Starting with LlamaIndex is a fantastic alternative when constructing an RAG pipeline. Normally, you wish an OpenAI API key to follow the numerous tutorials available.
Nevertheless, you would possibly face these situations:
- Your organization can only use privately deployed models on account of compliance.
- You’re using a model fine-tuned by your data science team.
- Legal restrictions prevent your organization’s private data from leaving the country.
- Other reasons that require using privately deployed models.
When constructing enterprise AI applications, you’ll be able to’t use OpenAI or other cloud providers’ LLM services.
This results in a frustrating first step: How do I connect my LlamaIndex code to my company’s private API service?
To save lots of your time, for those who just need the answer, install this extension:
pip install -U llama-index-llms-openai-like
This can solve your problem.
If you should understand why, let’s proceed.
