[阶段2] FAM-Edge 重构为整视频分析+同步接口+人物服务 - 移除切片/抽帧/队列，新增 oracle_db/person_service/qa/watch_processor/video_processor，api_gateway 提供 /api/oracle/sync 与 /api/oracle/people/correct
This commit is contained in:
ericwyuan
@@ -1,517 +1,103 @@
|
||||
"""
|
||||
API-Gateway - Flask 蓝图，接收任务
|
||||
API-Gateway - Flask 蓝图（新架构 v2）
|
||||
|
||||
模式:
|
||||
1. enqueue (异步): NAS 上传视频 → Edge 入队 → 立即返回 → 消费者异步处理 → NAS 轮询拉取结果
|
||||
2. push (同步, 兼容保留): NAS 上传 → Edge 同步处理 → 结果随响应返回
|
||||
3. analyze (旧拉取模式, 兼容保留)
|
||||
端点:
|
||||
GET /api/oracle/sync NAS 每 30 分钟拉取增量（since + token 校验）
|
||||
POST /api/oracle/people/correct NAS 推送手动命名校正（label -> canonical_name）
|
||||
POST /api/edge/chat/ask 智能问答编排（Gemini -> NVIDIA -> Ollama）
|
||||
GET /health 健康检查
|
||||
|
||||
已移除（旧推送/分块/队列模式）: /video/push, /enqueue, /chunk, /assemble,
|
||||
/results, /queue/stats, /mark_frames
|
||||
"""
|
||||
import os
|
||||
import base64
|
||||
import threading
|
||||
import requests
|
||||
|
||||
from flask import Blueprint, request, jsonify
|
||||
|
||||
from ..logger import setup_logger
|
||||
from ..ai_orchestrator.orchestrator import AIOrchestrator
|
||||
from ..video_preprocessor.preprocessor import VideoPreprocessor
|
||||
from ..queue import queue_manager
|
||||
from .. import state
|
||||
from ..qa import QAOrchestrator
|
||||
|
||||
logger = setup_logger('fam-edge.api_gateway')
|
||||
|
||||
api_bp = Blueprint('api_gateway', __name__)
|
||||
|
||||
_current_task_lock = threading.Lock()
|
||||
_currently_processing = False
|
||||
|
||||
_orchestrator = None
|
||||
_qa = None
|
||||
|
||||
|
||||
def get_orchestrator():
|
||||
global _orchestrator
|
||||
if _orchestrator is None:
|
||||
_orchestrator = AIOrchestrator()
|
||||
return _orchestrator
|
||||
def get_qa():
|
||||
global _qa
|
||||
if _qa is None:
|
||||
_qa = QAOrchestrator()
|
||||
return _qa
|
||||
|
||||
|
||||
@api_bp.route('/api/edge/video/analyze', methods=['POST'])
|
||||
def receive_task():
|
||||
"""接收分析任务"""
|
||||
global _currently_processing
|
||||
def _check_token() -> bool:
|
||||
expected = _sync_token()
|
||||
token = request.args.get('token') or request.form.get('token') or \
|
||||
(request.get_json(silent=True) or {}).get('token', '')
|
||||
return bool(expected) and token == expected
|
||||
|
||||
|
||||
_SYNC_TOK = None
|
||||
|
||||
|
||||
def _sync_token():
|
||||
global _SYNC_TOK
|
||||
if _SYNC_TOK is None:
|
||||
from ..config_loader import load_config
|
||||
_SYNC_TOK = load_config().get('sync_api', {}).get('token', '${ORACLE_SYNC_TOKEN}')
|
||||
if _SYNC_TOK.startswith('${') and _SYNC_TOK.endswith('}'):
|
||||
_SYNC_TOK = os.environ.get(_SYNC_TOK[2:-1], '')
|
||||
return _SYNC_TOK or ''
|
||||
|
||||
|
||||
@api_bp.route('/api/oracle/sync', methods=['GET'])
|
||||
def sync_pull():
|
||||
"""NAS 拉取增量数据。since=ISO 时间字符串（默认 '' 拉全量）。
|
||||
|
||||
返回: {videos:[...], events:[...], people:[...], server_time}
|
||||
"""
|
||||
if not _check_token():
|
||||
return jsonify({"error": "unauthorized"}), 401
|
||||
since = request.args.get('since', '')
