Fast search - Andi AI Search API Docs

Fast search is the default mode. It returns results in approximately 1 second, making it suitable for real-time applications and high-volume workloads.

curl "https://search-api.andisearch.com/api/v1/search?q=latest+AI+news" \
  -H "x-api-key: YOUR_API_KEY"

import requests

response = requests.get(
    "https://search-api.andisearch.com/api/v1/search",
    params={"q": "latest AI news"},
    headers={"x-api-key": "YOUR_API_KEY"}
)

data = response.json()
for result in data["results"]:
    print(f"{result['title']} — {result['source']}")

const response = await fetch(
  "https://search-api.andisearch.com/api/v1/search?q=latest+AI+news",
  { headers: { "x-api-key": "YOUR_API_KEY" } }
);

const data = await response.json();
data.results.forEach(r => console.log(`${r.title} — ${r.source}`));

Fast search is the default — no depth parameter is needed. Setting depth=fast explicitly has the same effect.

When to use fast search

Real-time search in user-facing applications
High-volume automated queries
AI agents that need quick answers
Applications where latency matters more than exhaustive coverage

Example response

{
  "results_type": "news",
  "answer": "",
  "type": "news",
  "title": "latest AI news",
  "results": [
    {
      "title": "Latest AI News and Developments",
      "link": "https://example.com/ai-news",
      "desc": "A roundup of the latest developments in artificial intelligence...",
      "source": "example.com",
      "type": "news"
    }
  ],
  "metrics": {
    "query": "latest AI news",
    "intent": "LatestNewsIntent",
    "duration": 890,
    "results_returned": 10,
    "total_results_found": 50
  }
}

Parsing the response

data = response.json()

# Check what type of results came back
print(data["results_type"])  # e.g., "news", "search", "images"

# Access results
for result in data["results"]:
    print(result["title"], result["link"])

# Check performance
print(f"Returned {data['metrics']['results_returned']} results in {data['metrics']['duration']}ms")

Adding extracts and metadata

Get richer data from each result:

# Text extracts from result pages
curl "https://search-api.andisearch.com/api/v1/search?q=latest+AI+news&extracts=true" \
  -H "x-api-key: YOUR_API_KEY"

# Full metadata including content type and reader data
curl "https://search-api.andisearch.com/api/v1/search?q=latest+AI+news&metadata=full" \
  -H "x-api-key: YOUR_API_KEY"

# Markdown format for passing to LLMs
curl "https://search-api.andisearch.com/api/v1/search?q=latest+AI+news&format=context" \
  -H "x-api-key: YOUR_API_KEY"

metadata=full adds latency because it fetches additional data from each result page. Use metadata=basic (the default) unless you need contentType or reader data.

Fast search vs. deep search

	Fast search	Deep search
Response time	~1 second	~2–3 seconds
Spell correction	No	Yes
Topic coverage	Single angle	Multiple angles
Result quality	Good	Thorough

Start with fast search. Switch to deep search when you need results a quick search might miss, or when thoroughness matters more than speed.

Next steps

Deep search

Enhanced search with spell correction and more sources.

Query parameters

Full parameter reference.

Basic search example

Complete integration with error handling.

Response format

Understand the response structure.

​When to use fast search

​Example response

​Parsing the response

​Fast search vs. deep search

​Next steps

Deep search

Query parameters

Basic search example

Response format

When to use fast search

Example response

Parsing the response

Fast search vs. deep search

Next steps