from langchain_community.vectorstores import FAISS
from langchain_huggingface import HuggingFaceEmbeddings  # ✅ Updated import
from langchain_core.documents import Document

# 1. Load the local embedding model
embedding = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")

# 2. Load text from a .txt file
file_path = "myfile.txt"  # 🔁 Change to your file path

with open(file_path, "r", encoding="utf-8") as f:
    text = f.read()

# Optional: Split into chunks (basic)
documents = [Document(page_content=chunk) for chunk in text.split("\n\n") if chunk.strip()]

# 3. Create the FAISS vector store
vectorstore = FAISS.from_documents(documents, embedding)

# 4. Do a similarity search
query = "Tell me About Om sir"
results = vectorstore.similarity_search(query, k=2)

# 5. Print results
for i, doc in enumerate(results, 1):
    print(f"Result {i}: {doc.page_content}")