85f674c9cb
- ChromaDB → Qdrant 전환 (맥미니 기존 인스턴스, tk_qc_issues 컬렉션) - Ollama 임베딩/텍스트 생성 URL 분리 (임베딩: 맥미니, 텍스트: GPU서버) - MLX fallback 제거, Ollama 단일 경로로 단순화 - ds923 docker-compose에서 ai-service 제거 - gateway/system3-web nginx: ai-service 프록시를 ai.hyungi.net 경유로 변경 - resolver + 변수 기반 proxy_pass로 런타임 DNS 해석 (컨테이너 시작 실패 방지) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
103 lines
3.3 KiB
Python
103 lines
3.3 KiB
Python
import uuid
|
|
from qdrant_client import QdrantClient
|
|
from qdrant_client.models import Distance, VectorParams, PointStruct, Filter, FieldCondition, MatchValue
|
|
from config import settings
|
|
|
|
|
|
class VectorStore:
|
|
def __init__(self):
|
|
self.client = None
|
|
self.collection = settings.QDRANT_COLLECTION # "tk_qc_issues"
|
|
|
|
def initialize(self):
|
|
self.client = QdrantClient(url=settings.QDRANT_URL)
|
|
self._ensure_collection()
|
|
|
|
def _ensure_collection(self):
|
|
collections = [c.name for c in self.client.get_collections().collections]
|
|
if self.collection not in collections:
|
|
# bge-m3 기본 출력 = 1024 dims
|
|
self.client.create_collection(
|
|
collection_name=self.collection,
|
|
vectors_config=VectorParams(size=1024, distance=Distance.COSINE),
|
|
)
|
|
|
|
@staticmethod
|
|
def _to_uuid(doc_id) -> str:
|
|
"""문자열/정수 ID → UUID5 변환 (Qdrant 호환)"""
|
|
return str(uuid.uuid5(uuid.NAMESPACE_URL, str(doc_id)))
|
|
|
|
def upsert(
|
|
self,
|
|
doc_id: str,
|
|
document: str,
|
|
embedding: list[float],
|
|
metadata: dict = None,
|
|
):
|
|
point_id = self._to_uuid(doc_id)
|
|
payload = {"document": document, "original_id": str(doc_id)}
|
|
if metadata:
|
|
payload.update(metadata)
|
|
self.client.upsert(
|
|
collection_name=self.collection,
|
|
points=[PointStruct(id=point_id, vector=embedding, payload=payload)],
|
|
)
|
|
|
|
def query(
|
|
self,
|
|
embedding: list[float],
|
|
n_results: int = 5,
|
|
where: dict = None,
|
|
) -> list[dict]:
|
|
query_filter = self._build_filter(where) if where else None
|
|
try:
|
|
results = self.client.search(
|
|
collection_name=self.collection,
|
|
query_vector=embedding,
|
|
limit=n_results,
|
|
query_filter=query_filter,
|
|
)
|
|
except Exception:
|
|
return []
|
|
|
|
items = []
|
|
for hit in results:
|
|
payload = hit.payload or {}
|
|
item = {
|
|
"id": payload.get("original_id", str(hit.id)),
|
|
"document": payload.get("document", ""),
|
|
"distance": round(1 - hit.score, 4), # cosine score → distance
|
|
"metadata": {k: v for k, v in payload.items() if k not in ("document", "original_id")},
|
|
"similarity": round(hit.score, 4),
|
|
}
|
|
items.append(item)
|
|
return items
|
|
|
|
@staticmethod
|
|
def _build_filter(where: dict) -> Filter:
|
|
"""ChromaDB 스타일 where 조건 → Qdrant Filter 변환"""
|
|
conditions = []
|
|
for key, value in where.items():
|
|
conditions.append(FieldCondition(key=key, match=MatchValue(value=value)))
|
|
return Filter(must=conditions)
|
|
|
|
def delete(self, doc_id: str):
|
|
point_id = self._to_uuid(doc_id)
|
|
self.client.delete(
|
|
collection_name=self.collection,
|
|
points_selector=[point_id],
|
|
)
|
|
|
|
def count(self) -> int:
|
|
info = self.client.get_collection(collection_name=self.collection)
|
|
return info.points_count
|
|
|
|
def stats(self) -> dict:
|
|
return {
|
|
"total_documents": self.count(),
|
|
"collection_name": self.collection,
|
|
}
|
|
|
|
|
|
vector_store = VectorStore()
|