Flash app commit

Files changed (10) hide show

Dockerfile CHANGED Viewed

@@ -1,26 +1,25 @@
-# Dockerfile
-FROM python:3.9-slim
-WORKDIR /app
-# Copy dependencies and install them
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
-# Copy application files
 COPY . .
-# Set environment variables for writable directories
-ENV HF_HOME=/tmp/.cache/huggingface
-# Cache directory for Hugging Face
-ENV TRANSFORMERS_CACHE=/tmp/.cache/transformers
-# Legacy cache for compatibility
-ENV BASE_PATH=/tmp/vector_db
- # Base path for vector database and metadata
-# Set environment variable for Hugging Face authentication token
-# The `hkey` secret from Hugging Face Spaces will automatically populate this
-ENV hkey=${hkey}
-CMD ["python", "app.py"]

+# Base image with GPU support for Hugging Face Spaces
+FROM nvidia/cuda:11.8.0-base-ubuntu20.04
+# Set environment variables
+ENV DEBIAN_FRONTEND=noninteractive
+# Install Python and dependencies
+RUN apt-get update && apt-get install -y \
+    python3 python3-pip git wget unzip && \
+    rm -rf /var/lib/apt/lists/*
+# Set the working directory
+WORKDIR /app
+# Copy the application files
 COPY . .
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+# Expose the default port used by Spaces
+EXPOSE 7860
+# Start the Flask app
+CMD ["python3", "run.py"]

app/__init__.py ADDED Viewed

+from flask import Flask
+def create_app():
+    v_app = Flask(__name__)
+    v_app.config['UPLOAD_FOLDER'] = 'app/uploads/'
+    v_app.config['ALLOWED_EXTENSIONS'] = {'zip'}
+    with v_app.app_context():
+        from .routes import v_bp
+        v_app.register_blueprint(v_bp)
+    return v_app

app/routes.py ADDED Viewed

+import os
+from flask import Blueprint, render_template, request, send_file, jsonify
+from .utils.zip_handler import handle_zip_upload
+from .utils.vector_db import process_files_to_vectors
+v_bp = Blueprint('routes', __name__)
+@v_bp.route('/', methods=['GET', 'POST'])
+def home():
+    if request.method == 'POST':
+        v_uploaded_file = request.files.get('file')
+        if v_uploaded_file and v_uploaded_file.filename.endswith('.zip'):
+            v_upload_path = os.path.join('app/uploads', v_uploaded_file.filename)
+            v_uploaded_file.save(v_upload_path)
+            # Process the zip file
+            v_output_path = handle_zip_upload(v_upload_path)
+            # Create or update vector database
+            v_result_path = process_files_to_vectors(v_output_path)
+            # Compress and send the result
+            result_zip = os.path.join('app/uploads/vectors/vector_db.zip')
+            os.system(f'zip -r {result_zip} {v_result_path}')
+            return send_file(result_zip, as_attachment=True)
+        return jsonify({'error': 'Please upload a valid zip file.'})
+    return render_template('index.html')

app/static/logo.png ADDED Viewed

app/templates/index.html ADDED Viewed

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Vector DB Creator</title>
+</head>
+<body>
+    <header>
+        <img src="{{ url_for('static', filename='logo.png') }}" alt="Logo" style="float:left; width:50px;">
+        <h1>Change your PDF, PPT, and CSV data to Vector DB</h1>
+    </header>
+    <main>
+        <p>Upload your data files or an existing vector database to create or update a vector DB.</p>
+        <form action="/" method="POST" enctype="multipart/form-data">
+            <label for="file">Upload ZIP File:</label>
+            <input type="file" name="file" id="file" accept=".zip" required>
+            <button type="submit">Upload</button>
+        </form>
+        <p>Your vector DB will be available for download after processing.</p>
+    </main>
+</body>
+</html>

app/utils/file_handler.py ADDED Viewed

File without changes

app/utils/vector_db.py ADDED Viewed

+import os
+def process_files_to_vectors(v_folder_path):
+    # Logic to create or update the vector DB
+    v_vector_folder = os.path.join(v_folder_path, 'vectors')
+    os.makedirs(v_vector_folder, exist_ok=True)
+    # Placeholder: Iterate over files and create vector representations
+    for v_root, _, v_files in os.walk(v_folder_path):
+        for v_file in v_files:
+            v_file_path = os.path.join(v_root, v_file)
+            if v_file.endswith(('.pdf', '.ppt', '.csv')):
+                # Process the files here (convert to vectors)
+                v_vector_file = os.path.join(v_vector_folder, v_file + '.vec')
+                with open(v_vector_file, 'w') as obj_out:
+                    obj_out.write(f'Vector representation of {v_file}')
+    return v_vector_folder

app/utils/zip_handler.py ADDED Viewed

+import os
+import zipfile
+def handle_zip_upload(v_zip_path):
+    v_extract_path = os.path.splitext(v_zip_path)[0]
+    with zipfile.ZipFile(v_zip_path, 'r') as obj_zip:
+        obj_zip.extractall(v_extract_path)
+    return v_extract_path

requirements.txt CHANGED Viewed

@@ -1,6 +1,9 @@
-faiss-cpu
-huggingface-hub
-sentence-transformers
-numpy
-pandas
-flask

+Flask==2.3.2
+transformers==4.27.4
+sentence-transformers==2.2.2
+torch==2.0.1
+torchvision==0.15.2
+numpy==1.24.2
+PyMuPDF==1.22.5
+python-pptx==0.6.21
+pandas==1.5.3

run.py ADDED Viewed

+from app import create_app
+if __name__ == "__main__":
+    obj_app = create_app()
+    obj_app.run(host='0.0.0.0', port=7860, debug=True)