml"
     tasks_config = "config/tasks.yaml"
 
     @agent
-    def music_researcher(self) -> Agent:
+    def job_researcher(self) -> Agent:
+        """
+        Creates the job researcher agent.
+
+        This agent is responsible for searching for job openings.
+
+        :return: An instance of the Agent class
+        """
+
+        return Agent(config=self.agents_config["job_researcher"],
+                     tools=[search_tool],
+                     verbose=True)
+
+    @agent
+    def profiler(self) -> Agent:
         """
-        Creates a music researcher agent.
+        Creates the profiler agent.
 
-        This agent is responsible for searching for the specified music on JioSaavn
-        and returning the results in a structured format.
+        This agent is responsible for researching and generating music details.
 
         :return: An instance of the Agent class
         """
-        return Agent(config=self.agents_config["music_researcher"], verbose=True)
+
+        return Agent(config=self.agents_config["profiler"],
+                     tools=[search_tool],
+                     verbose=True)
+
+    @agent
+    def resume_strategist(self) -> Agent:
+        """
+        Creates the resume strategist agent.
+
+        This agent is responsible for customizing resumes based on job
+        descriptions.
+
+        :return: An instance of the Agent class
+        """
+
+        return Agent(config=self.agents_config["resume_strategist"],
+                     tools=[search_tool],
+                     verbose=True)
+
+    @task
+    def research_task(self) -> Task:
+        """
+        Creates the research task.
+
+        This task is responsible for searching for job openings.
+
+        :return: An instance of the Task class
+        """
+
+        return Task(
+            config=self.tasks_config["research_task"],
+            async_execution=True
+        )
+
+    @task
+    def profile_task(self) -> Task:
+        """
+        Creates the profile task.
+
+        This task is responsible for researching and generating music details.
+
+        :return: An instance of the Task class
+        """
+
+        return Task(
+            config=self.tasks_config["profile_task"],
+            async_execution=True
+        )
 
     @task
-    def music_research_task(self) -> Task:
+    def profile_task(self) -> Task:
         """
-        Creates the music research task.
+        Creates the profile task.
 
-        This task is responsible for searching for the specified music on JioSaavn
-        and returning the results in a structured format.
+        This task is responsible for generating a profile based on the output
+        of the research task.
 
         :return: An instance of the Task class
         """
 
         return Task(
-            config=self.tasks_config["music_research_task"],
-            tools=[search_tool],
-            output_json=MusicDetails,
+            config=self.tasks_config["profile_task"],
+            context=[research_task, profile_task],
         )
 
     @crew

resume_maker_ai_agent/services/app_service.py

@@ -1,41 +1,50 @@
 import warnings
+import PyPDF2
+# from docx import Document
+import io
 
-from resume_maker_ai_agent.crew import JioSavanMusicDownloaderAgent
-from resume_maker_ai_agent.services.web_scarapper_service import scrape_pages
+from resume_maker_ai_agent.crew import ResumeMakerAIAgent
+from streamlit.runtime.uploaded_file_manager import UploadedFile
 
-warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
 
+def _extract_text_from_pdf(pdf_file_path):
+    """Extract text content from uploaded PDF file."""
+    pdf_reader = PyPDF2.PdfReader(pdf_file_path)
+    text = ""
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+    return text
 
-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}")
+def run(pdf_file_path: UploadedFile, job_description: str) -> str:
+    """
+    Processes a PDF resume file, customizes it based on the job description,
+    and returns the updated resume text.
 
-    return music_details
+    :param pdf_file_path: Path to the PDF file containing the resume.
+    :param job_description: Description of the job for which the resume needs to be customized.
+    :return: A string representing the updated resume content.
+    """
 
+    print("Extracting text from PDF")
+    resume_text = _extract_text_from_pdf(pdf_file_path)
 
-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 []
+    print("Running the crew")
+    inputs = {"resume_text": resume_text, "job_description": job_description}
+    result = ResumeMakerAIAgent().crew().kickoff(inputs=inputs)
 
+    return result.raw
 
-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)
+def create_docx(content):
+    """Create a Word document with the content."""
+    # doc = Document()
+    # doc.add_paragraph(content)
+
+    # # Save to bytes buffer
+    # buffer = io.BytesIO()
+    # doc.save(buffer)
+    # buffer.seek(0)
+    # return buffer
+    return none

resume_maker_ai_agent/services/web_scarapper_service.py

@@ -1,226 +0,0 @@
-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

@@ -1,9 +1,4 @@
-from crewai_tools import FileWriterTool, ScrapeWebsiteTool, SerperDevTool
+from crewai_tools import FileWriterTool, 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
-)
+search_tool = SerperDevTool()