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

# Chat with RAG

> Ground an agent's answers in your own documents using an Agntix Knowledge Store.

A **Knowledge Store** is a vector-indexed collection of your documents (PDFs, DOCX, CSV, or scraped websites). Once you attach a store to an agent, every user message triggers a retrieval pass — the most relevant chunks are pulled into the prompt and the agent answers from them, with citations. This guide walks you through creating a store, uploading content, and wiring it to an agent — entirely from the dashboard.

## Prerequisites

* A signed-in dashboard account at [app.agntix.ai](https://app.agntix.ai).
* An existing agent (see [Build your first agent](/guides/build-your-first-agent)). You'll attach the store to it in Step 4.
* The files you want to index (PDF, DOCX, or CSV), or a list of public URLs to scrape.

## Step 1: Open the Knowledge Store page

From the left navigation, click **Knowledge Store**. You'll land on a two-column layout — list of stores on the left, details for the selected store on the right.

<Frame caption="The Knowledge Store page. Click the + button (top of the left panel) to create your first store.">
  <img src="https://mintcdn.com/agntix/R90GFr3LneMDSJLq/images/guides/chat-with-rag/01-knowledge-store-empty.png?fit=max&auto=format&n=R90GFr3LneMDSJLq&q=85&s=a11cbc1a1d3223b6cde987da77a2a01a" alt="Empty Knowledge Store page" width="2244" height="1646" data-path="images/guides/chat-with-rag/01-knowledge-store-empty.png" />
</Frame>

Click the **+** button at the top of the left panel.

## Step 2: Create the store

A modal opens with a single required field — **Name**. Give the store a descriptive name (8–50 characters). Examples: *Help Center*, *Product Docs FY26*, *Onboarding playbook*.

<Frame caption="Create Knowledge Store modal — name only. Embeddings, chunking, and the vector index are configured automatically.">
  <img src="https://mintcdn.com/agntix/R90GFr3LneMDSJLq/images/guides/chat-with-rag/02-create-store-modal.png?fit=max&auto=format&n=R90GFr3LneMDSJLq&q=85&s=1b65294463de05a07473c6127c93a8c8" alt="Create store modal" width="2244" height="1646" data-path="images/guides/chat-with-rag/02-create-store-modal.png" />
</Frame>

<Tip>
  Keep stores **narrow**. Retrieval quality is much higher with one store per topic than one giant store containing everything your company has ever written. You can attach different stores to different agents.
</Tip>

Click **Create**. The new store appears in the left panel; select it to open the detail view.

## Step 3: Upload documents

In the store detail view, click the **Add** dropdown in the top right. Two sources are supported:

* **Upload file** — PDF, DOCX, CSV (multiple files allowed in one upload).
* **Add website** — scrape a single URL or a list of URLs.

<Frame caption="Add dropdown — pick file upload or website scrape.">
  <img src="https://mintcdn.com/agntix/R90GFr3LneMDSJLq/images/guides/chat-with-rag/03-upload-document-dropdown.png?fit=max&auto=format&n=R90GFr3LneMDSJLq&q=85&s=ff2ebd712029c926e002f5311e28daad" alt="Add dropdown" width="2244" height="1646" data-path="images/guides/chat-with-rag/03-upload-document-dropdown.png" />
</Frame>

Select **Upload file** and pick one or more documents. Each file is queued and processed asynchronously:

1. **Uploading** — bytes transfer to the gateway.
2. **Processing** — Agntix chunks the document (\~1k tokens per chunk), embeds it (Cohere by default), and writes vectors to Qdrant.
3. **Ready** — the document is searchable.

<Frame caption="Upload progress. Status badges flip from Uploading → Processing → Ready.">
  <img src="https://mintlify.s3.us-west-1.amazonaws.com/agntix/images/guides/chat-with-rag/04-upload-progress.png" alt="Upload in progress" />
</Frame>

Wait for every document to reach **Ready** before testing. Processing time scales with document size (typical: 1–2 seconds per page).

