Weaviate - Unstructured

First time creating a connector? Read this first.

Send processed data from Unstructured to Weaviate.

Requirements

You will need:

For the Unstructured Pipelines or the Unstructured API: only Weaviate Cloud clusters are supported.
For Unstructured Ingest: Weaviate Cloud clusters, Weaviate installed locally, and Embedded Weaviate are supported.
For Weaviate installed locally, you will need the name of the target collection on the local instance.
For Embedded Weaviate, you will need the instance’s connection URL and the name of the target collection on the instance.
For Weaviate Cloud, you will need:
- A Weaviate database instance. The following information assumes that you have a Weaviate Cloud (WCD) account with a Weaviate database cluster in that account. Create a WCD account. Create a database cluster. For other database options, learn more.
- The URL and API key for the database cluster. Get the URL and API key.
- The name of the target collection in the database. Create a collection. An existing collection is not required. At runtime, the collection behavior is as follows: For the Unstructured Pipelines or the Unstructured API:
  - If an existing collection name is specified, and Unstructured generates embeddings, but the number of dimensions that are generated does not match the existing collection’s embedding settings, the run will fail. You must change your Unstructured embedding settings or your existing collection’s embedding settings to match, and try the run again.
  - If a collection name is not specified, Unstructured creates a new collection in your Weaviate cluster. If Unstructured generates embeddings, the new collection’s name will be U<short-workflow-id>_<short-embedding-model-name>_<number-of-dimensions>. If Unstructured does not generate embeddings, the new collection’s name will be U<short-workflow-id.
  For Unstructured Ingest:
  - If an existing collection name is specified, and Unstructured generates embeddings, but the number of dimensions that are generated does not match the existing collection’s embedding settings, the run will fail. You must change your Unstructured embedding settings or your existing collection’s embedding settings to match, and try the run again.
  - If a collection name is not specified, Unstructured creates a new collection in your Weaviate cluster. The new collection’s name will be Unstructuredautocreated.
  If Unstructured creates a new collection and generates embeddings, you will not see an embeddings property in tools such as the Weaviate Cloud Collections user interface. To view the generated embeddings, you can run a Weaviate GraphQL query such as the following. In this query, replace <collection-name> with the name of the new collection, and replace <property-name> with the name of each additional available property that you want to return results for, such as text, type, element_id, record_id, and so on. The embeddings will be returned in the vector property.
  { Get { <collection-name> { _additional { vector } <property-name> <property-name> } } }

If auto-schema is enabled in Weaviate (which it is by default), Weaviate can infer missing properties and add them to the collection definition at run time. However, it is a Weaviate best practice to manually define as much of the data schema in advance as possible, since manual definition gives you the most control. The minimum viable schema for Unstructured includes only the element_id and record_id properties. The text and type properties should also be included, but they are technically optional. If you are using Unstructured to generate embeddings, you must The following code example shows how to use the weaviate-client Python package to create a collection in a Weaviate Cloud database cluster with this minimum viable schema, and to specify that Unstructured will generate the embeddings for this collection. To connect to a locally hosted Weaviate instance instead, call weaviate.connect_to_local. To connect to Embedded Weaviate instead, call weaviate.connect_to_embedded.

import os
import weaviate
from weaviate.classes.init import Auth
import weaviate.classes.config as wvc

client = weaviate.connect_to_weaviate_cloud(
    cluster_url=os.getenv("WEAVIATE_URL"),
    auth_credentials=Auth.api_key(api_key=os.getenv("WEAVIATE_API_KEY")),
)

collection = client.collections.create(
    name="MyCollection",
    properties=[
        wvc.Property(name="element_id", data_type=wvc.DataType.UUID),
        wvc.Property(name="record_id", data_type=wvc.DataType.TEXT),
        wvc.Property(name="text", data_type=wvc.DataType.TEXT),
        wvc.Property(name="type", data_type=wvc.DataType.TEXT),
    ],
    vectorizer_config=None, # Unstructured will generate the embeddings instead of Weaviate.
)

client.close()

The record_id, element_id, and id fields are closely related, but each has a distinct purpose. For more information, see How connectors use record IDs, element IDs, and IDs.

For objects in the metadata field that Unstructured produces and that you want to store in a Weaviate collection, be sure to follow Unstructured’s metadata field naming convention. For example, if Unstructured produces a metadata field with the following child objects:

"metadata": {
  "is_extracted": "true",
  "coordinates": {
    "points": [
      [
        134.20055555555555,
        241.36027777777795
      ],
      [
        134.20055555555555,
        420.0269444444447
      ],
      [
        529.7005555555555,
        420.0269444444447
      ],
      [
        529.7005555555555,
        241.36027777777795
      ]
    ],
    "system": "PixelSpace",
    "layout_width": 1654,
    "layout_height": 2339
  },
  "filetype": "application/pdf",
  "languages": [
    "eng"
  ],
  "page_number": 1,
  "image_mime_type": "image/jpeg",
  "filename": "realestate.pdf",
  "data_source": {
    "url": "file:///home/etl/node/downloads/00000000-0000-0000-0000-000000000001/7458635f-realestate.pdf",
    "record_locator": {
      "protocol": "file",
      "remote_file_path": "file:///home/etl/node/downloads/00000000-0000-0000-0000-000000000001/7458635f-realestate.pdf"
    }
  },
  "entities": {
    "items": [
      {
        "entity": "HOME FOR FUTURE",
        "type": "ORGANIZATION"
      },
      {
        "entity": "221 Queen Street, Melbourne VIC 3000",
        "type": "LOCATION"
      }
    ],
    "relationships": [
      {
        "from": "HOME FOR FUTURE",
        "relationship": "based_in",
        "to": "221 Queen Street, Melbourne VIC 3000"
      }
    ]
  }
}

