> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.privategpt.dev/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.privategpt.dev/_mcp/server.

# Vector Store

> Configure the vector store used for document retrieval.

PrivateGPT uses [Qdrant](https://qdrant.tech/) as the default vector store. By default it runs in local disk mode — no separate Qdrant server needed.

> **Warning**
>
> Local disk mode is not recommended for production. Use a remote Qdrant server for any persistent or multi-instance deployment.

```yaml
qdrant:
  path: local_data/qdrant   # relative to PGPT_HOME (~/.local/share/private-gpt by default)
```

---

## Remote Qdrant

To connect to an existing Qdrant server instead of the local disk instance:

```yaml
qdrant:
  url: http://localhost:6333
  api_key: your-api-key   # only needed for Qdrant Cloud
```

---

## Embedding dimensions

If you switch embedding models, the vector dimensions change. Re-ingest your documents after changing the model and update `embed_dim` to match:

```yaml
vectorstore:
  embed_dim: 1024   # must match the output dimension of your embedding model
```

Run `make wipe` before re-ingesting to avoid a dimension mismatch error.