> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tako.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Data Graph
export const AgentPromptCard = ({title, description, children}) =>
{title}
{description}
{children}
;
export const CodingAgentCTA = ({description, href}) =>
{description} Building with a coding agent?{" "}
Give your agent the full reference →
;
Give your coding agent the tako-graph-agent skill} description={<>Teaches your agent the graph-grounded workflow — resolve names to nodes, read what data exists, compose pinned searches, report gaps honestly. Its main use is building agentic applications that integrate Tako Search; it's equally handy for checking what Tako covers or debugging searches that return vague cards. One command installs it:}>
````bash theme={null}
mkdir -p .claude/skills/tako-graph-agent && \
curl -fsSL https://docs.tako.com/skills/tako-graph-agent.md \
| sed -n '/^```/,/^```/p' | sed '1d;$d' \
> .claude/skills/tako-graph-agent/SKILL.md && \
curl -fsSL https://docs.tako.com/skills/tako-graph-agent/resolve-example.md \
| sed -n '/^```/,/^```/p' | sed '1d;$d' \
> .claude/skills/tako-graph-agent/resolve-example.ts
````
## When to use the Data Graph
The Data Graph is Tako's index of **what its curated data actually covers** — every entity (companies, countries, teams, commodities…) and metric (revenue, CPI, win percentage…) as a node, connected by real relationships. Query it **before** [Search](/documentation/integrating-tako/search/overview) so your agent composes queries that hit, pins the exact nodes it resolved, and honestly reports what's missing. Reach for it when:
Resolve a name ("Nvidia", "inflation") to real graph nodes and read what data exists for them — instead of spending searches on guesses.
Pin resolved node ids into Search via `sources.data.node_ids` for guaranteed retrieval candidacy — or add `strict: true` to return only cards matching your nodes.
Competitors, subsidiaries, industry peers, cohort members — read them off named graph edges like `rel:competes_with` and `members`. A database read replaces the LLM-recalled lists that produce hallucinated comparisons.
When the graph can't ground part of a question, your agent can say so — *"Tako has X and Y, but not Z."* An empty result is an honest answer, not a failure.
No general-purpose AI-search API — Exa, Perplexity, Tavily, Brave — exposes a typed knowledge-graph traversal your agent can query before it searches. The closest analogues are the symbol-search endpoints of financial data APIs; the Data Graph extends that pattern to Tako's whole curated index, with relationships.
## The three endpoints
| Endpoint | What it does |
| --------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **[Graph Search](/api-reference/graph-search)** `GET /beta/graph/search` | Resolve a name to entity or metric nodes — "nvidia" → the company node, with its id, aliases, and description. |
| **[Graph Related](/api-reference/graph-related)** `GET /beta/graph/related` | Explore what a node connects to — its metrics, its entities, named relations (`rel:competes_with`, `rel:in_industry`…), and cohort membership (`part_of`, `members`). |
| **[Graph Node](/api-reference/graph-node)** `GET /beta/graph/node/{id}` | Confirm what a node id refers to. Occasional use — mostly for verifying ids you got from a card. |
## Free to call, easy to explore
Graph calls use the same `X-API-Key` header as every Tako endpoint and consume **no credits** — they're bounded only by rate limits (180/minute, 10,000/day). Discovery is free; spend your credits on the searches it grounds.
Browse the Data Graph visually with your Tako account — search any entity or metric, walk its relationships, and see exactly what your agent will see before you write a line of code.
**The Data Graph is in beta, and it's a guide — not a guarantee.** A node's related metrics come from the datasets that *cover* that entity, so a listed metric is strong evidence, not proof of that exact combination. And the graph is not the whole index: stock prices, market quotes, rankings, and overviews often live outside it, yet [Search](/documentation/integrating-tako/search/overview) has them. Confirm coverage with a search; treat a thin graph result for a well-covered entity as a cue to search anyway, not to declare a gap.
## Example — discover, then search grounded
```bash theme={null}
curl "https://tako.com/api/beta/graph/search?q=nvidia&types=entity" \
-H "X-API-Key: $TAKO_API_KEY"
```
Returns nodes with `id`, `name`, `aliases`, `subtype` — pick the company node and keep its `id`.
```bash theme={null}
curl "https://tako.com/api/beta/graph/related?node_id=$NODE_ID&relation=metrics&q=revenue" \
-H "X-API-Key: $TAKO_API_KEY"
```
Metrics matching "revenue", ranked by popularity and match strength — the combinations Tako actually covers.
```bash theme={null}
curl -X POST https://tako.com/api/v3/search \
-H "X-API-Key: $TAKO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "Nvidia quarterly revenue",
"sources": { "data": { "node_ids": ["'$NODE_ID'"] } }
}'
```
Pinned nodes get guaranteed retrieval candidacy plus a strong boost; organic results are unaffected.
## Next steps
* **[For your coding agent →](/documentation/integrating-tako/data-graph/for-coding-agent)** — the complete build reference: every parameter, label boosts, relation kinds, response shapes, and the common mistakes.
* **Building an agentic app?** Install the `tako-graph-agent` skill (card at the top of this page) — it packages the whole discover → ground → report-gaps loop for your coding agent.