You could create corresponding properties in your collection’s schema by using the following property names and data types:

import os
import weaviate
from weaviate.classes.init import Auth
import weaviate.classes.config as wvc

client = weaviate.connect_to_weaviate_cloud(
    cluster_url=os.getenv("WEAVIATE_URL"),
    auth_credentials=Auth.api_key(api_key=os.getenv("WEAVIATE_API_KEY")),
)

collection = client.collections.create(
    name="MyCollection",
    properties=[
        wvc.Property(name="element_id", data_type=wvc.DataType.UUID),
        wvc.Property(name="record_id", data_type=wvc.DataType.TEXT),
        wvc.Property(name="text", data_type=wvc.DataType.TEXT),
        wvc.Property(name="type", data_type=wvc.DataType.TEXT),
        wvc.Property(
            name="metadata",
            data_type=wvc.DataType.OBJECT,
            nested_properties=[
                wvc.Property(name="is_extracted", data_type=wvc.DataType.TEXT),
                wvc.Property(
                    name="coordinates",
                    data_type=wvc.DataType.OBJECT,
                    nested_properties=[
                        wvc.Property(name="points", data_type=wvc.DataType.TEXT),
                        wvc.Property(name="system", data_type=wvc.DataType.TEXT),
                        wvc.Property(name="layout_width", data_type=wvc.DataType.NUMBER),
                        wvc.Property(name="layout_height", data_type=wvc.DataType.NUMBER),
                    ],
                ),
                wvc.Property(name="filetype", data_type=wvc.DataType.TEXT),
                wvc.Property(name="languages", data_type=wvc.DataType.TEXT_ARRAY),
                wvc.Property(name="page_number", data_type=wvc.DataType.TEXT),
                wvc.Property(name="image_mime_type", data_type=wvc.DataType.TEXT),
                wvc.Property(name="filename", data_type=wvc.DataType.TEXT),
                wvc.Property(
                    name="data_source",
                    data_type=wvc.DataType.OBJECT,
                    nested_properties=[
                        wvc.Property(name="url", data_type=wvc.DataType.TEXT),
                        wvc.Property(name="record_locator", data_type=wvc.DataType.TEXT),
                    ],
                ),
                wvc.Property(
                    name="entities", 
                    data_type=wvc.DataType.OBJECT,
                    nested_properties=[
                        wvc.Property(
                            name="items", 
                            data_type=wvc.DataType.OBJECT_ARRAY,
                            nested_properties=[
                                wvc.Property(name="entity", data_type=wvc.DataType.TEXT),
                                wvc.Property(name="type", data_type=wvc.DataType.TEXT),
                            ],
                        ),
                        wvc.Property(
                            name="relationships", 
                            data_type=wvc.DataType.OBJECT_ARRAY,
                            nested_properties=[
                                wvc.Property(name="to", data_type=wvc.DataType.TEXT),
                                wvc.Property(name="from", data_type=wvc.DataType.TEXT),
                                wvc.Property(name="relationship", data_type=wvc.DataType.TEXT),
                            ],
                        ),
                    ],
                ),
            ],
        ),
    ],
    vectorizer_config=None, # Unstructured will generate the embeddings instead of Weaviate.
)

client.close()

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. See also:

Examples

To create a Weaviate destination connector, see the following examples. For more information on working with destination connectors using the Unstructured API, see Destination endpoints.

import os

from unstructured_client import UnstructuredClient
from unstructured_client.models.operations import CreateDestinationRequest
from unstructured_client.models.shared import CreateDestinationConnector

with UnstructuredClient(api_key_auth=os.getenv("UNSTRUCTURED_API_KEY")) as client:
    response = client.destinations.create_destination(
        request=CreateDestinationRequest(
            create_destination_connector=CreateDestinationConnector(
                name="<name>",
                type="weaviate-cloud",
                config={
                    "cluster_url": "<host-url>",
                    "collection": "<class-name>",
                    "api_key": "<api-key>"
                }
            )
        )
    )

    print(response.destination_connector_information)

Configuration settings

Replace the preceding placeholders as follows:

name

string

required

A unique name for this connector.

host_url

string

required

The URL of the Weaviate database cluster.

class_name

string

The name of the target collection within the cluster. If no value is provided, see the beginning of this article for the behavior at run time.

api_key

string

required

The API key provided by Weaviate to access the cluster.

​Requirements

​Examples

​Configuration settings

Requirements

Examples

Configuration settings