Skip to main content
POST
/
v1
/
agent
/
search
/
runs
Dispatch a search agent run
curl --request POST \
  --url https://tako.com/api/v1/agent/search/runs \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "query": "<string>",
  "thread_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "effort": "medium",
  "source_indexes": [],
  "cards": true,
  "output_schema": {},
  "locale": "en-US",
  "timezone": "<string>",
  "output_settings": {
    "image_dark_mode": true
  }
}
'
import requests

url = "https://tako.com/api/v1/agent/search/runs"

payload = {
    "query": "<string>",
    "thread_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "effort": "medium",
    "source_indexes": [],
    "cards": True,
    "output_schema": {},
    "locale": "en-US",
    "timezone": "<string>",
    "output_settings": { "image_dark_mode": True }
}
headers = {
    "X-API-Key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)
const options = {
  method: 'POST',
  headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    query: '<string>',
    thread_id: '3c90c3cc-0d44-4b50-8888-8dd25736052a',
    effort: 'medium',
    source_indexes: [],
    cards: true,
    output_schema: {},
    locale: 'en-US',
    timezone: '<string>',
    output_settings: {image_dark_mode: true}
  })
};

fetch('https://tako.com/api/v1/agent/search/runs', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));
<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://tako.com/api/v1/agent/search/runs",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'query' => '<string>',
    'thread_id' => '3c90c3cc-0d44-4b50-8888-8dd25736052a',
    'effort' => 'medium',
    'source_indexes' => [
        
    ],
    'cards' => true,
    'output_schema' => [
        
    ],
    'locale' => 'en-US',
    'timezone' => '<string>',
    'output_settings' => [
        'image_dark_mode' => true
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "X-API-Key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://tako.com/api/v1/agent/search/runs"

	payload := strings.NewReader("{\n  \"query\": \"<string>\",\n  \"thread_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n  \"effort\": \"medium\",\n  \"source_indexes\": [],\n  \"cards\": true,\n  \"output_schema\": {},\n  \"locale\": \"en-US\",\n  \"timezone\": \"<string>\",\n  \"output_settings\": {\n    \"image_dark_mode\": true\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("X-API-Key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}
HttpResponse<String> response = Unirest.post("https://tako.com/api/v1/agent/search/runs")
  .header("X-API-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"query\": \"<string>\",\n  \"thread_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n  \"effort\": \"medium\",\n  \"source_indexes\": [],\n  \"cards\": true,\n  \"output_schema\": {},\n  \"locale\": \"en-US\",\n  \"timezone\": \"<string>\",\n  \"output_settings\": {\n    \"image_dark_mode\": true\n  }\n}")
  .asString();
require 'uri'
require 'net/http'

url = URI("https://tako.com/api/v1/agent/search/runs")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"query\": \"<string>\",\n  \"thread_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n  \"effort\": \"medium\",\n  \"source_indexes\": [],\n  \"cards\": true,\n  \"output_schema\": {},\n  \"locale\": \"en-US\",\n  \"timezone\": \"<string>\",\n  \"output_settings\": {\n    \"image_dark_mode\": true\n  }\n}"