|
||||
try:
|
||||
delta = state.get_db().get_sync_delta(since)
|
||||
except Exception as e:
|
||||
logger.error(f"sync_pull 异常: {e}")
|
||||
return jsonify({"error": str(e)}), 500
|
||||
return jsonify(delta), 200
|
||||
|
||||
|
||||
@api_bp.route('/api/oracle/people/correct', methods=['POST'])
|
||||
def people_correct():
|
||||
"""NAS 手动命名校正推送。
|
||||
|
||||
请求: {"label": "人物A", "canonical_name": "张三", "token": "..."}
|
||||
更新 people 表（manual 优先，不被 LLM 覆盖），立即重算 known_members_context。
|
||||
"""
|
||||
if not _check_token():
|
||||
return jsonify({"error": "unauthorized"}), 401
|
||||
data = request.get_json(silent=True)
|
||||
if not data:
|
||||
return jsonify({"error": "Invalid JSON"}), 400
|
||||
|
||||
task_id = data.get('task_id')
|
||||
video_url = data.get('video_url')
|
||||
webhook_url = data.get('webhook_url')
|
||||
|
||||
if not task_id or not video_url or not webhook_url:
|
||||
return jsonify({"error": "缺少必填字段: task_id, video_url, webhook_url"}), 400
|
||||
|
||||
logger.info(f"[task_id={task_id}] 收到任务: {video_url}")
|
||||
|
||||
# 并发控制
|
||||
with _current_task_lock:
|
||||
if _currently_processing:
|
||||
logger.warning(f"[task_id={task_id}] 队列已满 (当前有任务处理中)，返回 429")
|
||||
return jsonify({"error": "Queue full", "retry_after": 60}), 429
|
||||
_currently_processing = True
|
||||
|
||||
# 异步处理
|
||||
def _process():
|
||||
global _currently_processing
|
||||
try:
|
||||
orch = get_orchestrator()
|
||||
orch.process_task(data)
|
||||
except Exception as e:
|
||||
logger.error(f"[task_id={task_id}] 处理异常: {e}", exc_info=True)
|
||||
finally:
|
||||
with _current_task_lock:
|
||||
_currently_processing = False
|
||||
|
||||
thread = threading.Thread(target=_process, daemon=True, name=f'task-{task_id}')
|
||||
thread.start()
|
||||
|
||||
return jsonify({"status": "accepted", "task_id": task_id}), 202
|
||||
|
||||
|
||||
@api_bp.route('/api/edge/video/enqueue', methods=['POST'])
|
||||
def enqueue_task():
|
||||
"""异步模式：接收 multipart 视频上传，入队后立即返回
|
||||
|
||||
NAS 上传视频 → Edge 保存到磁盘 + 入 SQLite 队列 → 返回 task_id
|
||||
消费者线程异步处理，NAS 通过 /api/edge/results 拉取结果
|
||||
"""
|
||||
task_id_raw = request.form.get('task_id')
|
||||
file = request.files.get('video')
|
||||
if not task_id_raw or not file:
|
||||
return jsonify({"error": "缺少必填字段: task_id, video"}), 400
|
||||
|
||||
label = (data.get('label') or '').strip()
|
||||
canonical = (data.get('canonical_name') or '').strip()
|
||||
if not label or not canonical:
|
||||
return jsonify({"error": "缺少 label / canonical_name"}), 400
|
||||
try:
|
||||
task_id = int(task_id_raw)
|
||||
except ValueError:
|
||||
return jsonify({"error": "task_id 必须是整数"}), 400
|
||||
|
||||
camera_name = request.form.get('camera_name', '')
|
||||
event_start_time = request.form.get('event_start_time', '')
|
||||
known_members_context = request.form.get('known_members_context', '')
|
||||
|
||||
upload_dir = os.environ.get('FAM_UPLOAD_DIR', '/tmp/fam_uploads')
|
||||
os.makedirs(upload_dir, exist_ok=True)
|
||||
