Update db.py

db.py

@@ -1,27 +1,28 @@
-# ingest.py
-from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.vectorstores import FAISS
-from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-
-DATA_PATH = "data/"
-DB_FAISS_PATH = "vectorstore/db_faiss"
-
-def create_vector_db():
-    loader = DirectoryLoader(
-        DATA_PATH, glob="*.pdf", loader_cls=PyPDFLoader
-    )
-
-    documents = loader.load()
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-    texts = text_splitter.split_documents(documents)
-
-    embeddings = HuggingFaceEmbeddings(
-        model_name="sentence-transformers/all-MiniLM-L6-v2", model_kwargs={"device": "cpu"}
-    )
-
-    db = FAISS.from_documents(texts, embeddings)
-    db.save_local(DB_FAISS_PATH)
-
-if __name__ == "__main__":
-    create_vector_db()
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from dotenv import load_dotenv
+import os
+import logging
+
+
+load_dotenv()
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+def load_embeddings():
+    return HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2", model_kwargs={"device": "cpu"})
+
+def load_vector_database(embeddings):
+    try:
+        db = FAISS.load_local("vectorstore/db_faiss", embeddings, allow_dangerous_deserialization=True)
+        logger.info("Vector database loaded successfully!")
+        return db
+    except Exception as e:
+        logger.error(f"Failed to load vector database: {e}")
+        raise e
+
+embeddings = load_embeddings()
+vector_db = load_vector_database(embeddings)