from sentence_transformers import SentenceTransformer
import faiss
import os

class KnowledgeIngestor:
    def __init__(self):
        self.model = SentenceTransformer("all-MiniLM-L6-v2")
        self.index = faiss.IndexFlatL2(384)
        self.texts = []

    def ingest_directory(self, dir_path):
        for fname in os.listdir(dir_path):
            if fname.endswith(".txt"):
                with open(os.path.join(dir_path, fname), "r", encoding="utf-8") as f:
                    content = f.read()
                    self.add_text(content)

    def add_text(self, text):
        vec = self.model.encode([text])
        self.index.add(vec)
        self.texts.append(text)

    def search(self, query, top_k=3):
        vec = self.model.encode([query])
        D, I = self.index.search(vec, top_k)
        return [self.texts[i] for i in I[0]]