Add feature: Support for multiple models on Azure and Azure model mapper

[shendongming]

Added support for multiple models on Azure; in practice, we will deploy several models on Azure, such as gpt-4, gpt-3.5, etc.

Two changes:

1. Added a new configuration item: AZURE_OPENAI_MODEL_MAPPER
2. Extended the configuration item: AZURE_URL

The changes are as follows:

AZURE_URL (optional)

Example: https://{azure-resource-url}/openai/deployments/{deploy-name}

Example: https://xxx.openai.azure.com/openai/deployments/{deploy-name}

Azure deploy url.

If {deploy-name} is using the template mode, then it will automatically replace the path based on the model selected by the client.
If your model name is different from the deployment name, then you need to set the AZURE_OPENAI_MODEL_MAPPER parameter.

AZURE_OPENAI_MODEL_MAPPER (optional)

Default: Empty
Example: gpt-3.5-turbo=gpt-35-turbo means map gpt-3.5-turbo to gpt-35-turbo

If you are deploying ChatGPT using Azure OpenAI, it is recommended to set the AZURE_OPENAI_MODEL_MAPPER.
The session summarization feature relies on the gpt-3.5-turbo model, unless the name of your Azure deployment is the same as it.

[H0llyW00dzZ]

this default: "2023-04", must made separate for azure as example, because it will affected for openai and become bad hallucination. if force default: "2023-04", for all service provider

[H0llyW00dzZ]

this default: "2023-04", must made separate for azure as example, because it will affected for openai and become bad hallucination. if force default: "2023-04", for all service provider

[H0llyW00dzZ]

Warning

The KnowledgeCutOffDate is intended for system prompts. Exercise caution when changing it, as it must be correctly aligned with the models.

[shendongming]

Thank you
I have set KnowledgeCutOffDate to 2021-09
@H0llyW00dzZ

[vercel]

Someone is attempting to deploy a commit to the NextChat Team on Vercel.

A member of the Team first needs to authorize it.

[github-actions]

Your build has completed!

Preview deployment

[lloydzhou]

看起来似乎是一个容易在配置文件中实现的方案 @Dogtiti

[lloydzhou]

可以直接使用CUSTOM_MODELS中配置gpt-4-1106-preview=gpt-4-turbo的方式，等于后面既作为展示名称，也作为deploy_name使用

[itcodes]

你好，这个最新 readme 文档有了吗？使用 azure 部署的遇到一些麻烦。