Unverified50% confidenceFactExact time
The generation stage runs on a local llama.cpp model on the developer's machine, called via the HTTP interface on port :8080, and falls back to a template when the server is down.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedOn Linux, Docker installs the Llama server at localhost:11434 by default; the Windows path uses port 8080, and OpenWebUI is consistently kept at localhost:3000.66% similarUnverifiedDSH 安装完成后会在本地启动 3080 端口的监听地址，通过该地址进入 Web 端对话界面62% similarUnverifiedThe project's backend is based on FastAPI and runs on port 8090.62% similarUnverifiedv3.30.0 fixes the issue of restore async HTTP/1.1 connection reuse in streaming scenarios.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033211API
curl https://kongchang.com/api/v1/knowledge/claims/1033211MCP
get_claim(id=1033211)