<Frame caption="Documents ready for retrieval.">
  <img src="https://mintcdn.com/agntix/R90GFr3LneMDSJLq/images/guides/chat-with-rag/05-document-ready.png?fit=max&auto=format&n=R90GFr3LneMDSJLq&q=85&s=06e189387269b640b8832cd880a7c1c0" alt="Documents ready" width="1086" height="560" data-path="images/guides/chat-with-rag/05-document-ready.png" />
</Frame>

## Step 4: Attach the store to an agent

<Warning>
  Attaching a knowledge store **from the dashboard is not available in the current release** — the agent's in-dashboard **Knowledge** tab is temporarily disabled while it's being finalized. For now, attach the store over the API as shown below; the dashboard flow will return in a future release.
</Warning>

Copy the store's ID from the Knowledge Store detail view (or from the create-store API response), then `PATCH` your agent to enable RAG and point it at the store:

```bash theme={null}
curl -X PATCH https://api.agntix.ai/v1/chat/agents/$AGENT_ID \
  -H "x-api-key: $AGNTIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "config": { "ragEnabled": true, "knowledgeStoreId": "ks_…" } }'
```

Retrieval behaviour — search type, **Top K** / **Top N**, **Agentic RAG**, and **Rerank** — defaults to sensible values. To tune it, set the matching `config` fields; see the **Agents** section of the [API Reference](/api-reference/agents/update) for the exact field names and ranges.

## Step 5: Test with a RAG-grounded question

Click **Test Agent** in the page header. Ask a question whose answer is in your uploaded documents — something specific enough that a generic LLM wouldn't know it.

<Frame caption="The agent answers from the knowledge store. Source snippets are shown inline (or in the response payload for API users).">
  <img src="https://mintlify.s3.us-west-1.amazonaws.com/agntix/images/guides/chat-with-rag/07-test-rag-response.png" alt="Test RAG response" />
</Frame>

Compare against the same question with the store *detached* — the difference should be obvious. If the agent ignores the store, see [Troubleshooting](#troubleshooting) below.

## Verify it works

* Every uploaded document shows **Ready** in the store detail view.
* The agent's `config` shows `ragEnabled: true` with your `knowledgeStoreId` (check via `GET /v1/chat/agents/{id}`).
* Test Agent answers contain facts that are only in your documents.
* The session log (Analytics tab or `/logs-history`) shows the retrieved chunks per message.

## Best practices

<CardGroup cols={2}>
  <Card title="One topic per store" icon="layer-group">
    Narrow stores out-perform giant stores. Split by product, region, or audience.
  </Card>

  <Card title="Refresh on a schedule" icon="rotate">
    Re-upload changed documents. Old chunks are replaced atomically, no downtime.
  </Card>

  <Card title="Always rerank" icon="wand-magic-sparkles">
    Cohere reranking adds \~150 ms but cuts hallucinations dramatically.
  </Card>

  <Card title="Cite sources in the prompt" icon="quote-left">
    Tell the agent to cite chunk titles. Builds user trust and makes wrong answers easy to debug.
  </Card>
</CardGroup>

## Troubleshooting

| Symptom                       | Likely cause                                                   | Fix                                                                                                 |
| ----------------------------- | -------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- |
| Agent ignores the store       | Document still **Processing**, or RAG not enabled on the agent | Wait for **Ready**; confirm the agent's `config.ragEnabled` is `true` and `knowledgeStoreId` is set |
| Wrong document retrieved      | **Top K** too low, or two stores overlap                       | Raise Top K to 8–10, or split overlapping content                                                   |
| Slow responses                | Rerank + Agentic RAG both on                                   | Turn off Agentic RAG first; keep rerank                                                             |
| "Quota exceeded" upload error | Org embedding quota                                            | Contact support; quotas are per-plan                                                                |

## API alternative

Same flow over HTTP — useful for CI / bulk ingestion / nightly refreshes:

```bash theme={null}
curl -X POST https://api.agntix.ai/v1/chat/knowledge-store \
  -H "x-api-key: $AGNTIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "name": "Help Center", "description": "Customer-facing help center articles" }'

curl -X PATCH https://api.agntix.ai/v1/chat/agents/$AGENT_ID \
  -H "x-api-key: $AGNTIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "config": { "ragEnabled": true, "knowledgeStoreId": "ks_…" } }'
```

For the full upload, document-listing, and chunk-level endpoints, see the auto-generated **Knowledge Store** section under [API Reference](/api-reference/introduction).