video_filename = f"task_{task_id}_{file.filename}"
|
||||
video_path = os.path.join(upload_dir, video_filename)
|
||||
|
||||
try:
|
||||
file.save(video_path)
|
||||
size_mb = os.path.getsize(video_path) / 1024 / 1024
|
||||
logger.info(f"[task_id={task_id}] 入队: {file.filename} ({size_mb:.1f}MB)")
|
||||
|
||||
queue_id = queue_manager.enqueue(
|
||||
nas_task_id=task_id,
|
||||
video_filename=file.filename,
|
||||
video_path=video_path,
|
||||
camera_name=camera_name,
|
||||
event_start_time=event_start_time,
|
||||
known_members_context=known_members_context,
|
||||
)
|
||||
|
||||
return jsonify({
|
||||
"status": "queued",
|
||||
"task_id": task_id,
|
||||
"queue_id": queue_id,
|
||||
}), 202
|
||||
|
||||
state.get_db().set_canonical(label, canonical, source='manual')
|
||||
except Exception as e:
|
||||
logger.error(f"[task_id={task_id}] 入队失败: {e}", exc_info=True)
|
||||
if os.path.exists(video_path):
|
||||
os.remove(video_path)
|
||||
logger.error(f"people_correct 异常: {e}")
|
||||
return jsonify({"error": str(e)}), 500
|
||||
|
||||
|
||||
# ========== 分块上传（断点续传）==========
|
||||
|
||||
CHUNK_SIZE = 20 * 1024 * 1024 # 20MB per chunk
|
||||
|
||||
|
||||
def _chunk_dir(task_id: int) -> str:
|
||||
upload_dir = os.environ.get('FAM_UPLOAD_DIR', '/tmp/fam_uploads')
|
||||
d = os.path.join(upload_dir, f"task_{task_id}")
|
||||
os.makedirs(d, exist_ok=True)
|
||||
return d
|
||||
|
||||
|
||||
@api_bp.route('/api/edge/video/chunk', methods=['POST'])
|
||||
def upload_chunk():
|
||||
"""接收单个分块，保存到 task_{id}/chunk_{index:04d}
|
||||
|
||||
断点续传：同一 task_id + chunk_index 重复上传会覆盖，
|
||||
NAS 端可通过 /chunks 查询已上传分块，跳过已有的。
|
||||
"""
|
||||
task_id_raw = request.form.get('task_id')
|
||||
chunk_index_raw = request.form.get('chunk_index')
|
||||
total_chunks_raw = request.form.get('total_chunks')
|
||||
filename = request.form.get('filename', 'video.mp4')
|
||||
chunk_file = request.files.get('chunk')
|
||||
|
||||
if not task_id_raw or not chunk_index_raw or not chunk_file:
|
||||
return jsonify({"error": "缺少必填字段: task_id, chunk_index, chunk"}), 400
|
||||
|
||||
try:
|
||||
task_id = int(task_id_raw)
|
||||
chunk_index = int(chunk_index_raw)
|
||||
total_chunks = int(total_chunks_raw) if total_chunks_raw else 0
|
||||
except ValueError:
|
||||
return jsonify({"error": "task_id/chunk_index 必须是整数"}), 400
|
||||
|
||||
d = _chunk_dir(task_id)
|
||||
chunk_path = os.path.join(d, f"chunk_{chunk_index:04d}")
|
||||
|
||||
try:
|
||||
# 检查 total_chunks 是否变化（chunk_size 变更导致），自动清理旧分块并更新元数据
|
||||
import json
|
||||
meta_path = os.path.join(d, "meta.json")
|
||||
if total_chunks and os.path.exists(meta_path):
|
||||
try:
|
||||
with open(meta_path) as mf:
|
||||
old_meta = json.load(mf)
|
||||
if old_meta.get('total_chunks') and old_meta['total_chunks'] != total_chunks:
|
||||
logger.warning(f"[task_id={task_id}] total_chunks 变更 "
|
||||
f"({old_meta['total_chunks']}→{total_chunks})，清理旧分块")
|
||||
for fn in os.listdir(d):
|
||||
if fn.startswith('chunk_'):
|
||||
os.remove(os.path.join(d, fn))
