Create rag.py

rag.py

@@ -0,0 +1,48 @@
+import pandas as pd
+# from langchain.schema import Document
+from langchain_core.documents import Document
+# from langchain.embeddings import HuggingFaceEmbeddings
+from langchain_huggingface import HuggingFaceEmbeddings
+# from langchain.vectorstores import FAISS
+from langchain_community.vectorstores import FAISS
+
+
+def load_student_documents(csv_path: str):
+    df = pd.read_csv(csv_path)
+    documents = []
+    for _, row in df.iterrows():
+        content = (
+    f"Student record. "
+    f"Register number {row['Register Number']}. "
+    f"Name {row['Name']}. "
+    f"Email {row['EmailID']}. "
+    f"Department {row['Department']}. "
+    f"Year {row['Year of Study']}. "
+    f"Hobby {row['Hobby']}. "
+    f"Study level {row['Study Level']}. "
+    f"Sleeptime {row['Sleeptime']}."
+)
+
+        documents.append(
+            Document(
+                page_content=content.strip(),
+                metadata={"register_number": row["Register Number"]}
+            )
+        )
+    return documents
+
+def create_vectorstore(documents):
+    embeddings = HuggingFaceEmbeddings(
+        model_name="sentence-transformers/all-MiniLM-L6-v2"
+    )
+    vectorstore = FAISS.from_documents(
+        documents=documents,
+        embedding=embeddings
+    )
+    return vectorstore
+
+def get_retriever(vectorstore):
+    return vectorstore.as_retriever(
+    search_type="mmr",
+    search_kwargs={"k": 6, "lambda_mult": 0.7}
+)