Exa Web Search

Search the web using Exa's AI-powered search API. Exa provides semantic search capabilities optimized for AI applications.

Configuration

Config file: ~/.config/exa-search/config.json

{
  "api_key": "your-exa-api-key-here"
}

Getting an API key

1. Go to https://dashboard.exa.ai/api-keys
2. Sign up or log in to your Exa account
3. Create a new API key

Troubleshooting config

If requests fail, verify the config:

# Check config exists and is valid JSON
cat ~/.config/exa-search/config.json | jq .

# Test connection
curl -s -X POST "https://api.exa.ai/search" \
  -H "x-api-key: $(jq -r .api_key ~/.config/exa-search/config.json)" \
  -H "Content-Type: application/json" \
  -d '{"query": "test", "numResults": 1}' | jq '.results | length'

Common issues:

• 401 Unauthorized: API key is invalid → get a new key from dashboard
• Connection refused: Network issue or API is down
• null or parse error: Config file is missing or malformed

If config is broken, guide the user to provide their Exa API key, then create/update the config:

mkdir -p ~/.config/exa-search
cat > ~/.config/exa-search/config.json << 'EOF'
{
  "api_key": "USER_PROVIDED_API_KEY"
}
EOF

Endpoint Selection Guide

Choose the appropriate endpoint based on user intent:

API Examples

Load API key

EXA_API_KEY=$(jq -r .api_key ~/.config/exa-search/config.json)

1. Search (/search)

Semantic search with optional content extraction. Returns results with their contents.

# Basic search
curl -s -X POST "https://api.exa.ai/search" \
  -H "x-api-key: $EXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "latest developments in AI agents",
    "numResults": 10
  }' | jq '.results[] | {title, url, publishedDate}'

# Search with content extraction
curl -s -X POST "https://api.exa.ai/search" \
  -H "x-api-key: $EXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "best practices for RAG systems",
    "numResults": 5,
    "contents": {
      "text": true,
      "highlights": {
        "numSentences": 3,
        "highlightsPerUrl": 2
      },
      "summary": {}
    }
  }' | jq '.results[] | {title, url, summary, highlights}'

# Search with date filters and domain restrictions
curl -s -X POST "https://api.exa.ai/search" \
  -H "x-api-key: $EXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "OpenAI announcements",
    "numResults": 10,
    "startPublishedDate": "2024-01-01T00:00:00.000Z",
    "includeDomains": ["openai.com", "techcrunch.com", "theverge.com"],
    "contents": {
      "text": {"maxCharacters": 1000},
      "summary": {}
    }
  }' | jq

# Search with category filter
curl -s -X POST "https://api.exa.ai/search" \
  -H "x-api-key: $EXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "transformer architecture papers",
    "numResults": 10,
    "category": "research paper",
    "contents": {
      "text": true,
      "summary": {}
    }
  }' | jq

# Deep search for comprehensive results
curl -s -X POST "https://api.exa.ai/search" \
  -H "x-api-key: $EXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "climate change mitigation strategies",
    "type": "deep",
    "numResults": 20,
    "contents": {
      "text": true,
      "summary": {}
    }
  }' | jq

Search types:

• auto (default): Intelligently combines neural and other methods
• neural: Pure semantic/embeddings-based search
• fast: Quick keyword-based search
• deep: Comprehensive search with query expansion

Categories: company, research paper, news, pdf, github, tweet, personal site, financial report, people

2. Contents (/contents)

Extract content from specific URLs.

# Get content from URLs
curl -s -X POST "https://api.exa.ai/contents" \
  -H "x-api-key: $EXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "urls": [
      "https://arxiv.org/abs/2307.06435",
      "https://example.com/article"
    ],
    "text": true,
    "summary": {},
    "highlights": {
      "numSentences": 2,
      "highlightsPerUrl": 3
    }
  }' | jq '.results[] | {url, title, summary, highlights}'

# Get content with livecrawl for fresh data
curl -s -X POST "https://api.exa.ai/contents" \
  -H "x-api-key: $EXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "urls": ["https://example.com/news"],
    "text": {"maxCharacters": 5000},
    "livecrawl": "preferred"
  }' | jq

Livecrawl options:

• never: Only use cache
• fallback: Livecrawl when cache is empty (default)
• preferred: Try livecrawl first, fall back to cache
• always: Always livecrawl, never use cache

3. Answer (/answer)

Get direct answers to questions, grounded in web search results.

# Get a direct answer
curl -s -X POST "https://api.exa.ai/answer" \
  -H "x-api-key: $EXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What is the current population of Tokyo?"
  }' | jq '{answer, citations: [.citations[] | {title, url}]}'

# Answer with full source text
curl -s -X POST "https://api.exa.ai/answer" \
  -H "x-api-key: $EXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What are the main features of GPT-4?",
    "text": true
  }' | jq

4. Research (/research/v1)

Long-running research tasks with structured output. This is asynchronous - you create a task and poll for results.

# Create a research task with structured output
RESEARCH_RESPONSE=$(curl -s -X POST "https://api.exa.ai/research/v1" \
  -H "x-api-key: $EXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "exa-research",
    "instructions": "Compare the top 3 cloud providers (AWS, Azure, GCP) on pricing for compute instances. Return structured data.",
    "outputSchema": {
      "type": "object",
      "required": ["providers"],
      "properties": {
        "providers": {
          "type": "array",
          "items": {
            "type": "object",
            "required": ["name", "computePricing", "strengths"],
            "properties": {
              "name": {"type": "string"},
              "computePricing": {"type": "string"},
              "strengths": {"type": "array", "items": {"type": "string"}}
            }
          }
        }
      }
    }
  }')

RESEARCH_ID=$(echo "$RESEARCH_RESPONSE" | jq -r '.researchId')
echo "Research ID: $RESEARCH_ID"

# Poll for results (repeat until status is "completed" or "failed")
curl -s "https://api.exa.ai/research/v1/$RESEARCH_ID" \
  -H "x-api-key: $EXA_API_KEY" | jq '{status, output}'

# Simple research without schema (returns markdown report)
curl -s -X POST "https://api.exa.ai/research/v1" \
  -H "x-api-key: $EXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "exa-research",
    "instructions": "Summarize the latest developments in quantum computing from the past 6 months."
  }' | jq

Research models:

• exa-research (default): Balanced speed and quality, adapts to task difficulty
• exa-research-pro: Maximum quality, more thorough analysis (slower)

Best practices for research:

• Be explicit about what information you want
• Describe how the agent should find information
• Specify the desired output format
• Keep schemas small (1-5 root fields)
• Use enums in schemas for better accuracy

API Reference

Search Parameters

Contents Options

Response Fields

Pricing Notes

• Search: $0.005 per request (1-25 results), $0.025 (26-100 results)
• Deep Search: $0.015 per request (1-25 results), $0.075 (26-100 results)
• Contents: $0.001 per page for text/highlights/summary
• Answer: Variable based on search and LLM usage
• Research: Variable usage-based (searches + pages read + reasoning tokens)