Relevance AI
Relevance AI
Metaphor logo

Metaphor integration

Search Rebuilt for AI. The Exa API retrieves the best content on the web using embeddings-based search.

What your agents can do with Metaphor

3 pre-built Metaphor tool steps, ready to drop into any agent. Anything they do not cover, an agent can reach with an authenticated API call.

Actions (3)

Search

Perform a search with a Metaphor prompt-engineered query and retrieve a list of relevant results.

Get Contents of Documents

Retrieve contents of documents based on a list of document IDs. It is used to instantly get content for documents, given the IDs of the documents. We currently support extracts - the first 1000 tokens (~750 words) of parsed HTML for a site. Note that each piece of content retrieved costs 1 request. Also note that instant is a little bit of a lie if you are using keyword search, in which case contents might take a few seconds to retrieve.

Find Similar Links

Find similar links to the link provided.

Set up Metaphor in Relevance AI

Do this once. Every agent in your workspace can then use the connection.

1

Create a Relevance AI account

Sign in, or create a free account. You do not need to be a developer to set this up.

2

Connect your Metaphor account

In Relevance AI, open Integrations and add Metaphor, then paste your API key. You will find it in your Metaphor account settings.

3

Use Metaphor in an agent

Create a tool, add a Metaphor tool step, and connect it to an agent. The agent fills in the step's inputs each time it runs.

Put Metaphor to work in your agents

Connect Metaphor alongside 1,800+ other integrations and let your agents run the busywork.