Exa - Neural Web Search & Research

Exa - Neural Web Search & Research

Setup

Read your credentials from ~/.gooseworks/credentials.json:

export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")

If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login

All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"

Neural search engine for finding similar content, extracting pages, and deep research.

Capabilities

• Exa Research: Retrieve a paginated list of your research tasks
• Answer: Get an LLM answer to a question informed by Exa search results
• Search: The search endpoint lets you intelligently search the web and extract contents from the results
• Get a task: Retrieve the status and results of a previously created research task
• Find similar links: Find similar links to the link provided and optionally return the contents of the pages
• Create a task: Create an asynchronous research task that explores the web, gathers sources, synthesizes findings, and returns results with citations
• Get contents: Get the full page contents, summaries, and metadata for a list of URLs

Usage

Exa Research

Retrieve a paginated list of your research tasks. The response follows a cursor-based pagination pattern. Pass the limit parameter to control page size (max 50) and use the cursor token returned in the response to fetch subsequent pages.

Parameters:

• cursor (string) - The cursor to paginate through the results Minimum string length: 1
• limit (number) - Number of results per page (1-50) Required range: 1 <= x <= 50

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \