These examples assume that you have already followed the instructured to set up the Unstructured Ingest CLI and the Unstructured Ingest Python library.

​
Changing partition strategy for a PDF

Here’s how you can modify partition strategy for a PDF file, and select an alternative model to use with Unstructured API. The hi_res strategy supports different models, and the default is layout_v1.1.0.
CLI
unstructured-ingest \
  local \
    --input-path $LOCAL_FILE_INPUT_DIR \
    --output-dir $LOCAL_FILE_OUTPUT_DIR \
    --strategy hi_res \
    --hi-res-model-name layout_v1.1.0 \
    --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}"
Python
import os

from unstructured_ingest.pipeline.pipeline import Pipeline
from unstructured_ingest.interfaces import ProcessorConfig
from unstructured_ingest.processes.connectors.local import (
    LocalIndexerConfig,
    LocalDownloaderConfig,
    LocalConnectionConfig,
    LocalUploaderConfig
)
from unstructured_ingest.processes.partitioner import PartitionerConfig

if __name__ == "__main__":
    Pipeline.from_configs(
        context=ProcessorConfig(),
        indexer_config=LocalIndexerConfig(input_path=os.getenv("LOCAL_FILE_INPUT_DIR")),
        downloader_config=LocalDownloaderConfig(),
        source_connection_config=LocalConnectionConfig(),
        partitioner_config=PartitionerConfig(
            strategy="hi_res",
            hi_res_model_name="layout_v1.0.0",
            partition_by_api=True,
            api_key=os.getenv("UNSTRUCTURED_API_KEY"),
            partition_endpoint=os.getenv("UNSTRUCTURED_API_URL"),
            additional_partition_args={
                "split_pdf_page": True,
                "split_pdf_allow_failed": True,
                "split_pdf_concurrency_level": 15
            }
        ),
        uploader_config=LocalUploaderConfig(output_dir=os.getenv("LOCAL_FILE_OUTPUT_DIR"))
    ).run()
If you have a local deployment of the Unstructured API, you can use other supported models, such as yolox.

​
Specifying the language of a document for better OCR results

For better OCR results, you can specify what languages your document is in using the languages parameter. View the list of available languages.
CLI
unstructured-ingest \
  local \
    --input-path $LOCAL_FILE_INPUT_DIR \
    --output-dir $LOCAL_FILE_OUTPUT_DIR \
    --strategy ocr_only \
    --ocr-languages kor \
    --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}"
Python
import os

from unstructured_ingest.pipeline.pipeline import Pipeline
from unstructured_ingest.interfaces import ProcessorConfig
from unstructured_ingest.processes.connectors.local import (
    LocalIndexerConfig,
    LocalDownloaderConfig,
    LocalConnectionConfig,
    LocalUploaderConfig
)
from unstructured_ingest.processes.partitioner import PartitionerConfig

if __name__ == "__main__":
    Pipeline.from_configs(
        context=ProcessorConfig(),
        indexer_config=LocalIndexerConfig(input_path=os.getenv("LOCAL_FILE_INPUT_DIR")),
        downloader_config=LocalDownloaderConfig(),
        source_connection_config=LocalConnectionConfig(),
        partitioner_config=PartitionerConfig(
            strategy="ocr_only",
            ocr_languages=["kor"],
            partition_by_api=True,
            api_key=os.getenv("UNSTRUCTURED_API_KEY"),
            partition_endpoint=os.getenv("UNSTRUCTURED_API_URL"),
            additional_partition_args={
                "split_pdf_page": True,
                "split_pdf_allow_failed": True,
                "split_pdf_concurrency_level": 15
            }
        ),
        uploader_config=LocalUploaderConfig(output_dir=os.getenv("LOCAL_FILE_OUTPUT_DIR"))
    ).run()

​
Saving bounding box coordinates

When elements are extracted from PDFs or images, it may be useful to get their bounding boxes as well. Set the coordinates parameter to true to add this field to the elements in the response.
CLI
unstructured-ingest \
  local \
    --input-path $LOCAL_FILE_INPUT_DIR \
    --output-dir $LOCAL_FILE_OUTPUT_DIR \
    --partition-by-api \
    --api-key $UNSTRUCTURED_API_KEY \
    --partition-endpoint $UNSTRUCTURED_API_URL \
    --strategy hi_res \
    --additional-partition-args="{\"coordinates\":\"true\", \"split_pdf_page\":\"true\", \"split_pdf_allow_failed\":\"true\", \"split_pdf_concurrency_level\": 15}"
Python
import os

from unstructured_ingest.pipeline.pipeline import Pipeline
from unstructured_ingest.interfaces import ProcessorConfig
from unstructured_ingest.processes.connectors.local import (
    LocalIndexerConfig,
    LocalDownloaderConfig,
    LocalConnectionConfig,
    LocalUploaderConfig
)
from unstructured_ingest.processes.partitioner import PartitionerConfig

if __name__ == "__main__":
    Pipeline.from_configs(
        context=ProcessorConfig(),
        indexer_config=LocalIndexerConfig(input_path=os.getenv("LOCAL_FILE_INPUT_DIR")),
        downloader_config=LocalDownloaderConfig(),
        source_connection_config=LocalConnectionConfig(),
        partitioner_config=PartitionerConfig(
            partition_by_api=True,
            api_key=os.getenv("UNSTRUCTURED_API_KEY"),
            partition_endpoint=os.getenv("UNSTRUCTURED_API_URL"),
            strategy="hi_res",
            additional_partition_args={
                "coordinates": True,
                "split_pdf_page": True,
                "split_pdf_allow_failed": True,
                "split_pdf_concurrency_level": 15
            }
        ),
        uploader_config=LocalUploaderConfig(output_dir=os.getenv("LOCAL_FILE_OUTPUT_DIR"))
    ).run()

