MongoDB - Unstructured

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

Batch process all your records to store structured outputs in MongoDB. The requirements are as follows. The MongoDB requirements for a MongoDB Atlas deployment include:

A MongoDB Atlas account. Create an account.
A MongoDB Atlas cluster. Create a cluster.
The cluster must be reachable from your application environment. Learn how.
The cluster must be configured to allow IP address. Learn how. 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.
The cluster must have at least one database. Create a database.
The database must have at least one user, and that user must have sufficient access to the database. Create a database user. Give the user database access.
The database must have at least one collection. Create a collection.
For the destination connector, Unstructured recommends that all documents in the target collection have a field named record_id with a String data type. Unstructured can use this field to do intelligent document overwrites. Without this field, duplicate documents might be written to the collection or, in some cases, the operation could fail altogether.
The connection string for the cluster. For MongoDB Atlas, this connection string must include the protocol, username, password, host, and cluster name. For example:
```
mongodb+srv://<db_user>:<db_password>@<host>/?retryWrites=true&w=majority&appName=<cluster>
```
To get the connection string in MongoDB Atlas, do the following:
1. Log in to your MongoDB Atlas console.
2. In the sidebar, under Databases, click Clusters.
3. Click on the cluster you want to connect to.
4. Click Connect, or click the Cmd Line Tools tab and then click Connect Instructions.
5. Click Drivers.
6. Under Add your connection string into your application code, copy the connection string. You can then close the Connect dialog in MongoDB Atlas. Before you use this connection string, be sure to fill in any placeholders in the string, such as your MongoDB Atlas database user’s password value.
Learn more.

The MongoDB connector dependencies:

CLI, Python

pip install "unstructured-ingest[mongodb]"

You might also need to install additional dependencies, depending on your needs. Learn more. For a MongoDB Atlas deployment, the following environment variables:

MONGODB_DATABASE - The name of the database, represented by --database (CLI) or database (Python).
MONGODB_COLLECTION - The name of the collection in the database, represented by --collection (CLI) or collection (Python).
MONGODB_URI - The connection string for the cluster, represented by --uri (CLI) or uri (Python).

For a local MongoDB server, the following environment variables:

MONGODB_HOST - The host for the local MongoDB server, represented by --host (CLI) or host (Python).
MONGODB_PORT - The port for the local MongoDB server, represented by --port (CLI) or port (Python).

Now call the Unstructured Ingest CLI or Unstructured Ingest Python. 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}" \
  mongodb \
    --uri $MONGODB_URI \
    --database $MONGODB_DATABASE \
    --collection $MONGODB_COLLECTION

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 version of the Unstructured API that is hosted on your own compute infrastructure.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 hosted on your own compute infrastructure, 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