wuyang/agent
2
2
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Let Ollama own model residency

Browse Source
This commit is contained in:
wuyang
2026-07-08 17:26:21 +08:00
parent 47c301c35f
commit ac6e0e03da
2 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
web/README.md
+1 -1
View File
@@ -38,7 +38,7 @@ https://lab.k1412.top/
- Search Agent 查询理解：`ChatGPT-5.6:light` - 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` - 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/` - 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/` - arXiv 摘要缓存到 `web/cache/arxiv/`
## Knowledge Design ## Knowledge Design
web/app.py
-1
View File
@@ -1236,7 +1236,6 @@ def call_ollama(model: str, prompt: str, mode: str) -> dict[str, Any]:
"model": model, "model": model,
"prompt": prompt, "prompt": prompt,
"stream": False, "stream": False,
"keep_alive": "2m",
"options": options, "options": options,
} }
data = json.dumps(payload, ensure_ascii=False).encode("utf-8") data = json.dumps(payload, ensure_ascii=False).encode("utf-8")