Skip to main content
Destinations are target systems where enriched metadata and document data can be exported. While Data Connectors bring documents into the platform, Destinations push enriched data out to vector databases, document management systems, and databases for downstream applications.

Supported Destinations

Qdrant

Vector database for AI applications and semantic search.

PostgreSQL

Relational database with vector support for hybrid search.

Azure SQL

Enterprise-grade SQL database in the Azure cloud.

SharePoint

Enrich original documents with metadata columns in Microsoft 365.

Configuration Details

Destination TypeDescriptionKey ConfigurationIdeal Use Case
QdrantVector database for AI applicationsCollection name, URL, API KeySemantic search, RAG pipelines
PostgreSQLRelational database with vector supportHost, Database, Collection, CredentialsStructured analytics, hybrid search
Azure SQLMicrosoft cloud databaseServer, Database, Table, CredentialsEnterprise data warehouses
SharePointMicrosoft 365 document managementClient ID/Secret, Tenant ID, Site NameEnriching original documents with metadata columns

Export Options

OptionDescriptionValues
Export LevelWhat data granularity to exportfile (document-level), chunk (segment-level), both
Export TagsSpecific metadata tags to includeList of tag names, or empty for all
Export NodesInclude vector embeddingstrue / false
Export MetadataInclude extracted metadatatrue / false
Metadata FormatHow metadata is storedcolumn_store (separate columns), json_store (single JSON column)
Export Processing:
  • Small Exports (< 100 files): Processed synchronously with immediate results
  • Large Exports (≥ 100 files): Processed in the background with progress tracking via tracker_id

How Destinations Work

1

Create a Destination

Configure the target system with the required credentials.
2

Select Export Options

Choose what data to export (file-level, chunk-level, specific tags).
3

Choose Metadata Format

Decide between column store (separate columns) or JSON store (single JSON column).
4

Run Export

The platform sends enriched data to your destination system.

Python SDK

from unstructured import UnstructuredClient

client = UnstructuredClient(
    username="your-username",
    password="your-password",
)

# Create a Qdrant destination
destination = client.destination.create(
    destination_name="my-vector-db",
    destination_body={
        "vector_db_type": "qdrant",
        "url": "https://your-cluster.qdrant.io",
        "api_key": "YOUR_QDRANT_API_KEY",
        "collection_name": "documents",
    },
)
print(f"Created destination: {destination.destination_id}")

API Reference