|
||||
with open(meta_path, 'w') as f:
|
||||
json.dump({"filename": filename, "total_chunks": total_chunks}, f)
|
||||
except (json.JSONDecodeError, IOError):
|
||||
pass
|
||||
|
||||
chunk_file.save(chunk_path)
|
||||
size_kb = os.path.getsize(chunk_path) / 1024
|
||||
|
||||
# 写元数据（首次上传时）
|
||||
if not os.path.exists(meta_path):
|
||||
meta = {"filename": filename, "total_chunks": total_chunks}
|
||||
with open(meta_path, 'w') as f:
|
||||
json.dump(meta, f)
|
||||
|
||||
# 统计已上传分块
|
||||
uploaded = sorted([
|
||||
int(fn.split('_')[1]) for fn in os.listdir(d)
|
||||
if fn.startswith('chunk_') and len(fn.split('_')) == 2
|
||||
])
|
||||
|
||||
logger.info(f"[task_id={task_id}] 分块 {chunk_index}/{total_chunks} 上传成功 "
|
||||
f"({size_kb:.0f}KB, 已上传 {len(uploaded)}/{total_chunks})")
|
||||
|
||||
return jsonify({
|
||||
"status": "ok",
|
||||
"task_id": task_id,
|
||||
"chunk_index": chunk_index,
|
||||
"uploaded_count": len(uploaded),
|
||||
"total_chunks": total_chunks,
|
||||
}), 200
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[task_id={task_id}] 分块上传失败: {e}", exc_info=True)
|
||||
return jsonify({"error": str(e)}), 500
|
||||
|
||||
|
||||
@api_bp.route('/api/edge/video/chunks', methods=['GET'])
|
||||
def query_chunks():
|
||||
"""查询已上传分块列表（断点续传：NAS 重启后查询跳过已有分块）"""
|
||||
task_id_raw = request.args.get('task_id')
|
||||
if not task_id_raw:
|
||||
return jsonify({"error": "缺少 task_id"}), 400
|
||||
|
||||
try:
|
||||
task_id = int(task_id_raw)
|
||||
except ValueError:
|
||||
return jsonify({"error": "task_id 必须是整数"}), 400
|
||||
|
||||
d = _chunk_dir(task_id)
|
||||
uploaded = sorted([
|
||||
int(fn.split('_')[1]) for fn in os.listdir(d)
|
||||
if fn.startswith('chunk_') and len(fn.split('_')) == 2
|
||||
]) if os.path.isdir(d) else []
|
||||
|
||||
total = 0
|
||||
meta_path = os.path.join(d, "meta.json")
|
||||
if os.path.exists(meta_path):
|
||||
import json
|
||||
try:
|
||||
with open(meta_path) as f:
|
||||
total = json.load(f).get('total_chunks', 0)
|
||||
except (json.JSONDecodeError, IOError):
|
||||
pass
|
||||
|
||||
return jsonify({
|
||||
"task_id": task_id,
|
||||
"uploaded_chunks": uploaded,
|
||||
"uploaded_count": len(uploaded),
|
||||
"total_chunks": total,
|
||||
}), 200
|
||||
|
||||
|
||||
@api_bp.route('/api/edge/video/assemble', methods=['POST'])
|
||||
def assemble_chunks():
|
||||
"""合并所有分块为完整视频文件，入 SQLite 队列
|
||||
|
||||
NAS 上传完全部分块后调用此端点触发合并 + 入队。
|
||||
"""
|
||||
task_id_raw = request.form.get('task_id')
|
||||
if not task_id_raw:
|
||||
return jsonify({"error": "缺少 task_id"}), 400
|
||||
|
||||
try:
|
||||
task_id = int(task_id_raw)
|
||||
except ValueError:
|
||||
return jsonify({"error": "task_id 必须是整数"}), 400
|
||||
|
||||
camera_name = request.form.get('camera_name', '')
|
||||
event_start_time = request.form.get('event_start_time', '')
|
||||
known_members_context = request.form.get('known_members_context', '')
|
||||
|
||||
d = _chunk_dir(task_id)
|
||||
|
||||
# 读取元数据
|
||||
import json
|
||||
meta_path = os.path.join(d, "meta.json")
