# DigitalOcean + Weaviate

<!-- Note: for images, use https://docs.google.com/presentation/d/15opIcJuaIjEEcs_1Zm8B6pccox2p7_MHSjCnRv4dPfU/edit?usp=sharing -->

[DigitalOcean's Serverless Inference](https://docs.digitalocean.com/products/inference/how-to/use-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.

:::callout{intent="note"}
Looking to _host_ Weaviate on DigitalOcean? See [DigitalOcean Managed Weaviate](../digitalocean/digitalocean.md).
:::

## Integrations with DigitalOcean

### Embedding models for vector search

![Embedding integration illustration](/assets/docs/weaviate/model-providers/_includes/integration_digitalocean_embedding.png)

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](digitalocean-embeddings.md) 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-embeddings.md)

### Generative AI models for RAG

![Single prompt RAG integration generates individual outputs per search result](/assets/docs/weaviate/model-providers/_includes/integration_digitalocean_rag_single.png)

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](digitalocean-generative.md) 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](digitalocean-generative.md)

## Summary

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

## Get started

Generate an API key in the [DigitalOcean Cloud console](https://cloud.digitalocean.com/) 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](digitalocean-embeddings.md)
- [Generative AI](digitalocean-generative.md)

## Questions and feedback

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

::::card-grid
:::card{title="Community Forum" href="https://forum.weaviate.io/c/support" icon="messages-square"}
Ask questions and connect with other developers on our **Community forum**.
:::

:::card{title="Support" href="/guides/support-overview" icon="life-buoy"}
Weaviate Cloud user or customer? Find the right channel on the **Support page**.
:::
::::

## Related pages

- [Agents](./agents-index.md)
- [AI-assisted Weaviate code generation](./ai-assisted-vibe-coding-index.md)
- [APIs](./apis-index.md)
- [Authorization and authentication](./authorization-and-authentication-index.md)
- [Benchmarks](./benchmarks-index.md)
- [Best practices](./best-practices-index.md)
- [Client libraries](./clients-index.md)
- [Client Libraries / SDKs](./client-libraries-index.md)
- [Cloud](./cloud-index.md)
- [Cloud account management](./cloud-account-management-index.md)

# Agent Instructions

This portal answers questions programmatically. To receive a synthesized,
source-cited answer instead of crawling page by page, append the `?ask=`
query parameter to any page URL on this site:

    /guides/quickstart?ask=how+do+I+authenticate

Optional parameters:

- `&goal=<what-you-are-trying-to-do>` steers the answer toward your
  objective (e.g. `&goal=write+a+python+client`).
- `&version=<label>` scopes the answer to a mounted version when the
  portal publishes more than one.

The response is `text/markdown`: the answer followed by a `# Sources` list
of the portal pages it was grounded in. Status codes are the contract:

- `200` — the answer; `402` — the portal owner’s plan or answer credits are
  exhausted (surface this to your operator; do NOT retry); `429` — you are
  rate-limited; back off for the `Retry-After` seconds; `503` — the answer
  lane is temporarily unavailable; fall back to crawling the `.md` pages.

For the full corpus map read `llms.txt` at the site root; for the tool
surface (search + page fetch as MCP tools) see `/mcp`.