DigitalOcean + Weaviate

DigitalOcean's Serverless Inference hosts a curated set of open-weight embedding and language models behind a single OpenAI-compatible API. Weaviate integrates with DigitalOcean's embedding and chat completions endpoints so you can vectorize, search, and generate over your data using DigitalOcean-hosted models directly from your Weaviate instance.

DigitalOcean Serverless Inference exposes embedding models (e.g. qwen3-embedding-0.6b) over an OpenAI-compatible /v1/embeddings API at https://inference.do-ai.run.

Weaviate integrates with DigitalOcean's embedding models through the text2vec-digitalocean vectorizer module. Configure a vector index to use a DigitalOcean model and Weaviate generates embeddings for imports, vector searches, and hybrid searches automatically.

DigitalOcean embedding integration page

DigitalOcean Serverless Inference exposes chat models (e.g. llama-4-maverick) over an OpenAI-compatible /v1/chat/completions API at https://inference.do-ai.run.

Weaviate integrates with DigitalOcean's generative models through the generative-digitalocean module. Configure a collection to use a DigitalOcean model and Weaviate performs retrieval augmented generation (RAG) over your search results automatically.

DigitalOcean generative integration page

These integrations let you leverage DigitalOcean's hosted embedding and generative models from Weaviate without managing inference infrastructure yourself.

Generate an API key in the DigitalOcean Cloud console and supply it to Weaviate via the DIGITALOCEAN_APIKEY environment variable or the X-Digitalocean-Api-Key request header. The same key serves both integrations. Then see the integration pages:

• Text Embeddings
• Generative AI

Have a question or feedback? Here's how to reach us.