Skip to main content
If you’re new to Unstructured, read this note first.Before you can create a destination connector, you must first sign in to your Unstructured account:After you sign in, the Unstructured user interface (UI) appears, which you use to create your destination connector.After you create the destination connector, add it along with a source connector to a workflow. Then run the worklow as a job. To learn how, try out the hands-on UI quickstart or watch the 4-minute video tutorial.You can also create destination connectors with the Unstructured API. Learn how.If you need help, email Unstructured Support at support@unstructured.io.You are now ready to start creating a destination connector! Keep reading to learn how.
Send processed data from Unstructured to Milvus. The requirements are as follows. The following video shows how to fulfill the minimum set of requirements for Milvus cloud-based instances, demonstrating Milvus on IBM watsonx.data:
  • For Zilliz Cloud, you will need:
    • A Zilliz Cloud account.
    • A Zilliz Cloud cluster.
    • The URI of the cluster, also known as the cluster’s public endpoint, which takes a format such as https://<cluster-id>.<cluster-type>.<cloud-provider>-<region>.cloud.zilliz.com. To get this public endpoint value, do the following:
      1. After you sign in to your Zilliz Cloud account, on the sidebar, in the list of available projects, select the project that contains the cluster.
      2. On the sidebar, click Clusters.
      3. Click the tile for the cluster.
      4. On the Cluster Details tab, on the Connect subtab, copy the Public Endpoint value.
    • The username and password to access the cluster, as follows:
      1. After you sign in to your Zilliz Cloud account, on the sidebar, in the list of available projects, select the project that contains the cluster.
      2. On the sidebar, click Clusters.
      3. Click the tile for the cluster.
      4. On the Users tab, copy the name of the user.
      5. Next to the user’s name, under Actions, click the ellipsis (three dots) icon, and then click Reset Password.
      6. Enter a new password for the user, and then click Confirm. Copy this new password.
    • The name of the database in the instance.
    • The name of the collection in the database. The collection must have a defined schema before Unstructured can write to the collection. The minimum viable schema for Unstructured contains only the fields element_id, embeddings, record_id, and text, as follows:
      Field NameField TypeMax LengthDimension
      element_id (primary key field)VARCHAR200—
      embeddings (vector field)FLOAT_VECTOR—384
      record_idVARCHAR200—
      textVARCHAR65536—
      In the Create Index area for the collection, next to Vector Fields, click Edit Index. Make sure that for the embeddings field, the Field Type is set to FLOAT_VECTOR and the Metric Type is set to Cosine.
      The number of dimensions for the embeddings field must match the number of dimensions for the embedding model that you plan to use.
  • For Milvus on IBM watsonx.data, you will need:
  • For Milvus local, you will need:
All Milvus instances require the target collection to have a defined schema before Unstructured can write to the collection. The minimum viable schema for Unstructured contains only the fields element_id, embeddings, record_id, and text, as follows. This example code demonstrates the use of the Python SDK for Milvus to create a collection with this schema, targeting Milvus on IBM watsonx.data. For the MilvusClient arguments to connect to other types of Milvus deployments, see your Milvus provider’s documentation:
Python
import os

from pymilvus import (
    MilvusClient,
    FieldSchema,
    DataType,
    CollectionSchema
)

DATABASE_NAME   = "default"
COLLECTION_NAME = "my_collection"

client = MilvusClient(
    uri="https://" +
        os.getenv("MILVUS_USER") + 
        ":" + 
        os.getenv("MILVUS_PASSWORD") + 
        "@" + 
        os.getenv("MILVUS_GRPC_HOST") + 
        ":" + 
        os.getenv("MILVUS_GRPC_PORT"),
    db_name=DATABASE_NAME
)

primary_key_field = FieldSchema(
    name="element_id",
    dtype=DataType.VARCHAR,
    is_primary=True,
    max_length=200
)

# IMPORTANT: The number of dimensions for the "embeddings" field
# must match the number of dimensions for the embedding model 
# that you plan to use.
embeddings_field = FieldSchema(
    name="embeddings",
    dtype=DataType.FLOAT_VECTOR,
    dim=384
)

record_id_field = FieldSchema(
    name="record_id",
    dtype=DataType.VARCHAR,
    max_length=200
)

text_field = FieldSchema(
    name="text",
    dtype=DataType.VARCHAR,
    max_length=65535
)

schema = CollectionSchema(
    fields=[
        primary_key_field, 
        embeddings_field,
        record_id_field, 
        text_field
    ]
)

client.create_collection(
    collection_name=COLLECTION_NAME",
    schema=schema,
    using=DATABASE_NAME
)

index_params = client.prepare_index_params()

index_params.add_index(
    field_name="embeddings",
    metric_type="COSINE",
    index_type="IVF_FLAT",
    params={"nlist": 1024}
)

client.create_index(
    collection_name=COLLECTION_NAME,
    index_params=index_params
)

client.load_collection(
    collection_name=COLLECTION_NAME
)
Other approaches, such as creating collections instantly or setting nullable and default fields, have not been fully evaluated by Unstructured and might produce unexpected results. Unstructured cannot provide a schema that is guaranteed to work in all circumstances. This is because these schemas will vary based on your source files’ types; how you want Unstructured to partition, chunk, and generate embeddings; any custom post-processing code that you run; and other factors. To create the destination connector:
  1. On the sidebar, click Connectors.
  2. Click Destinations.
  3. Cick New or Create Connector.
  4. Give the connector some unique Name.
  5. In the Provider area, click Milvus.
  6. Click Continue.
  7. Follow the on-screen instructions to fill in the fields as described later on this page.
  8. Click Save and Test.
Fill in the following fields for Milvus on IBM watsonx.data:
  • Name (required): A unique name for this connector.
  • GRPC Host (required): The GRPC host name for the Milvus instance.
  • GRPC Port: The GRPC port number for the instance.
  • DB Name: The name of the database in the instance. The default is default if not otherwise specified.
  • Collection Name (required): The name of the collection in the database.
  • Username: The username to access the Milvus instance. The default is ibmlhapikey if not otherwise specified.
  • API Key (required): The IBM Cloud user API key.
Fill in the following fields for Milvus on Zilliz Cloud:
  • Name (required): A unique name for this connector.
  • URI (required): The URI of the Milvus instance, for example: https://12345.serverless.gcp-us-west1.cloud.zilliz.com.
  • DB Name: The name of the database in the instance. The default is default if not otherwise specified.
  • Collection Name (required): The name of the collection in the database.
  • Username (required): The username to access the Milvus instance.
  • Password (required): The password corresponding to the username to access the instance.
Fill in the following fields for other Milvus deployments:
  • Name (required): A unique name for this connector.
  • URI (required): The URI of the Milvus instance, for example: https://12345.serverless.gcp-us-west1.cloud.zilliz.com.
  • DB Name: The name of the database in the instance. The default is default if not otherwise specified.
  • Collection Name (required): The name of the collection in the database.
  • Username (required): The username to access the Milvus instance.
  • Password (required): The password corresponding to the username to access the instance.
⌘I