Inconsistency in AI Proxy plugin configuration for Mistral

[lfavreli]

Where is the problem?

https://docs.konghq.com/hub/kong-inc/ai-proxy/how-to/llm-provider-integration-guides/mistral/

What happened?

There is an inconsistency between the documentation and the provided cURL command for configuring the AI Proxy plugin for Mistral. The documentation states:

Enable and configure the AI Proxy plugin for Mistral (using ollama format in this example):"

However, the command uses the openai format instead of ollama:

curl -X POST http://localhost:8001/routes/mistral-chat/plugins \
 --data "name=ai-proxy" \
 --data "config.route_type=llm/v1/chat" \
 --data "config.auth.header_name=Authorization" \
 --data "config.auth.header_value=Bearer <MISTRAL_AI_KEY>" \
 --data "config.model.provider=mistral" \
 --data "config.model.name=mistral-tiny" \
 --data "config.model.options.mistral_format=openai" \
 --data "config.model.options.upstream_url=https://api.mistral.ai/v1/chat/completions" \ 

This discrepancy can lead to confusion.

What did you expect to happen?

The documentation should correctly reflect the format used in the command.

If the format openai is correct, the documentation should state:

"Enable and configure the AI Proxy plugin for Mistral (using openai format in this example):".

If ollama is correct, the command should be updated accordingly.

Code of Conduct and Community Expectations

• I agree to follow this project's Code of Conduct
• I agree to abide by the Community Expectations