windpacer/ExperionCrawler
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: LLM 모델명 외부 설정 + 포인트 추가 기능

Browse Source 
- mcp-server: 하드코딩된 모델명을 llm-model.json 기반 config.py로 외부화
- C#: AppendPointsAsync로 기존 데이터 유지하면서 포인트 추가
- C#: LlmConfigController로 LLM 모델명 조회/저장 API
- Frontend: LLM 설정 UI 카드 + 포인트 빌더에서 추가하기 버튼
This commit is contained in:
windpacer
2026-05-11 17:55:18 +09:00
parent de728f013a
commit 5cacc5dbb5
15 changed files with 544 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
mcp-server/worker/nl2sql_worker.py
View File

@@ -34,7 +34,8 @@ DB_CONNECTION_STRING = os.environ.get("DB_CONNECTION_STRING", "postgresql://post
DB_TIMEOUT = int(os.environ.get("DB_TIMEOUT", "10"))
VLLM_BASE_URL = os.environ.get("VLLM_BASE_URL", "http://localhost:8000/v1")
VLLM_MODEL = os.environ.get("VLLM_MODEL", "Qwen3.6-27B-FP8")
from config import get_vllm_model
VLLM_MODEL = get_vllm_model()
logging.basicConfig(
level=logging.INFO,
@@ -150,7 +151,7 @@ async def _generate_sql(natural_language: str) -> str:
)
response = await client.chat.completions.create(
model="Qwen3.6-27B-FP8",
model=VLLM_MODEL,
messages=[
{"role": "system", "content": system},
{"role": "user", "content": natural_language},

7
mcp-server/worker/pid_extract_template.py
View File

@@ -10,7 +10,7 @@
환경 변수:
VLLM_BASE_URL: vLLM 엔드포인트 (기본: http://localhost:8000/v1)
VLLM_MODEL: 모델명 (기본: Qwen3.6-27B-FP8)
VLLM_MODEL: 모델명 (기본: llm-model.json 참조)
"""
import argparse
@@ -22,6 +22,9 @@ import sys
import time
from typing import List
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from config import get_vllm_model
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s [%(name)s] %(levelname)s %(message)s",
@@ -84,7 +87,7 @@ def call_llm(system_prompt: str, user_text: str, max_tokens: int = 65536) -> Lis
from openai import OpenAI
base_url = os.environ.get("VLLM_BASE_URL", "http://localhost:8000/v1")
model = os.environ.get("VLLM_MODEL", "Qwen3.6-27B-FP8")
model = os.environ.get("VLLM_MODEL") or get_vllm_model()
client = OpenAI(base_url=base_url, api_key="dummy")

11
mcp-server/worker/pid_worker.py
View File

@@ -30,7 +30,8 @@ import uvicorn
# ── 설정 ─────────────────────────────────────────────────────────────────────
VLLM_BASE_URL = os.environ.get("VLLM_BASE_URL", "http://localhost:8000/v1")
VLLM_MODEL = os.environ.get("VLLM_MODEL", "Qwen3.6-27B-FP8")
from config import get_vllm_model
VLLM_MODEL = get_vllm_model()
DB_CONNECTION_STRING = os.environ.get("DB_CONNECTION_STRING", "postgresql://postgres:postgres@localhost:5432/iiot_platform")
DB_TIMEOUT = int(os.environ.get("DB_TIMEOUT", "10"))
@@ -173,7 +174,7 @@ def _extract_pid_tags(text: str, source_type: str) -> str:
)
truncated = text[:100000]
resp = _llm().chat.completions.create(
model="Qwen3.6-27B-FP8",
model=VLLM_MODEL,
messages=[
{"role": "system", "content": system},
{"role": "user", "content": f"Source: {source_type}\n\nText:\n{truncated}"},
@@ -202,7 +203,7 @@ def _match_pid_tags(pid_tags: list, experion_tags: list) -> str:
"- Output ONLY the JSON array.\n"
)
resp = _llm().chat.completions.create(
model="Qwen3.6-27B-FP8",
model=VLLM_MODEL,
messages=[
{"role": "system", "content": system},
{"role": "user", "content": (
@@ -247,7 +248,7 @@ def _parse_pid_dxf(filepath: str) -> str:
ensure_ascii=False, indent=2)
resp = _llm().chat.completions.create(
model="Qwen3.6-27B-FP8",
model=VLLM_MODEL,
messages=[
{"role": "system", "content": _TAG_EXTRACT_SYSTEM},
{"role": "user", "content": f"Source: dxf\n\nText:\n{text[:8000]}"},
@@ -273,7 +274,7 @@ def _parse_pid_pdf(filepath: str, use_ocr: bool = True) -> str:
ensure_ascii=False, indent=2)
resp = _llm().chat.completions.create(
model="Qwen3.6-27B-FP8",
model=VLLM_MODEL,
messages=[
{"role": "system", "content": _TAG_EXTRACT_SYSTEM},
{"role": "user", "content": f"Source: pdf\n\nText:\n{text[:12000]}"},

