added db file

app.py

@@ -1,8 +1,16 @@
 import gradio as gr
+import os
 from database.vaccine_coverage_db import VaccineCoverageDB
 from rag.rag_pipeline import RAGPipeline
 from utils.helpers import process_response
 from config import DB_PATH, METADATA_FILE, PDF_DIR
+from initialize_db import initialize_database, populate_database
+
+# Initialize database if it doesn't exist
+if not os.path.exists(DB_PATH):
+    print("Database not found. Initializing...")
+    initialize_database()
+    populate_database()
 
 # Initialize database and RAG pipeline
 db = VaccineCoverageDB(DB_PATH)
@@ -23,7 +31,7 @@ def save_pdf(item_key):
     attachments = db.get_attachments_for_item(item_key)
     if attachments:
         attachment_key = attachments[0]["key"]
-        output_path = f"{attachment_key}.pdf"
+        output_path = os.path.join(PDF_DIR, f"{attachment_key}.pdf")
         if db.save_pdf_to_file(attachment_key, output_path):
             return f"PDF saved successfully to {output_path}"
     return "Failed to save PDF or no attachments found"

config.py

@@ -1,11 +1,20 @@
 import os
 
+# Base directory
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+
 # Database configuration
-DB_PATH = 'vaccine_coverage_study.db'
+DB_NAME = "vaccine_coverage_study.db"
+DB_PATH = os.path.join(BASE_DIR, DB_NAME)
 
 # RAG Pipeline configuration
-METADATA_FILE = os.path.join('data', 'metadata_map.json')
-PDF_DIR = os.path.join('data', 'pdfs')
+DATA_DIR = os.path.join(BASE_DIR, "data")
+METADATA_FILE = os.path.join(DATA_DIR, "metadata_map.json")
+PDF_DIR = os.path.join(DATA_DIR, "pdfs")
+
+# Create directories if they don't exist
+os.makedirs(DATA_DIR, exist_ok=True)
+os.makedirs(PDF_DIR, exist_ok=True)
 
 # OpenAI configuration
-OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")

initialize_db.py

@@ -0,0 +1,91 @@
+import sqlite3
+import json
+import os
+from config import DB_PATH, METADATA_FILE, PDF_DIR
+
+
+def initialize_database():
+    conn = sqlite3.connect(DB_PATH)
+    cursor = conn.cursor()
+
+    # Create tables
+    cursor.execute(
+        """
+    CREATE TABLE IF NOT EXISTS items (
+        key TEXT PRIMARY KEY,
+        title TEXT,
+        abstract TEXT,
+        authors TEXT,
+        year INTEGER,
+        doi TEXT
+    )
+    """
+    )
+
+    cursor.execute(
+        """
+    CREATE TABLE IF NOT EXISTS attachments (
+        key TEXT PRIMARY KEY,
+        parent_key TEXT,
+        content BLOB,
+        FOREIGN KEY (parent_key) REFERENCES items (key)
+    )
+    """
+    )
+
+    conn.commit()
+    conn.close()
+
+
+def populate_database():
+    if not os.path.exists(METADATA_FILE):
+        print(f"Metadata file not found: {METADATA_FILE}")
+        return
+
+    with open(METADATA_FILE, "r") as f:
+        metadata = json.load(f)
+
+    conn = sqlite3.connect(DB_PATH)
+    cursor = conn.cursor()
+
+    for item_key, item_data in metadata.items():
+        metadata = item_data["metadata"]
+        cursor.execute(
+            """
+        INSERT OR REPLACE INTO items (key, title, abstract, authors, year, doi)
+        VALUES (?, ?, ?, ?, ?, ?)
+        """,
+            (
+                item_key,
+                metadata["title"],
+                metadata["abstract"],
+                metadata["authors"],
+                metadata["year"],
+                metadata["doi"],
+            ),
+        )
+
+        pdf_path = item_data.get("pdf_path")
+        if pdf_path:
+            full_pdf_path = os.path.join(PDF_DIR, os.path.basename(pdf_path))
+            if os.path.exists(full_pdf_path):
+                with open(full_pdf_path, "rb") as pdf_file:
+                    pdf_content = pdf_file.read()
+                    cursor.execute(
+                        """
+                    INSERT OR REPLACE INTO attachments (key, parent_key, content)
+                    VALUES (?, ?, ?)
+                    """,
+                        (os.path.basename(pdf_path), item_key, pdf_content),
+                    )
+            else:
+                print(f"PDF file not found: {full_pdf_path}")
+
+    conn.commit()
+    conn.close()
+
+
+if __name__ == "__main__":
+    initialize_database()
+    populate_database()
+    print("Database initialized and populated.")

rag/rag_pipeline.py

@@ -25,6 +25,11 @@ class RAGPipeline:
         self.build_index()
 
     def load_documents(self):
+        if not os.path.exists(self.metadata_file):
+            print(f"Metadata file not found: {self.metadata_file}")
+            self.documents = []
+            return
+
         with open(self.metadata_file, "r") as f:
             self.metadata = json.load(f)