Couchbase - Unstructured

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

Couchbase is a Distributed NoSQL Cloud Database. Couchbase embraces AI with coding assistance for developers, and vector search for their applications. Batch process all your records to store structured outputs in a Couchbase database. The requirements are as follows.

For the Unstructured UI or the Unstructured API, only Couchbase Capella clusters are supported.
For Unstructured Ingest, Couchbase Capella clusters and local Couchbase server deployments are supported.

For Couchbase Capella, you will need:

A Couchbase Capella account.
A Couchbase Capella cluster.
A bucket, scope, and collection on the cluster.
The cluster’s public connection string.
The cluster access name (username) and secret (password).
Incoming IP address allowance for the cluster. To get Unstructured’s IP address ranges, go to https://assets.p6m.u10d.net/publicitems/ip-prefixes.json and allow all of the ip_prefix fields’ values that are listed.
These IP address ranges are subject to change. You can always find the latest ones in the preceding file.

For a local Couchbase server, you will need:

Installation of a local Couchbase server.
Connection details to the local Couchbase server.

To learn more about how to set up a Couchbase cluster and play with data, refer to this tutorial. The Couchbase DB connector dependencies:

CLI, Python

pip install "unstructured-ingest[couchbase]"

You might also need to install additional dependencies, depending on your needs. Learn more. These environment variables are required for the Couchbase Connector:

CB_CONN_STR - The Connection String for the Couchbase server, represented by --connection-string (CLI) or connection_string (Python).
CB_USERNAME - The username for the Couchbase server, represented by --username (CLI) or username (Python).
CB_PASSWORD - The password for the Couchbase server, represented by --password (CLI) or password (Python).
CB_BUCKET - The name of the bucket in the Couchbase server, represented by --bucket (CLI) or bucket (Python).
CB_SCOPE - The name of the scope in the bucket, represented by --scope (CLI) or scope (Python).
CB_COLLECTION - The name of the collection in the scope, represented by --collection (CLI) or collection (Python).

Additional available settings include:

--collection-id (CLI) or collection_id in CouchbaseDownloaderConfig (Python) - Optional for the source connector. The
unique key of the ID field in the collection. The default is id if not otherwise specified. Learn more.

Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. 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 \
    --output-dir $LOCAL_FILE_OUTPUT_DIR \
    --strategy hi_res \
    --chunk-elements \
    --embedding-provider huggingface \
    --num-processes 2 \
    --verbose \
    --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}" \
  couchbase \
    --connection-string $CB_CONN_STR \
    --username $CB_USERNAME \
    --password $CB_PASSWORD \
    --bucket $CB_BUCKET \
    --scope $CB_SCOPE \
    --collection $CB_COLLECTION \
    --num-processes 2 \
    --batch-size 80

To understand how vector search works in Couchbase, refer to this tutorial and the Couchbase docs 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