Skip to main content

​
Capabilities

Answer is the fastest way to get a written, source-attributed answer from Tako. It runs the same retrieval as Search — Tako’s structured knowledge cards and the live web — and synthesizes the best answer from both into one response, returned in a single synchronous call you can use inline.

One fast, synchronous call

A single request returns a finished answer — no dispatching, polling, or retrieval to orchestrate. Fast enough to drop inline into a chat, an assistant, or an agentic loop.

Built on Tako Search

Answer grounds on the same retrieval as Search — structured knowledge cards plus the live web — then writes the answer over them, so you get prose and the results that produced it in one call.

Ready to show, with receipts

Every answer ships with the Tako cards and web results that back it — named sources and methodology — so it’s citable, auditable, and safe to drop straight into a user-facing surface.
Choosing between Tako’s surfaces (see the full comparison):
SurfaceWhat it’s for
AnswerA written, source-attributed answer in one call.
SearchFast, parallel retrieval of structured data and cards, no synthesized answer.
Answer AgentDeep research synthesizing a cited answer backed by visualizations.
Search AgentMulti-step research returning schema-defined structured data and cards.

​
Example

curl -X POST https://tako.com/api/v1/answer \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "How have Nvidia and AMD headcount changed since 2013?"
  }'

Example Result

Answer: “Nvidia has grown to about 36,000 full-time employees as of the end of 2024 — up roughly 309% from about 8,800 in 2013. AMD reached about 28,000 over the same period, giving Nvidia both the larger workforce and the faster growth of the two.”

​
Use cases

Return one synthesized, source-attributed answer in a single call.
response = client.answer(SearchRequest(query="What is the weather in San Francisco?"))
print(response.answer)
Re-run the same query to refresh prose that stays grounded in live data.
response = client.answer(SearchRequest(query="Latest US CPI, year over year"))
print(response.answer)
Use the backing cards’ sources and methodology to cite the answer.
response = client.answer(SearchRequest(query="Nvidia revenue growth"))
for card in response.cards or []:
    print(card.title, card.sources)
Limit the answer to Tako’s authoritative sources, skipping the web.
response = client.answer(SearchRequest(query="Global military spending in 2024", sources={"data": {}}))
Want the data behind a card as CSV? Pass a card’s URL to Contents to download its underlying data — or inline it here with include_contents.
By consuming the answer and its grounding information, you can keep your content always up to date and accurate.