I don't know what datasets you guys are working with that have no issues being shared in plain text across three separate proprietary paid services, but this is a nonstarter for me.
- Airbyte has two self-hosted options: OSS & Enterprise
- Langchain: OSS
- OpenAI: you can host an OSS model if you want to
- Pinecone: there are OSS/self-hosted alternatives
Just to confirm: you mean models like Facebook's Llama 2 and variants right? Since OpenAI hasn't released any OSS models.