|
||||
if not os.path.exists(meta_path):
|
||||
return jsonify({"error": "元数据不存在，请先上传分块"}), 400
|
||||
|
||||
try:
|
||||
with open(meta_path) as f:
|
||||
meta = json.load(f)
|
||||
except json.JSONDecodeError:
|
||||
return jsonify({"error": "元数据损坏"}), 500
|
||||
|
||||
filename = meta.get('filename', 'video.mp4')
|
||||
total_chunks = meta.get('total_chunks', 0)
|
||||
|
||||
# 检查分块完整性
|
||||
chunk_files = sorted([
|
||||
fn for fn in os.listdir(d)
|
||||
if fn.startswith('chunk_') and len(fn.split('_')) == 2
|
||||
])
|
||||
|
||||
if total_chunks and len(chunk_files) < total_chunks:
|
||||
missing = total_chunks - len(chunk_files)
|
||||
return jsonify({
|
||||
"error": f"分块不完整: {len(chunk_files)}/{total_chunks}，缺 {missing} 块",
|
||||
"uploaded_count": len(chunk_files),
|
||||
"total_chunks": total_chunks,
|
||||
}), 400
|
||||
|
||||
# 合并分块
|
||||
upload_dir = os.environ.get('FAM_UPLOAD_DIR', '/tmp/fam_uploads')
|
||||
video_filename = f"task_{task_id}_{filename}"
|
||||
video_path = os.path.join(upload_dir, video_filename)
|
||||
|
||||
try:
|
||||
with open(video_path, 'wb') as out:
|
||||
for cf in chunk_files:
|
||||
chunk_path = os.path.join(d, cf)
|
||||
with open(chunk_path, 'rb') as chunk_f:
|
||||
out.write(chunk_f.read())
|
||||
|
||||
size_mb = os.path.getsize(video_path) / 1024 / 1024
|
||||
logger.info(f"[task_id={task_id}] 分块合并完成: {filename} ({size_mb:.1f}MB, {len(chunk_files)} 块)")
|
||||
|
||||
# 清理分块目录
|
||||
import shutil
|
||||
shutil.rmtree(d, ignore_errors=True)
|
||||
|
||||
# 入队
|
||||
queue_id = queue_manager.enqueue(
|
||||
nas_task_id=task_id,
|
||||
video_filename=filename,
|
||||
video_path=video_path,
|
||||
camera_name=camera_name,
|
||||
event_start_time=event_start_time,
|
||||
known_members_context=known_members_context,
|
||||
)
|
||||
|
||||
return jsonify({
|
||||
"status": "queued",
|
||||
"task_id": task_id,
|
||||
"queue_id": queue_id,
|
||||
"size_mb": round(size_mb, 1),
|
||||
}), 202
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[task_id={task_id}] 合并失败: {e}", exc_info=True)
|
||||
return jsonify({"error": str(e)}), 500
|
||||
|
||||
|
||||
@api_bp.route('/api/edge/results', methods=['GET'])
|
||||
def get_results():
|
||||
"""返回已完成但未拉取的结果，标记为已交付"""
|
||||
limit = int(request.args.get('limit', 10))
|
||||
results = queue_manager.get_undelivered_results(limit=limit)
|
||||
|
||||
import json
|
||||
payload = []
|
||||
task_ids = []
|
||||
for r in results:
|
||||
try:
|
||||
result_json = json.loads(r['result_json']) if r['result_json'] else None
|
||||
except json.JSONDecodeError:
|
||||
result_json = None
|
||||
if r['status'] == 'FAILED':
|
||||
result_json = {
|
||||
"status": "failed",
|
||||
"error_message": r['error_message'] or 'unknown',
|
||||
"failure_stage": r['failure_stage'] or '',
|
||||
}
|
||||
payload.append({
|
||||
"nas_task_id": r['nas_task_id'],
|
||||
"result": result_json,
|
||||
})
|
||||
task_ids.append(r['id'])
|
||||
|
||||
if task_ids:
|
||||
queue_manager.mark_delivered(task_ids)
