| """ |
| BƯỚC 4: VECTORSTORE (FAISS in-memory) |
| """ |
|
|
| from langchain_community.vectorstores import FAISS |
| from embeddings import get_embeddings |
|
|
|
|
| def build_vectorstore(chunks): |
| print(">>> Initialising embedding model for FAISS index ...") |
| embeddings = get_embeddings() |
|
|
| print(f">>> Building FAISS index from {len(chunks)} chunks ...") |
| vs = FAISS.from_documents(chunks, embeddings) |
| print(">>> FAISS index built.\n") |
| return vs |
|
|
|
|
| if __name__ == "__main__": |
| from load_documents import load_documents |
| from split_documents import split_documents |
|
|
| docs = load_documents() |
| chunks = split_documents(docs) |
| vs = build_vectorstore(chunks) |
| res = vs.similarity_search( |
| "Fristen für die Prüfungsanmeldung im Bachelorstudium", k=3 |
| ) |
| for r in res: |
| print(r.page_content[:200], r.metadata) |
|
|
