Upload 3 files

Dockerfile

@@ -0,0 +1,18 @@
+FROM python:3.10
+
+WORKDIR interExblorer/code
+
+COPY ./requirements.txt interExblorer/code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r interExblorer/code/requirements.txt
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY . .
+
+CMD ["python", "app.py", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,74 @@
+# app.py
+from flask import Flask, render_template, request
+import subprocess
+import json
+import os
+import sys
+from sentence_transformers import SentenceTransformer
+from pinecone import Pinecone
+
+app = Flask(__name__)
+
+PINECONE_API_KEY = os.environ.get('PINECONE_API_KEY')
+PINECONE_SPACE_NAME = os.environ.get('PINECONE_SPACE_NAME')
+
+model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
+
+# Initialize Pinecone client
+pc = Pinecone(api_key=PINECONE_API_KEY, environment='gcp-starter')
+indexE = pc.Index(PINECONE_SPACE_NAME)
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+@app.route('/search', methods=['POST'])
+def search():
+    if request.method == 'POST':
+        query = request.form['query']
+        youtube_links = []
+
+        try:
+            # Encode the user-provided input
+            query_vector = model.encode(query)
+
+            # Convert the query vector to a list
+            query_vector_list = query_vector.tolist()
+
+            # Query Pinecone with the vector using the 'Index' object
+            results = indexE.query(
+                namespace='',
+                top_k=3,
+                include_values=True,
+                include_metadata=True,
+                vector=query_vector_list,
+            )
+
+            if results and 'matches' in results and results['matches']:
+                # Access metadata from each match
+                for match in results['matches']:
+                    metadata = match.get('metadata', {})
+                    video_id = metadata.get('video_id')
+                    start_time = metadata.get('start_time')
+                    time = int(start_time)
+
+                    # Create a clickable YouTube link
+                    youtube_link = f'https://www.youtube.com/watch?v={video_id}&t={time}s'
+                    youtube_links.append(youtube_link)
+
+        except Exception as e:
+            # Handle exceptions gracefully
+            error_message = str(e)
+            output = {'error': error_message}
+            print(json.dumps(output))
+
+        else:
+            # No exceptions, render the template with results
+            if youtube_links:
+                return render_template('results.html', query=query, youtube_links=youtube_links)
+            else:
+                no_results_message = "No results found."
+                return render_template('results.html', query=query, no_results_message=no_results_message)
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=7860)

requirements.txt

@@ -0,0 +1,4 @@
+Flask==3.0.1
+sentence-transformers==2.2.2
+pinecone-client==3.0.0
+Gunicorn