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

# Quickstart

> Connect a source, generate its search config, and serve it to your audience

Raily Search Rail turns a data source into a search endpoint that your audience's AI agents can call from Claude, ChatGPT, or your own app. The whole flow runs across the top of **Search Rail**, in three stages: **Your corpus → Search Rail → Your audience**. Here it is end to end.

<Steps>
  <Step title="Connect your source">
    In the sidebar, open **Search Rail** (under **Rails**), then click **Connect source**. Pick where your data lives. Raily connects to vector stores (Qdrant, Pinecone, Weaviate, Milvus, pgvector, Oracle), cloud storage, and CRMs like Salesforce.

    See [Connect a vector store](/integrations/vector-store/overview) for the per-provider details.

    <Frame caption="Pick where your data lives">
      <img src="https://mintcdn.com/railyai/XX1nxXkekI9EWYGS/images/quickstart/choose_integration.png?fit=max&auto=format&n=XX1nxXkekI9EWYGS&q=85&s=a32941722189495905959cc82356b18f" alt="Connect a data source" width="2550" height="1256" data-path="images/quickstart/choose_integration.png" />
    </Frame>
  </Step>

  <Step title="Pick collections and an embedding model">
    Name the source and confirm its credentials show **Verified**. Click **Fetch Collections**, toggle on each collection you want to search, and choose an embedding model. Raily only offers models that match how your data was embedded, so queries are embedded the same way as your corpus. Click **Create Integration**.

    <Frame caption="Choose the collections to search">
      <img src="https://mintcdn.com/railyai/XX1nxXkekI9EWYGS/images/quickstart/qdrant1.png?fit=max&auto=format&n=XX1nxXkekI9EWYGS&q=85&s=4df80c53edfa2929835632049544162e" alt="Select collections and an embedding model" width="2548" height="1264" data-path="images/quickstart/qdrant1.png" />
    </Frame>
  </Step>

  <Step title="Let Raily build the search config">
    Raily profiles the collection and generates its search config for you. When it finishes, the collection shows **Ready** and the config is saved as **v1 · latest**. You can open **Edit** to tune it, or **History** to see past versions, anytime.

    <Frame caption="Raily profiles the collection and generates its config">
      <img src="https://mintcdn.com/railyai/XX1nxXkekI9EWYGS/images/quickstart/progress.png?fit=max&auto=format&n=XX1nxXkekI9EWYGS&q=85&s=286fe8e6105c397b6735ccd01097b0d8" alt="Profiling the collection and generating its config" width="2543" height="1263" data-path="images/quickstart/progress.png" />
    </Frame>
  </Step>

  <Step title="Point an endpoint at it and go live">
    Under **Searched by**, click **add endpoint**. You have two choices:

    * **Point an existing endpoint here** (for example **Point Raily MCP Server here**). This moves the endpoint onto this collection.
    * **Create a new endpoint** when this collection needs its own. See [AI Endpoints](/concepts/ai-endpoints) for details.

    Either way, the collection goes **live** and starts serving your audience through Claude, ChatGPT, or your app.

    <Frame caption="Point an endpoint at the collection">
      <img src="https://mintcdn.com/railyai/XX1nxXkekI9EWYGS/images/quickstart/qdrant2_endpoint.png?fit=max&auto=format&n=XX1nxXkekI9EWYGS&q=85&s=e7957775e18478f10bddb504e8f77df5" alt="Point an endpoint at the collection" width="2553" height="652" data-path="images/quickstart/qdrant2_endpoint.png" />
    </Frame>

    Once it's wired, the collection reads **live** and shows the endpoint that searches it.

    <Frame caption="The collection is live and serving your audience">
      <img src="https://mintcdn.com/railyai/XX1nxXkekI9EWYGS/images/quickstart/test.png?fit=max&auto=format&n=XX1nxXkekI9EWYGS&q=85&s=15f55f8df832a3f86e54dd99affcfe15" alt="The collection is live, searched by your endpoint" width="2579" height="762" data-path="images/quickstart/test.png" />
    </Frame>

    See [AI Endpoints](/concepts/ai-endpoints) for more on endpoints and who can reach them.
  </Step>

  <Step title="Test your endpoint">
    Click **Test your endpoint** to preview exactly what your audience's agents see. Ask a question in plain language. Raily searches your collection and answers with links back to the source. This page is an admin preview. Your audience never sees it. They ask from inside Claude, ChatGPT, or your app.

    <Frame caption="Preview what your audience sees">
      <img src="https://mintcdn.com/railyai/XX1nxXkekI9EWYGS/images/quickstart/chat.png?fit=max&auto=format&n=XX1nxXkekI9EWYGS&q=85&s=4a27a96364d39fa66c9628735f680fde" alt="Test your endpoint" width="2555" height="1261" data-path="images/quickstart/chat.png" />
    </Frame>
  </Step>
</Steps>

## Connect your source to AI clients

Your endpoint is live. Now point an AI client at it so people can search your data from the tools they already use.

<CardGroup cols={2}>
  <Card title="Connect to Claude" icon="comment" href="/connect/claude">
    Add your endpoint to Claude as a custom connector.
  </Card>

  <Card title="Connect to ChatGPT" icon="comments" href="/connect/chatgpt">
    Add your endpoint to ChatGPT as an app.
  </Card>
</CardGroup>