[Bug] Ollama integration not working.

[ZaEvab55555]

📦 Environment

Docker

📌 Version

Latest Docker, Windows 11

💻 Operating System

Windows

🌐 Browser

Other

🐛 Bug Description

When I try to use Lobe Chat with oLLama, it tells me "{
"error": {
"message": "fetch failed",
"name": "TypeError"
},
"provider": "ollama"
}"
Why does it do that?

📷 Recurrence Steps

I start ollama and start the lobe chat server. Then I navigate to the local server and try to chat.

🚦 Expected Behavior

I thought it would respond to my prompt of "What is lobechat?"

📝 Additional Information

No response

[lobehubbot]

👀 @ZaEvab55555

Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible.
Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事，并尽快回复您。 请确保您已经提供了尽可能多的背景信息。

[dosubot]

Hey @ZaEvab55555! I'm here to help you with any bugs, questions, or contributions. Let's tackle this issue together!

The "fetch failed" TypeError you're encountering with the Ollama integration in Lobe Chat on Windows 11 using Docker can be resolved by enabling the client request mode in LobeChat. When this mode is disabled, the Ollama model configuration will fail with a 'fetch failed' TypeError. Make sure that client request mode is enabled in your LobeChat configuration to fix the issue ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}

[dosubot]

The "fetch failed" TypeError when using Ollama integration with Lobe Chat in a Docker environment on Windows 11 can be resolved by enabling the client request mode in LobeChat. When client request mode is disabled, the Ollama model configuration will fail with this error. Ensure that client request mode is enabled in your LobeChat configuration to fix the issue ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}

[ZaEvab55555]

@dosu what about this error?
{
"error": {
"message": "[GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-thinking-exp-01-21:streamGenerateContent?alt=sse: [400 ] Function calling is not enabled for models/gemini-2.0-flash-thinking-exp-01-21"
},
"provider": "google"
}

[dosubot]

The error message indicates that function calling is not enabled for the specified Google Generative AI model. To enable function calling for Google Generative AI models in Lobe Chat, ensure that the model's description includes 'function calling' or 'tools'. This is checked in the transformModel method of the LobeHigressAI class, which enables function calling based on the model's description ^[1][2].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}

[lobehubbot]

✅ @ZaEvab55555

This issue is closed, If you have any questions, you can comment and reply.
此问题已经关闭。如果您有任何问题，可以留言并回复。

[lobehubbot]

🎉 This issue has been resolved in version 1.49.11 🎉

The release is available on:

• npm package (@latest dist-tag)
• GitHub release

Your semantic-release bot 📦🚀