diff --git a/16-Evaluations/data/Newwhitepaper_Agents2.pdf b/16-Evaluations/data/Newwhitepaper_Agents2.pdf
new file mode 100644
index 000000000..6c74cdd80
Binary files /dev/null and b/16-Evaluations/data/Newwhitepaper_Agents2.pdf differ
diff --git a/16-Evaluations/myrag.py b/16-Evaluations/myrag.py
new file mode 100644
index 000000000..73dc9ce27
--- /dev/null
+++ b/16-Evaluations/myrag.py
@@ -0,0 +1,71 @@
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders import PyMuPDFLoader
+from langchain_community.vectorstores import FAISS
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.prompts import PromptTemplate
+from langchain_openai import OpenAIEmbeddings
+from langchain_core.runnables import RunnablePassthrough
+
+
+class PDFRAG:
+    def __init__(self, file_path: str, llm):
+        self.file_path = file_path
+        self.llm = llm
+
+    def load_documents(self):
+        # 문서 로드(Load Documents)
+        loader = PyMuPDFLoader(self.file_path)
+        docs = loader.load()
+        return docs
+
+    def split_documents(self, docs):
+        # 문서 분할(Split Documents)
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=300, chunk_overlap=50)
+        split_documents = text_splitter.split_documents(docs)
+        return split_documents
+
+    def create_vectorstore(self, split_documents):
+        # 임베딩(Embedding) 생성
+        embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
+
+        # DB 생성(Create DB) 및 저장
+        vectorstore = FAISS.from_documents(
+            documents=split_documents, embedding=embeddings
+        )
+        return vectorstore
+
+    def create_retriever(self):
+        vectorstore = self.create_vectorstore(
+            self.split_documents(self.load_documents())
+        )
+        # 검색기(Retriever) 생성
+        retriever = vectorstore.as_retriever()
+        return retriever
+
+    def create_chain(self, retriever):
+        # 프롬프트 생성(Create Prompt)
+        prompt = PromptTemplate.from_template(
+            """You are an assistant for question-answering tasks. 
+        Use the following pieces of retrieved context to answer the question. 
+        If you don't know the answer, just say that you don't know. 
+
+        #Context: 
+        {context}
+
+        #Question:
+        {question}
+
+        #Answer:"""
+        )
+
+        # 체인(Chain) 생성
+        chain = (
+            {
+                "context": retriever,
+                "question": RunnablePassthrough(),
+            }
+            | prompt
+            | self.llm
+            | StrOutputParser()
+        )
+        return chain