From ac6e0e03dac7212cc83e49f1823b8829e6c10f99 Mon Sep 17 00:00:00 2001 From: wuyang <5700876+banisherwy@user.noreply.gitee.com> Date: Wed, 8 Jul 2026 17:26:21 +0800 Subject: [PATCH] Let Ollama own model residency --- web/README.md | 2 +- web/app.py | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/web/README.md b/web/README.md index 7801ac8..41c0fb9 100644 --- a/web/README.md +++ b/web/README.md @@ -38,7 +38,7 @@ https://lab.k1412.top/ - Search Agent 查询理解:`ChatGPT-5.6:light` - Search Agent 结果简报、搜索追问、论文对话:`ChatGPT-5.6:fast` - Ollama 请求单并发执行,并缓存结果到 `web/cache/ai/` -- 应用侧不下发 `num_ctx`,上下文长度由 Ollama 服务端 runner 统一控制 +- 应用侧不下发 `num_ctx` / `keep_alive`,上下文长度和模型常驻由 Ollama 服务端统一控制 - arXiv 摘要缓存到 `web/cache/arxiv/` ## Knowledge Design diff --git a/web/app.py b/web/app.py index bb00663..e41d709 100644 --- a/web/app.py +++ b/web/app.py @@ -1236,7 +1236,6 @@ def call_ollama(model: str, prompt: str, mode: str) -> dict[str, Any]: "model": model, "prompt": prompt, "stream": False, - "keep_alive": "2m", "options": options, } data = json.dumps(payload, ensure_ascii=False).encode("utf-8")