|
||||
|
||||
return jsonify({"results": payload, "count": len(payload)}), 200
|
||||
|
||||
|
||||
@api_bp.route('/api/edge/queue/stats', methods=['GET'])
|
||||
def queue_stats():
|
||||
"""队列状态统计"""
|
||||
stats = queue_manager.get_queue_stats()
|
||||
return jsonify(stats), 200
|
||||
|
||||
|
||||
@api_bp.route('/api/edge/video/push', methods=['POST'])
|
||||
def receive_push_task():
|
||||
"""推送模式：接收 multipart 视频上传，同步分析，结果随 HTTP 响应返回
|
||||
|
||||
NAS 无法被 Oracle 反向访问（Tailscale 不通），因此改为 NAS 主动上传视频，
|
||||
Edge 用 OpenCV 场景变化检测抽帧后分析，摘要直接放在响应里带回。
|
||||
"""
|
||||
global _currently_processing
|
||||
|
||||
task_id_raw = request.form.get('task_id')
|
||||
file = request.files.get('video')
|
||||
if not task_id_raw or not file:
|
||||
return jsonify({"error": "缺少必填字段: task_id, video"}), 400
|
||||
|
||||
try:
|
||||
task_id = int(task_id_raw)
|
||||
except ValueError:
|
||||
return jsonify({"error": "task_id 必须是整数"}), 400
|
||||
|
||||
logger.info(f"[task_id={task_id}] 收到推送任务: {file.filename}")
|
||||
|
||||
# 并发控制（同步处理，占用整个请求周期）
|
||||
with _current_task_lock:
|
||||
if _currently_processing:
|
||||
logger.warning(f"[task_id={task_id}] 已有任务处理中，返回 429")
|
||||
return jsonify({"error": "Queue full", "retry_after": 60}), 429
|
||||
_currently_processing = True
|
||||
|
||||
preprocessor = None
|
||||
try:
|
||||
preprocessor = VideoPreprocessor(task_id)
|
||||
video_path = preprocessor.save_upload(file)
|
||||
|
||||
task_data = {
|
||||
"task_id": task_id,
|
||||
"camera_name": request.form.get('camera_name', ''),
|
||||
"event_start_time": request.form.get('event_start_time', ''),
|
||||
"event_end_time": request.form.get('event_end_time', ''),
|
||||
"known_members_context": request.form.get('known_members_context', ''),
|
||||
}
|
||||
|
||||
result = get_orchestrator().process_push_task(task_data, video_path, preprocessor)
|
||||
return jsonify(result), 200
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[task_id={task_id}] 推送任务异常: {e}", exc_info=True)
|
||||
return jsonify({
|
||||
"task_id": task_id, "status": "failed",
|
||||
"failure_stage": "upload", "error_message": str(e)
|
||||
}), 200
|
||||
finally:
|
||||
if preprocessor is not None:
|
||||
preprocessor.cleanup()
|
||||
with _current_task_lock:
|
||||
_currently_processing = False
|
||||
|
||||
|
||||
@api_bp.route('/api/edge/mark_frames', methods=['POST'])
|
||||
def mark_frames():
|
||||
"""NAS 存量关键帧批量补红框（检测计算在 Edge，NAS 只存图）"""
|
||||
data = request.get_json(silent=True)
|
||||
if not data:
|
||||
return jsonify({"error": "Invalid JSON"}), 400
|
||||
images = data.get('images')
|
||||
if not isinstance(images, list) or not images or len(images) > 12:
|
||||
return jsonify({"error": "images 需要 1-12 项 [{key, data}]"}), 400
|
||||
|
||||
from ..frame_marker import mark_jpeg
|
||||
results = []
|
||||
for item in images:
|
||||
key = item.get('key', '')
|
||||
b64 = item.get('data', '')
|
||||
try:
|
||||
marked, faces = mark_jpeg(base64.b64decode(b64))
|
||||
results.append({
|
||||
"key": key,
|
||||
"data": base64.b64encode(marked).decode('ascii'),
|
||||
"faces": faces
|
||||
})
|
||||
except Exception as e:
|
||||
logger.warning(f"补标失败 {key}: {e}")
|
||||
results.append({"key": key, "data": None, "faces": 0, "error": str(e)})
|
||||
return jsonify({"results": results}), 200
|
||||
|
||||
|
||||
@api_bp.route('/health', methods=['GET'])
|
||||
def health():
|
||||
"""健康检查"""
|
||||
global _currently_processing
|
||||
orch = get_orchestrator()
|
||||
healthy = orch.health_check_all()
|
||||
if not healthy:
|
||||
return jsonify({
|
||||
"status": "unavailable",
|
||||
"healthy_models": [],
|
||||
"processing": _currently_processing
|
||||
}), 503
|
||||
return jsonify({
|
||||
"status": "ok",
|
||||
"healthy_models": [a.provider_name for a in healthy],
|
||||
"processing": _currently_processing
|
||||
}), 200
|
||||
|
||||
|
||||
@api_bp.route('/api/edge/chat', methods=['POST'])
|
||||
def chat_proxy():
|
||||
"""代理转发至本地 Ollama /api/generate（兼容旧调用，Ollama 未对外暴露）"""
|
||||
data = request.get_json(silent=True)
|
||||
if not data:
|
||||
return jsonify({"error": "Invalid JSON"}), 400
|
||||
|
||||
try:
|
||||
resp = requests.post(
|
||||
'http://127.0.0.1:11434/api/generate',
|
||||
json=data,
|
||||
timeout=data.get('options', {}).get('timeout', 120)
|
||||
)
|
||||
return jsonify(resp.json()), resp.status_code
|
||||
except requests.RequestException as e:
|
||||
logger.error(f"Chat proxy error: {e}")
|
||||
return jsonify({"error": f"Ollama unreachable: {e}"}), 502
|
||||
return jsonify({"status": "ok", "label": label, "canonical_name": canonical}), 200
|
||||
|
||||
|
||||
@api_bp.route('/api/edge/chat/ask', methods=['POST'])
|
||||
def chat_ask():
|
||||
"""智能问答编排：Gemini → NVIDIA → 本地 Ollama（两云端都失败才用本地兜底）
|
||||
|
||||
请求: {"prompt": "..."}
|
||||
请求: {"prompt": "...", "max_tokens": 512}
|
||||
响应: {"answer": "...", "provider": "gemini"|"nvidia"|"ollama"}
|
||||
"""
|
||||
data = request.get_json(silent=True)
|
||||
@@ -519,12 +105,24 @@ def chat_ask():
|
||||
return jsonify({"error": "缺少必填字段: prompt"}), 400
|
||||
|
||||
prompt = data['prompt']
|
||||
max_tokens = int(data.get('max_tokens', 512))
|
||||
max_tokens = int(data.get('max_tokens', 1024))
|
||||
|
||||
answer, provider = get_orchestrator().run_qa(prompt, max_tokens=max_tokens)
|
||||
answer, provider = get_qa().run_qa(prompt, max_tokens=max_tokens)
|
||||
if answer is None:
|
||||
return jsonify({
|
||||
"error": "所有模型均不可用（Gemini / NVIDIA / Ollama 全部失败）"
|
||||
}), 503
|
||||
|
||||
return jsonify({"answer": answer, "provider": provider}), 200
|
||||
|
||||
|
||||
@api_bp.route('/health', methods=['GET'])
|
||||
def health():
|
||||
"""健康检查"""
|
||||
try:
|
||||
db = state.get_db()
|
||||
vids = db._conn.execute(
|
||||
"SELECT COUNT(*) c FROM videos WHERE status='done'").fetchone()['c']
|
||||
return jsonify({"status": "ok", "processed_videos": vids}), 200
|
||||
except Exception as e:
|
||||
return jsonify({"status": "error", "error": str(e)}), 500
|
||||
|
||||
Reference in New Issue
Block a user