Python과 LLM 임베딩을 활용한 컨텍스트 인식 검색 엔진 구축

model = SentenceTransformer("all-MiniLM-L6-v2")
texts = [t["text"] for t in tickets]
embeddings = model.encode(texts, normalize_embeddings=True, show_progress_bar=True)

class ContextAwareIndex:
    def __init__(self, embeddings: np.ndarray, documents: list):
        self.embeddings = embeddings
        self.documents = documents
    def search(self, query: str, top_k: int = 5, team: str = None, status: str = None, priority: str = None, after: "date" = None, before: "date" = None, min_score: float = 0.0):
        q_vec = model.encode([query], normalize_embeddings=True)[0]
        mask = np.ones(len(self.documents), dtype=bool)
        # ... (filtering logic) ...
        candidate_idx = np.where(mask)[0]
        scores = self.embeddings[candidate_idx] @ q_vec
        # ... (ranking logic) ...

np.save("ticket_embeddings.npy", embeddings)
with open("ticket_metadata.json", "w") as f:
    json.dump([{**t, "created": t["created"].isoformat()} for t in tickets], f, indent=2)