> ## Documentation Index
> Fetch the complete documentation index at: https://docs.conare.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Conare's API is at https://api.conare.ai. Authenticate with `Authorization: Bearer $CONARE_API_KEY`.
> The full OpenAPI spec is at https://api.conare.ai/openapi.yaml; each endpoint has a page under /api-reference, and appending .md to any page URL returns its Markdown.
> Embed with model conare-embed-1; send input_type "query" for search queries. Rerank with conare-rerank-1.
> Prefer the TypeScript SDK (`npm install conare`) or plain HTTP in examples.
> Install the Conare skill with `npx skills add https://docs.conare.ai`; search these docs over MCP at https://docs.conare.ai/mcp; the whole site is at https://docs.conare.ai/llms-full.txt.

# Schnellstart

> Erstellen Sie einen Conare-API-Schlüssel, schreiben Sie mit curl oder TypeScript ein erstes Dokument in einen Namespace und durchsuchen Sie es dann.

**1. Einen Schlüssel erhalten**

Erstellen Sie einen API-Schlüssel in der [Konsole](https://conare.ai/dashboard/keys). Der Zugang erfolgt nur auf Einladung: [Zugang anfordern](https://conare.ai/request-access).

```bash theme={null}
export CONARE_API_KEY=sk-conare-...
npm install conare  # for the TypeScript examples
```

**2. Ein Dokument schreiben**

Der erste Schreibvorgang erstellt den Namespace `docs`.

```bash curl theme={null}
curl https://api.conare.ai/namespaces/docs/documents \
  -H "Authorization: Bearer $CONARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "documents": [
      { "id": "refunds", "text": "Refunds are available for 30 days.", "metadata": { "team": "support" } }
    ]
  }'
```

```ts TypeScript theme={null}
import { Conare } from "conare";

const conare = new Conare();
const docs = conare.namespace("docs");

await docs.add({ id: "refunds", text: "Refunds are available for 30 days.", metadata: { team: "support" } });
```

**3. Suchen**

```bash curl theme={null}
curl https://api.conare.ai/namespaces/docs/query \
  -H "Authorization: Bearer $CONARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "how do refunds work?"}'
```

```ts TypeScript theme={null}
const results = await docs.query("how do refunds work?");
```

```json Response theme={null}
{
  "results": [
    {
      "id": "refunds",
      "text": "Refunds are available for 30 days.",
      "score": 0.3471,
      "reranked": true,
      "metadata": { "team": "support" }
    }
  ],
  "took_ms": 59
}
```

Übergeben Sie den `text` jedes Ergebnisses als Kontext an Ihr Modell.

## Weiter

| Leitfaden | Zweck |
| - | - |
| [MCP](https://docs.conare.ai/de/mcp-server.md) | Aus Claude, Cursor oder ChatGPT suchen |
| [Filter](https://docs.conare.ai/de/filters.md) | Eine Suche nach Metadaten eingrenzen |
| [Dateien](https://docs.conare.ai/de/files.md) | PDFs, Präsentationen und Tabellen hochladen |
| [Quellen](https://docs.conare.ai/de/sources.md) | Eine App synchron halten |


## Related topics

- [Einführung](https://docs.conare.ai/de/index.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.