response = http.request(request)
puts response.read_body
{
  "run_id": "<string>",
  "created_at": "<string>",
  "object": "agent.search.run",
  "thread_id": "<string>",
  "completed_at": "<string>",
  "result": {
    "answer": "<string>",
    "cards": [
      {
        "card_id": "<string>",
        "title": "<string>",
        "description": "<string>",
        "semantic_description": "<string>",
        "webpage_url": "<string>",
        "image_url": "<string>",
        "embed_url": "<string>",
        "sources": [
          {
            "source_name": "S&P Global",
            "source_description": "<string>",
            "url": "https://xignite.com",
            "source_text": "<string>"
          }
        ],
        "methodologies": [
          {
            "methodology_name": "Where the Data Comes From - S&P Global",
            "methodology_description": "The financial metrics are collected from S&P Global, where information is sourced from original regulatory filings, press releases, and subsequent restatements. Data points, including over 5,000 financial, supplemental, segment, ratio, and industry-specific items, are standardized across over 180,000 companies to ensure consistency and comparability across different reporting formats. This comprehensive and methodical process enables robust historical analysis and back-testing by seamlessly integrating diverse financial datasets while preserving the granularity of the original reports."
          }
        ],
        "source_indexes": [],
        "card_type": "<string>",
        "content": {
          "cost": 0,
          "data": "<string>",
          "records": [
            {}
          ],
          "dataset": {
            "columns": [
              {
                "name": "<string>"
              }
            ],
            "rows": [
              [
                "<string>"
              ]
            ],
            "total_rows": 123,
            "truncated": true,
            "ref": "<string>",
            "sources": [
              {
                "name": "<string>",
                "index": "data"
              }
            ],
            "provenance": "query"
          },
          "url": "<string>",
          "expires_at": "<string>",
          "total_rows": 123,
          "truncated": false,
          "export_pricing": {
            "baseline_usd": 123,
            "row_cpm_usd": 123,
            "free_rows": 123,
            "max_rows_ceiling": 123
          }
        },
        "relevance_score": 123,
        "nodes": [
          {
            "id": "<string>",
            "name": "<string>",
            "description": "<string>"
          }
        ]
      }
    ],
    "citations": [
      {
        "index": 123,
        "title": "<string>",
        "url": "<string>",
        "source_name": "<string>",
        "excerpt": "<string>",
        "publish_date": "<string>",
        "content": {
          "cost": 0,
          "data": "<string>",
          "records": [
            {}
          ],
          "dataset": {
            "columns": [
              {
                "name": "<string>"
              }
            ],
            "rows": [
              [
                "<string>"
              ]
            ],
            "total_rows": 123,
            "truncated": true,
            "ref": "<string>",
            "sources": [
              {
                "name": "<string>",
                "index": "data"
              }
            ],
            "provenance": "query"
          },
          "url": "<string>",
          "expires_at": "<string>",
          "total_rows": 123,
          "truncated": false,
          "export_pricing": {
            "baseline_usd": 123,
            "row_cpm_usd": 123,
            "free_rows": 123,
            "max_rows_ceiling": 123
          }
        }
      }
    ],
    "metadata": {
      "citations": [
        {
          "index": 123,
          "title": "<string>",
          "url": "<string>",
          "source_name": "<string>",
          "excerpt": "<string>",
          "publish_date": "<string>",
          "content": {
            "cost": 0,
            "data": "<string>",
            "records": [
              {}
            ],
            "dataset": {
              "columns": [
                {
                  "name": "<string>"
                }
              ],
              "rows": [
                [
                  "<string>"
                ]
              ],
              "total_rows": 123,
              "truncated": true,
              "ref": "<string>",
              "sources": [
                {
                  "name": "<string>",
                  "index": "data"
                }
              ],
              "provenance": "query"
            },
            "url": "<string>",
            "expires_at": "<string>",
            "total_rows": 123,
            "truncated": false,
            "export_pricing": {
              "baseline_usd": 123,
              "row_cpm_usd": 123,
              "free_rows": 123,
              "max_rows_ceiling": 123
            }
          }
        }
      ],
      "definitions": [
        {
          "term": "<string>",
          "definition": "<string>",
          "source_ref": 123
        }
      ],
      "assumptions": [
        {
          "title": "<string>",
          "description": "<string>",
          "category": "<string>",
          "source_ref": 123
        }
      ],
      "methodology": [
        {
          "title": "<string>",
          "description": "<string>"
        }
      ]
    },
    "structured_output": {},
    "structured_output_citations": {},
    "unfilled_fields": [
      "<string>"
    ],
    "structured_output_error": {
      "code": "<string>",
      "message": "<string>"
    },
    "request_id": "<string>"
  },
  "error": {
    "code": "<string>",
    "message": "<string>"
  },
  "usage": {
    "total_cost_usd": 123,
    "compute": {
      "cost_usd": 123
    },
    "data": {
      "cost_usd": 123,
      "datasets": 123
    }
  },
  "request": {
    "query": "<string>",
    "thread_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "effort": "medium",
    "source_indexes": [],
    "cards": true,
    "output_schema": {},
    "locale": "en-US",
    "timezone": "<string>",
    "output_settings": {
      "image_dark_mode": true
    }
  }
}
{
  "code": "<string>",
  "message": "<string>"
}
{
  "code": "<string>",
  "message": "<string>"
}
{
  "code": "<string>",
  "message": "<string>"
}
{
  "code": "<string>",
  "message": "<string>"
}
{
  "code": "<string>",
  "message": "<string>"
}
{
  "code": "<string>",
  "message": "<string>"
}
The Search Agent researches a natural-language question across Tako’s knowledge and the live web, then returns schema-defined structured data (structured_output) plus visualization cards and a cited answer. Use it for questions that need real retrieval work — resolving a cohort, ranking or filtering a set, multi-hop aggregation. See the Search Agent guide for examples, structured outputs, streaming, threads, and sources.

