feat: 更新后端配置、Docker部署、API模块及多项文档

- 更新后端 main.py、config.py 核心配置
- 更新 compute API 模块
- 更新 Docker 部署配置(app/compute docker-compose、nginx、环境变量)
- 更新前端 API 模块(dataset、model、request)及 vite 配置
- 更新多项项目文档(架构、部署、开发计划、日志等)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
wuyongtao
2026-07-21 10:09:36 +08:00
parent a67ca2c19c
commit bccd3bf448
21 changed files with 418 additions and 415 deletions

View File

@@ -14,6 +14,7 @@ from compute.engines.llama_factory.adapter import build_command, parse_log_line
def create_app() -> FastAPI:
app = FastAPI(title="YG Fine-Tune Compute API")
jobs: dict[str, dict[str, Any]] = {}
route_prefix = os.getenv("MODELTF_ROUTE_PREFIX", "/modelTF").rstrip("/") or "/modelTF"
def now() -> float:
return time.time()
@@ -101,14 +102,14 @@ def create_app() -> FastAPI:
)
return gpus
@app.get("/health")
@app.get(f"{route_prefix}/health")
async def health_check() -> dict[str, str]:
return {
"status": "ok",
"compute_host_id": os.getenv("COMPUTE_HOST_ID", "unknown"),
}
@app.get("/api/v1/compute/health")
@app.get(f"{route_prefix}/v1/compute/health")
async def compute_health_check() -> dict[str, str | bool]:
data_root = Path(os.getenv("YG_FT_DATA_ROOT", "/data/yg-ft"))
llama_factory_home = Path(os.getenv("LLAMA_FACTORY_HOME", "/app/LLaMA-Factory"))
@@ -122,15 +123,15 @@ def create_app() -> FastAPI:
"llama_factory_home_exists": llama_factory_home.exists(),
}
@app.get("/api/v1/compute/jobs")
@app.get(f"{route_prefix}/v1/compute/jobs")
async def list_jobs_alias() -> dict[str, list[dict[str, Any]]]:
return {"items": [job_status(job) for job in jobs.values()]}
@app.get("/compute/resources/gpus")
@app.get(f"{route_prefix}/compute/resources/gpus")
async def list_gpus() -> dict[str, Any]:
return {"items": gpu_resources(), "compute_host_id": host_id()}
@app.post("/compute/jobs")
@app.post(f"{route_prefix}/compute/jobs")
async def create_job(payload: dict[str, Any]) -> dict[str, Any]:
try:
command = build_command(payload, os.getenv("LLAMA_FACTORY_HOME", "/app/LLaMA-Factory"))
@@ -153,18 +154,18 @@ def create_app() -> FastAPI:
jobs[job_id] = job
return job_status(job)
@app.get("/compute/jobs")
@app.get(f"{route_prefix}/compute/jobs")
async def list_jobs() -> dict[str, Any]:
return {"items": [job_status(job) for job in jobs.values()]}
@app.get("/compute/jobs/{job_id}")
@app.get(f"{route_prefix}/compute/jobs/{{job_id}}")
async def get_job(job_id: str) -> dict[str, Any]:
job = jobs.get(job_id)
if not job:
raise HTTPException(status_code=404, detail="job not found")
return job_status(job)
@app.post("/compute/jobs/{job_id}/stop")
@app.post(f"{route_prefix}/compute/jobs/{{job_id}}/stop")
async def stop_job(job_id: str) -> dict[str, Any]:
job = jobs.get(job_id)
if not job:
@@ -173,7 +174,7 @@ def create_app() -> FastAPI:
job["progress"] = min(job.get("progress", 0), 99)
return job
@app.get("/compute/jobs/{job_id}/logs")
@app.get(f"{route_prefix}/compute/jobs/{{job_id}}/logs")
async def job_logs(job_id: str) -> dict[str, Any]:
job = jobs.get(job_id)
if not job:
@@ -182,14 +183,14 @@ def create_app() -> FastAPI:
metrics = [parse_log_line(line) for line in job["logs"].splitlines()]
return {"job_id": job_id, "content": job["logs"], "metrics": [m for m in metrics if m]}
@app.post("/compute/files/upload")
@app.post(f"{route_prefix}/compute/files/upload")
async def upload_file(payload: dict[str, Any]) -> dict[str, Any]:
file_id = str(payload.get("id") or f"file_{int(now() * 1000)}")
return {"id": file_id, "status": "available", "local_path": f"/data/yg-ft/uploads/{file_id}"}
@app.get("/compute/files/{file_id}/download")
@app.get(f"{route_prefix}/compute/files/{{file_id}}/download")
async def download_file(file_id: str) -> dict[str, Any]:
return {"id": file_id, "status": "ready", "download_url": f"/compute/files/{file_id}/download"}
return {"id": file_id, "status": "ready", "download_url": f"{route_prefix}/compute/files/{file_id}/download"}
return app