Update rag.py

rag.py

@@ -0,0 +1,41 @@
+from langchain_community.document_loaders import PyPDFLoader, TextLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import FAISS
+from langchain_community.embeddings import HuggingFaceEmbeddings
+
+
+def create_vectorstore(file_path):
+
+    # ----------------------------
+    # Load Document
+    # ----------------------------
+    if file_path.endswith(".pdf"):
+        loader = PyPDFLoader(file_path)
+    else:
+        loader = TextLoader(file_path, encoding="utf-8")
+
+    documents = loader.load()
+
+    # ----------------------------
+    # Split Documents into Chunks
+    # ----------------------------
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=200
+    )
+
+    docs = text_splitter.split_documents(documents)
+
+    # ----------------------------
+    # Create Embeddings
+    # ----------------------------
+    embeddings = HuggingFaceEmbeddings(
+        model_name="sentence-transformers/all-MiniLM-L6-v2"
+    )
+
+    # ----------------------------
+    # Create FAISS Vector Store
+    # ----------------------------
+    vectorstore = FAISS.from_documents(docs, embeddings)
+
+    return vectorstore