Incorrect use of GPT-4 leads to increased costs

[lvjiajjjlzy]

Self Checks

• This is only for bug report, if you would like to ask a question, please head to Discussions.
• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• Please do not modify this template :) and fill in all the required fields.

Dify version

0.6.8

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

选择GPT-4o并运行后，对话就可能会引发问题，问题位于生成标题。After selecting GPT-4o and running it, the conversation can trigger the problem

✔️ Expected Behavior

Use GPT-4o to generate the title.使用GPT-4o来生成标题。

❌ Actual Behavior

使用了GPT-4。is GPT-4.

[dosubot]

To address the issue where GPT-4 is being used instead of GPT-4o in your self-hosted Dify setup, leading to increased costs, follow these steps:

1. Check Dify's Model Configuration:

   • Ensure the model name and server URL in Dify's settings are correctly set for GPT-4o. This is found under Settings > Model Providers > LocalAI.

2. Verify LocalAI Model Configuration:

   • Confirm that the models/gpt-3.5-turbo.yaml or your specific GPT-4o model configuration file correctly points to the GPT-4o model file. It's crucial that this configuration does not mistakenly point to a GPT-4 model file.

3. Review Network Configuration for Docker:

   • If Dify is deployed via Docker, make sure the network configuration allows Dify containers to correctly access the LocalAI endpoint. The Server URL in Dify's model configuration should point to the correct LocalAI endpoint, which might be your host IP address followed by the port, e.g., http://192.168.1.100:8080.

4. LocalAI Version and Compatibility:

   • Ensure your LocalAI version supports GPT-4o and that you've followed any specific instructions for deploying GPT-4o models with LocalAI.

If these steps do not resolve the issue, it may be necessary to consult the LocalAI documentation or support channels for further guidance on configuring GPT-4o models.

Details

Sources

• 高级模型（gpt-4）的潜在使用
• en/tutorials/model-configuration/localai.md
• en/tutorials/model-configuration/README.md
• api/core/model_runtime/model_providers/openai/llm/gpt-4o.yaml
• api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-05-13.yaml
• en/getting-started/install-self-hosted/environments.md
• en/features/logs.md
• .github/ISSUE_TEMPLATE/bug_report.yml
• api/controllers/console/app/error.py
• api/controllers/web/error.py
• api/core/model_runtime/model_providers/openai/llm/gpt-4.yaml

About Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.

[crazywoola]

Change this

[ozeron]

Wow, GPT-4 is the most expensive one, please change default one to something else.
I leaked about 10$ over couple of days due to this =(