Build WorkflowsIntegrationsLangChainVector StoresQdrant

Qdrant

🚀

Enhanced

Direct integration with Langfuse tracing

Prerequisites

A locally running instance of Qdrant or a Qdrant cloud instance.

To get a Qdrant cloud instance:

  1. Head to the Clusters section of the Cloud Dashboard.
  2. Select Clusters and then click + Create.
  1. Choose your cluster configurations and region.
  2. Hit Create to provision your cluster.

Setup

  1. Get/Create your API Key from the Data Access Control section of the Cloud Dashboard.
  2. Add a new Qdrant node on canvas.
  3. Create new Qdrant credential using the API Key
  1. Enter the required info into the Qdrant node:
    • Qdrant server URL
    • Collection name
  1. Document input can be connected with any node under Document Loader category.
  2. Embeddings input can be connected with any node under Embeddings category.

Filtering

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

Then, you want to filter by it. Qdrant supports following syntax when it comes to filtering:

UI

API

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

Resources

PostgresRedis