This page was recently updated. What do you think about it? Let us know!.
Connect SingleStore to your preprocessing pipeline, and use the Unstructured Ingest CLI or the Unstructured Ingest Python library to batch process all your documents and store structured outputs locally on your filesystem. The requirements are as follows.
  • A SingleStore deployment, database, and table. Learn how.
  • The hostname for the SingleStore deployment.
  • The port for the host.
  • The username for the deployment.
  • The password for the user.
  • The name of the database in the deployment.
  • The name of the table in the database.
To get the values for the hostname, port, username, and password:
  1. In your SingleStore account’s dashboard sidebar, click Deployments.
  2. From the drop-down list at the top of the Deployments page, select your deployment.
  3. On the Overview tab, in the Compute area, in the Connect drop-down list for your deployment, select Your App.
  4. If a Create User dialog box appears, note the User name and Password values.
  5. In the Connect to Workspace pane’s Your App tab, note the string in the following format:
<user-name>:<password>@<host>:<port>
  • <user-name> is the username.
  • <password> is the user’s password.
  • <host> is the workspace’s hostname.
  • <post> is the host’s port.
To get the values for the database and table names:
  1. In your SingleStore dashboard’s sidebar, click Deployments.
  2. From the drop-down list at the top of the Deployments page, select your deployment.
  3. On the Databases tab, note Name of your database.
  4. Click the database and, on the Tables tab, note the name of your table.
The SingleStore connector dependencies:
CLI, Python
pip install "unstructured-ingest[singlestore]"
You might also need to install additional dependencies, depending on your needs. Learn more. These environment variables:
  • SINGLESTORE_HOST - The hostname for the SingleStore deployment, represented by --host (CLI) or host (Python).
  • SINGLESTORE_PORT - The port for the host, represented by --port (CLI) or port (Python).
  • SINGLESTORE_USER - The username for the deployment, represented by --user (CLI) or user (Python).
  • SINGLESTORE_PASSWORD - The password for the user, represented by --password (CLI) or password (Python).
  • SINGLESTORE_DB - The name of the database in the deployment, represented by --database (CLI) or database (Python).
  • SINGLESTORE_TABLE - The name of the table in the database, represented by --table-name (CLI) or table_name (Python).
Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The destination connector can be any of the ones supported. This example uses the local destination connector. This example sends data to Unstructured for processing by default. To process data locally instead, see the instructions at the end of this page. 
#!/usr/bin/env bash

# Chunking and embedding are optional.

unstructured-ingest \
  singlestore \
    --host $SINGLESTORE_HOST \
    --port $SINGLESTORE_PORT \
    --user $SINGLESTORE_USER \
    --password $SINGLESTORE_PASSWORD \
    --database $SINGLESTORE_DB \
    --table-name $SINGLESTORE_TABLE \
    --id-column id \
    --batch-size 100 \
    --output-dir $LOCAL_FILE_OUTPUT_DIR \
    --partition-by-api \
    --api-key $UNSTRUCTURED_API_KEY \
    --partition-endpoint $UNSTRUCTURED_API_URL \
    --strategy fast \
    --chunking-strategy by_title \
    --embedding-provider huggingface
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.