​
Returning unique element IDs

By default, the element ID is a SHA-256 hash of the element text. This is to ensure that the ID is deterministic. One downside is that the ID is not guaranteed to be unique. Different elements with the same text will have the same ID, and there could also be hash collisions. To use UUIDs in the output instead, set unique_element_ids=true. Note: this means that the element IDs will be random, so with every partition of the same file, you will get different IDs. This can be helpful if you’d like to use the IDs as a primary key in a database, for example.
CLI
unstructured-ingest \
  local \
    --input-path $LOCAL_FILE_INPUT_DIR \
    --output-dir $LOCAL_FILE_OUTPUT_DIR \
    --partition-by-api \
    --api-key $UNSTRUCTURED_API_KEY \
    --partition-endpoint $UNSTRUCTURED_API_URL \
    --strategy hi_res \
    --additional-partition-args="{\"unique_element_ids\":\"true\", \"split_pdf_page\":\"true\", \"split_pdf_allow_failed\":\"true\", \"split_pdf_concurrency_level\": 15}"
Python
import os

from unstructured_ingest.pipeline.pipeline import Pipeline
from unstructured_ingest.interfaces import ProcessorConfig
from unstructured_ingest.processes.connectors.local import (
    LocalIndexerConfig,
    LocalDownloaderConfig,
    LocalConnectionConfig,
    LocalUploaderConfig
)
from unstructured_ingest.processes.partitioner import PartitionerConfig

if __name__ == "__main__":
    Pipeline.from_configs(
        context=ProcessorConfig(),
        indexer_config=LocalIndexerConfig(input_path=os.getenv("LOCAL_FILE_INPUT_DIR")),
        downloader_config=LocalDownloaderConfig(),
        source_connection_config=LocalConnectionConfig(),
        partitioner_config=PartitionerConfig(
            partition_by_api=True,
            api_key=os.getenv("UNSTRUCTURED_API_KEY"),
            partition_endpoint=os.getenv("UNSTRUCTURED_API_URL"),
            strategy="hi_res",
            additional_partition_args={
                "unique_element_ids": True,
                "split_pdf_page": True,
                "split_pdf_allow_failed": True,
                "split_pdf_concurrency_level": 15
            }
        ),
        uploader_config=LocalUploaderConfig(output_dir=os.getenv("LOCAL_FILE_OUTPUT_DIR"))
    ).run()

​
Adding the chunking step after partitioning

You can combine partitioning and subsequent chunking in a single request by setting the chunking_strategy parameter. By default, the chunking_strategy is set to None, and no chunking is performed.
CLI
unstructured-ingest \
  local \
    --input-path $LOCAL_FILE_INPUT_DIR \
    --output-dir $LOCAL_FILE_OUTPUT_DIR \
    --chunking-strategy by_title \
    --chunk-max-characters 1024 \
    --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}"
Python
import os

from unstructured_ingest.pipeline.pipeline import Pipeline
from unstructured_ingest.interfaces import ProcessorConfig
from unstructured_ingest.processes.connectors.local import (
    LocalIndexerConfig,
    LocalDownloaderConfig,
    LocalConnectionConfig,
    LocalUploaderConfig
)
from unstructured_ingest.processes.partitioner import PartitionerConfig
from unstructured_ingest.processes.chunker import ChunkerConfig

if __name__ == "__main__":
    Pipeline.from_configs(
        context=ProcessorConfig(),
        indexer_config=LocalIndexerConfig(input_path=os.getenv("LOCAL_FILE_INPUT_DIR")),
        downloader_config=LocalDownloaderConfig(),
        source_connection_config=LocalConnectionConfig(),
        partitioner_config=PartitionerConfig(
            partition_by_api=True,
            api_key=os.getenv("UNSTRUCTURED_API_KEY"),
            partition_endpoint=os.getenv("UNSTRUCTURED_API_URL"),
            strategy="hi_res",
            additional_partition_args={
                "split_pdf_page": True,
                "split_pdf_allow_failed": True,
                "split_pdf_concurrency_level": 15
            }
        ),
        chunker_config=ChunkerConfig(
            chunking_strategy="by_title",
            chunk_max_characters=1024
        ),
        uploader_config=LocalUploaderConfig(output_dir=os.getenv("LOCAL_FILE_OUTPUT_DIR"))
    ).run()