Kafka

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

Connect Kafka 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 Kafka cluster in Confluent Cloud. (Create a cluster.)

  The following video shows how to set up a Kafka cluster in Confluent Cloud:

• The hostname and port number of the bootstrap Kafka cluster to connect to..

• The name of the topic to read messages from or write messages to on the cluster. Create a topic. Access available topics.

• For authentication, an API key and secret.

The Kafka connector dependencies:

CLI, Python

pip install "unstructured-ingest[kafka]"

You might also need to install additional dependencies, depending on your needs. Learn more.

The following environment variables:

• KAFKA_BOOTSTRAP_SERVER - The hostname of the bootstrap Kafka cluster to connect to, represented by --bootstrap-server (CLI) or bootstrap_server (Python).
• KAFKA_PORT - The port number of the cluster, represented by --port (CLI) or port (Python).
• KAFKA_TOPIC - The unique name of the topic to read messages from and write messages to on the cluster, represented by --topic (CLI) or topic (Python).

If you use Kafka API keys and secrets for authentication:

• KAFKA_API_KEY - The Kafka API key value, represented by --kafka-api-key (CLI) or kafka_api_key (Python).
• KAFKA_SECRET - The secret value for the Kafka API key, represented by --secret (CLI) or secret (Python).

Additional settings include:

• --confluent (CLI) or confluent (Python): True to indicate that the cluster is running Confluent Kafka.
• --num-messages-to-consume (CLI) or num_messages_to_consume (Python): The maximum number of messages to get from the topic. The default is 1 if not otherwise specified.
• --timeout (CLI) or timeout (Python): The maximum amount of time to wait for the response of a request to the topic, expressed in seconds. The default is 1.0 if not otherwise specified.
• --group-id (CLI) or group_id (Python): The ID of the consumer group, if any, that is associated with the target Kafka cluster. (A consumer group is a way to allow a pool of consumers to divide the consumption of data over topics and partitions.) The default is default_group_id if not otherwise specified.

Now call the Unstructured CLI or Python. 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.

CLI

#!/usr/bin/env bash

# Chunking and embedding are optional.

unstructured-ingest \
  kafka \
    --bootstrap-server $KAFKA_BOOTSTRAP_SERVER \ 
    --port $KAFKA_PORT \
    --topic $KAFKA_TOPIC \
    --kafka-api-key $KAFKA_API_KEY \
    --secret $KAFKA_API_KEY \
    --confluent true \
    --batch-size 100 \
    --num-messages-to-consume 1 \
    --timeout 1.0 \
    --output-dir $LOCAL_FILE_OUTPUT_DIR \
    --chunking-strategy by_title \
    --embedding-provider huggingface \
    --partition-by-api \
    --api-key $UNSTRUCTURED_API_KEY \
    --partition-endpoint $UNSTRUCTURED_API_URL \
    --strategy hi_res \
    --additional-partition-args="{\"split_pdf_page\":\"true\", \"split_pdf_allow_failed\":\"true\", \"split_pdf_concurrency_level\": 15}"

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 [e-mail].