dify 连接不上ollama An error occurred during credentials validation:

三大报错

An error occurred during credentials validation: HTTPConnectionPool(host='host.docker.internal', port=11434): Max retries exceeded with url: /api/chat (Caused by NameResolutionError("<urllib3.connection.HTTPConnection object at 0x7f26fc3c00b0>: Failed to resolve 'host.docker.internal' (Errno -2 Name or service not known)"))

An error occurred during credentials validation: HTTPConnectionPool(host='192.168.1.100', port=11434): Max retries exceeded with url: /api/chat (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7f26fc23ea80>, 'Connection to 192.168.1.100 timed out. (connect timeout=10)'))

An error occurred during credentials validation: HTTPConnectionPool(host='172.17.0.1', port=11434): Max retries exceeded with url: /api/chat (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f26fcbce660>: Failed to establish a new connection: Errno 111 Connection refused'))

真服了!!!

按照大家搜的,一般都能解决,

首先确保 自己的不是回环。

sudo netstat -tuln | grep 11434

输出为 tcp 什么 127.0.0.1 这个就不行

输出为tcp6 0 0 :::11434 :::* LISTEN

这个 就可以

先停止 参考https://zhuanlan.zhihu.com/p/23168996538

复制代码
systemctl stop ollama

后启动

OLLAMA_HOST=0.0.0.0 nohup ollama serve > ollama.log 2>&1 &

又是浪费5个小时的狗血经历

相关推荐
武子康5 天前
调查研究-200 llama.cpp b9754:一次很小但很关键的 Agent 工具调用修复
人工智能·agent·llama
AI小百科16 天前
llama.cpp vs vLLM:深度解析与选型指南
llama·vllm
下班走回家17 天前
本地部署大模型的三种方式:Ollama vs vLLM vs llama.cpp
人工智能·llama·vllm
zhy2956319 天前
【DNN】基于llama.cpp的Qwen3-0.6B量化部署微调
人工智能·lora·dnn·llama·qwen3
kuokay20 天前
MLOps 与 AIOps 的核心概
人工智能·分布式·大模型·agent·llama
Trouville0121 天前
windows系统使用llama.cpp进行本地大模型部署
llama
棒棒的唐21 天前
windows 直接安装llama.cpp的方法
llama
troubles maker21 天前
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
llm·nlp·llama·多模态
xyz_CDragon21 天前
把旧电脑变成AI算力:llama.cpp RPC 局域网分布式推理验证与实战
人工智能·分布式·python·rpc·llama