​
Notes

  • To authenticate, send your Tako API key in the X-API-Key header. Store it as an environment variable rather than hardcoding it.
  • The agent is asynchronous: this endpoint returns 202 with a SearchAgentRun whose status is queued. Poll Poll a Search Agent run until status is completed or failed.
  • To stream progress live instead of polling, send Accept: text/event-stream. The response is then a Server-Sent Events stream of SearchAgentStreamEnvelope events. See the coding-agent reference.

​
Structured output

Pass an output_schema (JSON Schema) to get machine-usable JSON in result.structured_output. Mark a property with "x-tako-dataset": true to request a dataset slot, filled with exact retrieved rows. Supported subset: object/array/string/number/integer/boolean, enum, required, description. Caps: 16 KB, depth 5, 64 properties, 4 dataset slots — violations return 400 output_schema_invalid.

​
Choosing sources

source_indexes is optional and defaults to ["data", "web"] — both. Pass it only to restrict: ["data"] (curated knowledge graph only) or ["web"] (open web only). The legacy value "tako" is a synonym for "data".

​
Continuing a thread

Pass the thread_id from a prior run to ask a follow-up in the same conversation. Omit it to start a new thread. A thread is pinned to the Search Agent and to one set of source_indexes.

Authorizations

​
X-API-Key
string
header
required

Body

application/json

Request body for POST /v1/agent/search/runs.

​
query
string
required

Natural-language data-retrieval request for the search agent.

Example:

"S&P 500 semiconductor companies' 2024 revenue and YoY growth"

​
thread_id
string<uuid> | null

Existing thread to continue (follow-up). Omit to start a new thread.

​
effort
enum<string>
default:medium

Search-agent effort. Only 'medium' is currently supported.

Available options:
medium
​
source_indexes
enum<string>[]

Which sources the agent may use: 'data' (curated knowledge) and/or 'web' (open-web search). Defaults to ['data', 'web']. The legacy value 'tako' is accepted as a synonym for 'data'.

Available options:
data,
web
Examples:
["data"]
["web"]
["data", "web"]
​
cards
boolean
default:true

Whether the agent may build visualization cards. Default true and permissive: true means the agent MAY build cards, not that it must (a completed run with no cards is legitimate). false suppresses card building entirely.

​
output_schema
Output Schema · object | null

JSON Schema for structured output. Synthesized fields are written by the agent; dataset slots (marked with x-tako-dataset: true) are filled with exact retrieved rows as a TakoDataset. Supported subset: object/array/string/number/integer/boolean types, enum, required, description; caps: 16KB, depth 5, 64 properties, 4 dataset slots. Violations return 400 output_schema_invalid.

​
locale
string
default:en-US

BCP-47 locale. Drives the language of the agent's answer and the locale used when rendering card preview images. Defaults to en-US.

​
timezone
string | null

IANA timezone (e.g. 'America/New_York') used to render dates/times in card preview images. Does not affect the returned data.

​
output_settings
AgentOutputSettings · object | null

Settings controlling the response/rendering.

Response

Run dispatched. With Accept: application/json, poll GET /v1/agent/search/runs/{run_id} for status. With Accept: text/event-stream, the response is an SSE stream of SearchAgentStreamEnvelope events terminating at stream_done; if the stream ends without an agent_result event, poll GET /v1/agent/search/runs/{run_id} for terminal status.

The search-agent run resource returned by dispatch (202) and poll (GET).

​
run_id
string
required
​
status
enum<string>
required
Available options:
queued,
running,
completed,
failed
​
created_at
string
required
​
object
string
default:agent.search.run
Allowed value: "agent.search.run"
​
thread_id
string | null
​
completed_at
string | null
​
result
SearchAgentResult · object | null

Final search-agent output. answer is markdown prose with [n] citation markers; cards reuse the sibling TakoCard; citations is the unified top-level registry (data + web, S1 §5.2) — there is no web_results field; metadata carries definitions/assumptions/methodology (citations lifted out). structured_output_* fields carry the caller-shaped output_schema result (S3 §5.1) — present iff the request supplied output_schema; see each field's description for the exact presence matrix.

​
error
ErrorObject · object | null
​
usage
Usage · object | null

Cost-plus usage for one metered request. total_cost_usd is always present (the total quoted charge). compute / data are the additive breakdown and appear only where they apply. See module docstring for the quote-vs-drawdown caveat and the total == compute + data invariant.

​
request
SearchAgentRunRequest · object | null

Request body for POST /v1/agent/search/runs.