> For the complete documentation index, see [llms.txt](https://tailwindsdocs.innovativesol.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://tailwindsdocs.innovativesol.com/readme/chatflows/langchain/vector-stores/qdrant.md).

# Qdrant

## Prerequisites

A Qdrant cloud instance.

To get a Qdrant cloud instance:

1. Head to the Clusters section of the [Cloud Dashboard](https://cloud.qdrant.io/overview).
2. Select **Clusters** and then click **+ Create**.

<figure><img src="/files/U4b3Gu5xy2Hj3qzLZVHq" alt=""><figcaption></figcaption></figure>

3. Choose your cluster configurations and region.
4. Hit **Create** to provision your cluster.

## Setup

1. Get/Create your **API Key** from the **Data Access Control** section of the [Cloud Dashboard](https://cloud.qdrant.io/overview).
2. Add a new **Qdrant** node on canvas.
3. Create new Qdrant credential using the API Key

<figure><img src="/files/7DJaGAWuohVYHxNQgaOc" alt="" width="563"><figcaption></figcaption></figure>

4. Enter the required info into the **Qdrant** node:
   * Qdrant server URL
   * Collection name

<figure><img src="/files/sycaTUGEJsPJHbBGYUr5" alt="" width="239"><figcaption></figcaption></figure>

5. **Document** input can be connected with any node under [**Document Loader**](/readme/chatflows/langchain/document-loaders.md) category.
6. **Embeddings** input can be connected with any node under [**Embeddings**](/readme/chatflows/langchain/embeddings.md) category.

## Filtering

Let's say you have different documents upserted, each specified with a unique value under the metadata key `{source}`

<div align="left"><figure><img src="/files/tW8ysFk8ncaNegU1Q0Fg" alt="" width="563"><figcaption></figcaption></figure> <figure><img src="/files/faZ4BUdnPkBW6hfkPfww" alt="" width="563"><figcaption></figcaption></figure></div>

Then, you want to filter by it. Qdrant supports following [syntax](https://qdrant.tech/documentation/concepts/filtering/#nested-key) when it comes to filtering:

**UI**

<figure><img src="/files/eEeJYpwEqfjAOXnQelK0" alt="" width="338"><figcaption></figcaption></figure>

**API**

```json
"overrideConfig": {
    "qdrantFilter": {
        "should": [
            {
                "key": "metadata.source",
                "match": {
                    "value": "apple"
                }
            }
        ]
    }
}
```

## Resources

* [Qdrant documentation](https://qdrant.tech/documentation/)
* [LangChain JS Qdrant](https://js.langchain.com/docs/integrations/vectorstores/qdrant)
* [Qdrant Filter](https://qdrant.tech/documentation/concepts/filtering/#nested-key)