Upload 4 files

.gitignore

@@ -0,0 +1,38 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Virtual Environment
+venv/
+env/
+ENV/
+
+# IDE specific files
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# OS generated files
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Logs and databases
+*.log
+*.sqlite
+*.db
+
+# Environment variables
+.env
+
+# Downloaded models
+*.bin
+*.h5
+*.pth
+*.pt

README.md

@@ -1,19 +1,102 @@
----
-title: Mypythonapp
-emoji: 🚀
-colorFrom: red
-colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
-pinned: false
-short_description: Streamlit template space
----
-
-# Welcome to Streamlit!
-
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
-
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+# Resume Parser & Summarizer (Streamlit + Hugging Face)
+
+A Streamlit web app that parses resumes (PDF/DOCX) and generates an AI summary using the Hugging Face Inference API. It extracts contact details and detected skills and produces a concise summary.
+
+## Features
+
+- Upload resumes in PDF or DOCX
+- Extract contact information (email, phone)
+- Detect common technical skills via keyword scan
+- Summarize resume content using a Hugging Face summarization model
+- Streamlit UI with sidebar for HF model and API token
+
+## Local Installation
+
+1. Clone the repository:
+   ```bash
+   git clone <repository-url>
+   cd windsurf-project-2
+   ```
+
+2. Create a virtual environment (recommended):
+   ```bash
+   python -m venv venv
+   source venv/bin/activate  # On Windows: venv\Scripts\activate
+   ```
+
+3. Install the required packages:
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+4. (Optional) Set your Hugging Face token for higher rate limits:
+   ```bash
+   # Windows (PowerShell)
+   setx HF_TOKEN "hf_XXXXXXXXXXXXXXXXXXXXXXXXXXXX"
+   # macOS/Linux
+   export HF_TOKEN="hf_XXXXXXXXXXXXXXXXXXXXXXXXXXXX"
+   ```
+
+## Usage
+
+1. Run the Streamlit application:
+   ```bash
+   streamlit run app.py
+   ```
+
+2. Open your web browser and navigate to `http://localhost:8501`
+
+3. Upload a resume file (PDF or DOCX) using the file uploader
+
+4. In the sidebar, set the summarization model (default: `facebook/bart-large-cnn`) and provide your HF API token if not set as a secret or environment variable.
+
+5. View extracted info and the AI-generated summary.
+
+## Hugging Face Inference API
+
+This app uses the Hugging Face Inference API via `huggingface-hub` to run text summarization. You can choose a model such as:
+
+- `facebook/bart-large-cnn` (default)
+- `sshleifer/distilbart-cnn-12-6` (faster, smaller)
+
+You may supply an API token via any of the following (priority order):
+
+1. `st.secrets["HF_TOKEN"]`
+2. Environment variable `HF_TOKEN`
+3. Sidebar password input
+
+Create a token at: https://huggingface.co/settings/tokens
+
+## Deploy to Hugging Face Spaces
+
+1. Create a new Space at https://huggingface.co/spaces and choose "Streamlit" as the SDK.
+2. Push your repository files (ensure `app.py` and `requirements.txt` are present).
+3. In the Space, go to Settings → Secrets and add:
+   - Key: `HF_TOKEN`
+   - Value: your Hugging Face token
+4. The app will build automatically. Once running, you can change models from the sidebar.
+
+Notes:
+- Keep dependencies minimal for faster builds (see `requirements.txt`).
+- Uploaded files are kept in the Space runtime; do not rely on persistence across restarts.
+
+## Dependencies
+
+- Python 3.9+
+- Streamlit
+- PyPDF2
+- python-docx
+- huggingface-hub
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Notes & Next Steps
+
+This is a lightweight implementation designed to run well on Hugging Face Spaces. Ideas to extend:
+
+- Use a custom summarization prompt or instruction-tuned models.
+- Add job description matching and scoring.
+- Export parsed data to CSV/JSON.
+- Improve skill/entity extraction with advanced NLP if needed.

app.py

@@ -0,0 +1,78 @@
+import streamlit as st
+import os
+from utils.resume_parser import parse_resume
+from utils.ai_summarizer import summarize_resume
+
+# Set page config
+st.set_page_config(
+    page_title="Resume Parser & Summarizer",
+    page_icon="📄",
+    layout="wide"
+)
+
+def main():
+    st.title("📄 Resume Parser & Summarizer")
+    st.write("Upload a resume (PDF or DOCX) to extract and summarize key information.")
+    
+    # Create necessary directories
+    os.makedirs("data", exist_ok=True)
+    
+    # Sidebar: Hugging Face Settings
+    st.sidebar.header("Hugging Face Settings")
+    default_model = "facebook/bart-large-cnn"
+    hf_model = st.sidebar.text_input(
+        "Summarization model (repo id)", value=default_model,
+        help="e.g., facebook/bart-large-cnn, sshleifer/distilbart-cnn-12-6"
+    )
+    # Prefer token from secrets, then environment, then user input
+    secrets_token = st.secrets.get("HF_TOKEN") if hasattr(st, "secrets") else None
+    env_token = os.environ.get("HF_TOKEN")
+    token_placeholder = "Using st.secrets['HF_TOKEN']" if secrets_token else ("Using env HF_TOKEN" if env_token else "Paste your token (optional)")
+    input_token = st.sidebar.text_input("Hugging Face API Token", value="", type="password", help=token_placeholder)
+    hf_token = input_token or secrets_token or env_token
+    
+    # File uploader
+    uploaded_file = st.file_uploader("Choose a resume file", type=["pdf", "docx"])
+    
+    if uploaded_file is not None:
+        # Save the uploaded file
+        file_path = os.path.join("data", uploaded_file.name)
+        with open(file_path, "wb") as f:
+            f.write(uploaded_file.getbuffer())
+        
+        st.success(f"Successfully uploaded {uploaded_file.name}")
+        
+        # Parse the resume
+        with st.spinner("Parsing resume..."):
+            resume_data = parse_resume(file_path)
+        
+        if resume_data:
+            st.subheader("Extracted Information")
+            
+            # Display basic info
+            col1, col2 = st.columns(2)
+            with col1:
+                if resume_data.get('name'):
+                    st.markdown(f"**Name:** {resume_data['name']}")
+                if resume_data.get('email'):
+                    st.markdown(f"**Email:** {resume_data['email']}")
+                if resume_data.get('phone'):
+                    st.markdown(f"**Phone:** {resume_data['phone']}")
+            
+            with col2:
+                if resume_data.get('skills'):
+                    st.markdown("**Skills:**")
+                    st.write(", ".join(resume_data['skills']))
+            
+            # Generate and display summary
+            with st.spinner("Generating summary..."):
+                summary = summarize_resume(resume_data, hf_model=hf_model, hf_token=hf_token)
+                st.subheader("AI-Powered Summary")
+                st.write(summary)
+            
+            # Display full text (collapsible)
+            with st.expander("View Full Extracted Text"):
+                st.text(resume_data.get('raw_text', 'No text extracted'))
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -1,3 +1,5 @@
-altair
-pandas
-streamlit
+streamlit==1.32.0
+python-docx==1.1.0
+PyPDF2==3.0.1
+huggingface-hub==0.24.5
+requests>=2.31.0