11
mcp-server/worker/pid_worker_test.py
View File

@@ -31,7 +31,8 @@ import uvicorn
# ── 설정 ─────────────────────────────────────────────────────────────────────
VLLM_BASE_URL = os.environ.get("VLLM_BASE_URL", "http://localhost:8000/v1")
VLLM_MODEL = os.environ.get("VLLM_MODEL", "Qwen3.6-27B-FP8")
from config import get_vllm_model
VLLM_MODEL = get_vllm_model()
DB_CONNECTION_STRING = os.environ.get("DB_CONNECTION_STRING", "postgresql://postgres:postgres@localhost:5432/iiot_platform")
DB_TIMEOUT = int(os.environ.get("DB_TIMEOUT", "10"))
@@ -174,7 +175,7 @@ def _extract_pid_tags(text: str, source_type: str) -> str:
)
truncated = text[:100000]
resp = _llm().chat.completions.create(
model="Qwen3.6-27B-FP8",
model=VLLM_MODEL,
messages=[
{"role": "system", "content": system},
{"role": "user", "content": f"Source: {source_type}\n\nText:\n{truncated}"},
@@ -203,7 +204,7 @@ def _match_pid_tags(pid_tags: list, experion_tags: list) -> str:
"- Output ONLY the JSON array.\n"
)
resp = _llm().chat.completions.create(
model="Qwen3.6-27B-FP8",
model=VLLM_MODEL,
messages=[
{"role": "system", "content": system},
{"role": "user", "content": (
@@ -248,7 +249,7 @@ def _parse_pid_dxf(filepath: str) -> str:
ensure_ascii=False, indent=2)
resp = _llm().chat.completions.create(
model="Qwen3.6-27B-FP8",
model=VLLM_MODEL,
messages=[
{"role": "system", "content": _TAG_EXTRACT_SYSTEM},
{"role": "user", "content": f"Source: dxf\n\nText:\n{text[:8000]}"},
@@ -274,7 +275,7 @@ def _parse_pid_pdf(filepath: str, use_ocr: bool = True) -> str:
ensure_ascii=False, indent=2)
resp = _llm().chat.completions.create(
model="Qwen3.6-27B-FP8",
model=VLLM_MODEL,
messages=[
{"role": "system", "content": _TAG_EXTRACT_SYSTEM},
{"role": "user", "content": f"Source: pdf\n\nText:\n{text[:12000]}"},

5
mcp-server/worker/rag_worker.py
View File

@@ -32,7 +32,8 @@ import httpx
OLLAMA_URL = os.environ.get("OLLAMA_URL", "http://localhost:11434")
QDRANT_URL = os.environ.get("QDRANT_URL", "http://localhost:6333")
VLLM_BASE_URL = os.environ.get("VLLM_BASE_URL", "http://localhost:8000/v1")
VLLM_MODEL = os.environ.get("VLLM_MODEL", "Qwen3.6-27B-FP8")
from config import get_vllm_model
VLLM_MODEL = get_vllm_model()
EMBED_MODEL = os.environ.get("EMBED_MODEL", "nomic-embed-text")
COL_CODEBASE = os.environ.get("COL_CODEBASE", "ws-65f457145aee80b2")
@@ -105,7 +106,7 @@ async def _ask_llm(question: str, context: str = "") -> str:
prompt = question
response = await client.chat.completions.create(
model="Qwen3.6-27B-FP8",
model=VLLM_MODEL,
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt},