from sentence_transformers import SentenceTransformer
from langchain.vectorstores import FAISS
from langchain.text_splitter import CharacterTextSplitter
from langchain.document_loaders import TextLoader

# Charger les documents
loader = TextLoader("document.txt")
documents = loader.load()

# Découper les documents en chunks
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
docs = text_splitter.split_documents(documents)

# Générer les embeddings et créer la base vectorielle
model = SentenceTransformer('all-MiniLM-L6-v2')
embeddings = model.encode([doc.page_content for doc in docs])
vector_store = FAISS.from_documents(docs, embeddings)