Elasticsearch - Unstructured

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

Connect Elasticsearch 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.

For the Unstructured UI or the Unstructured API, only Elastic Cloud instances are supported.
For Unstructured Ingest, Elastic Cloud instances and self-manged Elasticsearch instances are supported.
For Elastic Cloud, you will need an Elastic Cloud service instance.
For self-managed Elasticsearch, you will need a self-managed Elasticsearch instance.

You will need the name of the index on the instance. See Create index and Get index. The Elasticsearch index that you use must have a schema that is compatible with the schema of the documents that Unstructured produces for you. 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. You can adapt the following index schema example for your own needs:

{
    "settings": {
        "index": {
            "knn": true,
            "knn.algo_param.ef_search": 100
        }
    },
    "mappings": {
        "properties": {
            "record_id": {
                "type": "text"
            },
            "element_id": {
                "type": "keyword"
            },
            "text": {
                "type": "text"
            },
            "embeddings": {
                "type": "dense_vector",
                "dims": 384,
                "index": true,
                "similarity": "cosine"
            },
            "metadata": {
                "type": "object",
                "properties": {
                    "parent_id": {
                        "type": "text"
                    },
                    "page_number": {
                        "type": "integer"
                    },
                    "is_continuation": {
                        "type": "boolean"
                    },
                    "orig_elements": {
                        "type": "text"
                    },
                    "partitioner_type": {
                        "type": "text"
                    }
                }
            }
        }
    }
}

See also:

For Elastic Cloud, you will need the Elastic Cloud service instance’s API key. If you are using Unstructured Ingest, you will also need the instance’s Cloud ID. To get these, see your Elasticsearch Service web console.
For self-managed Elasticsearch, you will need:
- The self-managed instance’s hostname and port number. See Networking.
- If you’re using basic authentication to the self-managed instance, the user’s name and password.
- If you’re using token-based authentication to the self-managed instance, the bearer token or API key for the instance. See Token-based authentication services and Create API key.
- If you’re using certificate authentication to the self-managed instance, the path to the Certificate Authority (CA) file on the instance, and the certificate fingerprint. See SSL certificate API and Where can I see my Certificate Fingerprint?.

The Elasticsearch connector dependencies:

CLI, Python

pip install "unstructured-ingest[elasticsearch]"

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

ELASTICSEARCH_HOST - The hostname and port number, defined as <hostname>:<port-number> and represented by --hosts (CLI) or hosts (Python).
ELASTICSEARCH_INDEX_NAME - The name of the search index, represented by --index-name (CLI) or index_name (Python).

If you’re using Elastic Cloud to connect to ElasticSearch:

ELASTIC_CLOUD_ID - The instance’s Cloud ID, represented by --cloud-id (CLI) or cloud_id (Python).
ELASTIC_CLOUD_API_KEY - The corresponding Cloud API key value, represented by --api-key-id (CLI) or api_key_id (Python).

If you’re using basic authentication to the instance:

ELASTICSEARCH_USERNAME - The user’s name, represented by --username (CLI) or username (Python).
ELASTICSEARCH_PASSWORD - The user’s password, represented by --password (CLI) or password (Python).

If you’re using token-based authentication to the instance instead:

ELASTICSEARCH_BEARER_TOKEN - The bearer token’s value, represented by --bearer-auth (CLI) or bearer_auth (Python).
ELASTIC_CLOUD_API_KEY_ID - The API key’s value, represented by --api-key (CLI) or api_key (Python).

If you’re using certificates:

ELASTICSEARCH_CA_CERTS - The path to the Certificate Authority (CA) file, represented by --ca-certs (CLI) or ca_certs (Python).
ELASTICSEARCH_SSL_ASSERT_FINGERPRINT - The certificate’s fingerprint, represented by --ssl-assert-fingerprint or ssl_assert_fingerprint (Python).

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 files locally instead, see the instructions at the end of this page.

#!/usr/bin/env bash

unstructured-ingest \
  elasticsearch \
    --metadata-exclude filename,file_directory,metadata.data_source.date_processed \
    --hosts $ELASTICSEARCH_HOST \
    --username $ELASTICSEARCH_USERNAME \
    --password $ELASTICSEARCH_PASSWORD \
    --index-name $ELASTICSEARCH_INDEX_NAME \
    --ca-certs $ELASTICSEARCH_CA_CERTS \
    --ssl-assert-fingerprint $ELASTICSEARCH_SSL_ASSERT_FINGERPRINT \
    --fields 'ethnicity, director, plot' \
    --output-dir $LOCAL_FILE_OUTPUT_DIR \
    --num-processes 2
    --partition-by-api \
    --api-key $UNSTRUCTURED_API_KEY \
    --partition-endpoint $UNSTRUCTURED_API_URL \
    --strategy hi_res

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