MotherDuck - Unstructured

This page was recently updated. What do you think about it? Let us know!.

Batch process all your records to store structured outputs in a MotherDuck account. The requirements are as follows.

A MotherDuck account.
A MotherDuck access token for the account.
A database in the account.
- Create a database.
- List available databases.
You can run commands to manage MotherDuck databases, schemas, tables, and more in the MotherDuck UI or for example by connecting to MotherDuck with the DuckDB CLI.
A schema in the target database.
- Create a schema.
- You can list available schemas and their parent catalogs by running the following command in the MotherDuck UI or the DuckDB CLI:
  SELECT * FROM information_schema.schemata;
The MotherDuck connector uses the default schema name of main if not otherwise specified.

A table in the target schema.

Create a table.
You can list available tables in a schema by running the following commands in the MotherDuck UI or the DuckDB CLI, replacing the target catalog and schema names:
```
USE <catalog_name>.<schema_name>;
SHOW TABLES;
```

The MotherDuck connector uses the default table name of elements if not otherwise specified. For maximum compatibility, Unstructured recommends the following table schema:

CREATE TABLE elements (
    id VARCHAR,
    element_id VARCHAR,
    text TEXT,
    embeddings FLOAT[],
    type VARCHAR,
    system VARCHAR,
    layout_width DECIMAL,
    layout_height DECIMAL,
    points TEXT,
    url TEXT,
    version VARCHAR,
    date_created INTEGER,
    date_modified INTEGER,
    date_processed DOUBLE,
    permissions_data TEXT,
    record_locator TEXT,
    category_depth INTEGER,
    parent_id VARCHAR,
    attached_filename VARCHAR,
    filetype VARCHAR,
    last_modified TIMESTAMP,
    file_directory VARCHAR,
    filename VARCHAR,
    languages VARCHAR[],
    page_number VARCHAR,
    links TEXT,
    page_name VARCHAR,
    link_urls VARCHAR[],
    link_texts VARCHAR[],
    sent_from VARCHAR[],
    sent_to VARCHAR[],
    subject VARCHAR,
    section VARCHAR,
    header_footer_type VARCHAR,
    emphasized_text_contents VARCHAR[],
    emphasized_text_tags VARCHAR[],
    text_as_html TEXT,
    regex_metadata TEXT,
    detection_class_prob DECIMAL,
    partitioner_type VARCHAR
);

You can list the schema of a table by running the following commands in the MotherDuck UI or the DuckDB CLI, replacing the target catalog, schema, and table names:

USE <catalog_name>.<schema_name>;
DESCRIBE TABLE <table_name>;

The MotherDuck connector dependencies:

CLI, Python

pip install "unstructured-ingest[duckdb]"

You might also need to install additional dependencies, depending on your needs. Learn more. The following environment variables:

MOTHERDUCK_MD_TOKEN - The access token for the target MotherDuck account, represented by --md-token (CLI) or md_token (Python).
MOTHERDUCK_DATABASE - The name of the target database in the account, represented by --database (CLI) or database (Python).
MOTHERDUCK_DB_SCHEMA - The name of the target schema in the database, represented by --db-schema (CLI) or db_schema (Python).
MOTHERDUCK_TABLE - The name of the target table in the schema, represented by --table (CLI) or table (Python).

Now call the Unstructured CLI or Python. The source connector can be any of the ones supported. This example uses the local source connector. This example sends files to Unstructured for processing by default. To process files locally instead, see the instructions at the end of this page.

#!/usr/bin/env bash

# Chunking and embedding are optional.

unstructured-ingest \
  local \
    --input-path $LOCAL_FILE_INPUT_DIR \
    --chunking-strategy by_title \
    --embedding-provider huggingface \
    --partition-by-api \
    --api-key $UNSTRUCTURED_API_KEY \
    --partition-endpoint $UNSTRUCTURED_API_URL \
    --additional-partition-args="{\"split_pdf_page\":\"true\", \"split_pdf_allow_failed\":\"true\", \"split_pdf_concurrency_level\": 15}" \
  motherduck \
    --md-token $MOTHERDUCK_MD_TOKEN \
    --database $MOTHERDUCK_DATABASE \
    --db-schema $MOTHERDUCK_DB_SCHEMA \
    --table $MOTHERDUCK_TABLE

For the Unstructured Ingest CLI and the Unstructured Ingest Python library, you can use the --partition-by-api option (CLI) or partition_by_api (Python) parameter to specify where files are processed:

To do local file processing, omit --partition-by-api (CLI) or partition_by_api (Python), or explicitly specify partition_by_api=False (Python). Local file processing does not use an Unstructured API key or API URL, so you can also omit the following, if they appear:
- --api-key $UNSTRUCTURED_API_KEY (CLI) or api_key=os.getenv("UNSTRUCTURED_API_KEY") (Python)
- --partition-endpoint $UNSTRUCTURED_API_URL (CLI) or partition_endpoint=os.getenv("UNSTRUCTURED_API_URL") (Python)
- The environment variables UNSTRUCTURED_API_KEY and UNSTRUCTURED_API_URL
To send files to the Unstructured Partition Endpoint for processing, specify --partition-by-api (CLI) or partition_by_api=True (Python). Unstructured also requires an Unstructured API key and API URL, by adding the following:
- --api-key $UNSTRUCTURED_API_KEY (CLI) or api_key=os.getenv("UNSTRUCTURED_API_KEY") (Python)
- --partition-endpoint $UNSTRUCTURED_API_URL (CLI) or partition_endpoint=os.getenv("UNSTRUCTURED_API_URL") (Python)
- The environment variables UNSTRUCTURED_API_KEY and UNSTRUCTURED_API_URL, representing your API key and API URL, respectively.
You must specify the API URL only if you are not using the default API URL for Unstructured Ingest, for example, if you are using a self-hosted instance of the Unstructured API.The default API URL for Unstructured Ingest is https://api.unstructuredapp.io/general/v0/general, which is the API URL for the Unstructured Partition Endpoint.If you do not have an API key, get one now.If the Unstructured API is self-hosted, the process for generating Unstructured API keys, and the Unstructured API URL that you use, are different. For details, contact Unstructured Sales at sales@unstructured.io.

Ingestion