Azure OpenAI integration

[TempoShaman]

Is your feature request related to a problem? Please describe.
I can't use Azure OpenAI api-key.

Describe the solution you'd like
It would be nice to have option to use Azure OpenAI api-key for working with Wren.ai since this is main platform where I would like to use your solution.

Describe alternatives you've considered
One alternative can be using Azure OpenAI integration provided with Langchain but I am not certain that it would not cause any further issues. I have not tried it yet.

[cyyeh]

@TempoShaman Thanks for reaching out! We have provided a document demonstrating how to add your preferred LLM or Document Store. Please check out this guide: https://docs.getwren.ai/installation/custom_llm. We are using Haystack underneath, and it already supports Azure OpenAI. I think you can integrate it within 30 minutes. We welcome your contributions! Thank you!

https://docs.haystack.deepset.ai/docs/azureopenaigenerator

Feel free to ask us any questions!

[cyyeh]

@TempoShaman after this PR is merged, you can start using Azure OpenAI I think :)
#390

[puneet1389]

@cyyeh firstly thanks for this solution, i was trying to explore this but i got stuck in the api key step, it is still asking for Open AI key whereas i want to add azure open AI keys. how can i proceed with this problem?

[cyyeh]

@puneet1389 thanks for reaching out! We haven't added to our launcher yet. We'll write documentation for it later, thank you.

Basically you clone the repo, fill in environment variables in the docker folder and docker-compose.yaml, then run docker-compose --env-file .env.local up -d

Welcome to join our Discord server and checkout this link for further details:
Discord invitation link:
https://discord.com/invite/5DvshJqG8Z

discussion:
https://discord.com/channels/1227143286951514152/1252162187796152434

[cyyeh]

All, we now support using Azure OpenAI, Ollama, and OpenAI API-compatible LLMs now with the latest release: https://github.com/Canner/WrenAI/releases/tag/0.6.0

Setups on how to run Wren AI using custom LLMs: https://docs.getwren.ai/installation/custom_llm#running-wren-ai-with-your-custom-llm-or-document-store

Currently, there is one obvious limitation for custom LLMs: you need to use the same provder(such as OpenAI, or Ollama) for LLM and embedding model. We'll fix that and release a new version soon. Stay tuned 🙂

I'll close this issue as completed now.