Multi-Format Parsing
Scans `.pst`, `.msg`, `.pdf`, `.docx`, `.xlsx`, and nested `.zip` files.
Enterprise-Grade Ingestion Engine
Local-first, High-Performance Ingestion Engine: Unstructured Files processed at 1TB/Day on a laptop.
Transform unstructured files into structured data for AI, legal, compliance, eDiscovery, and data migration workflows.
Capabilities
Recursive Attachments
Parseable attachments are processed recursively, including archives and email files.
Identify PII
Detect personal information across unstructured data. NexusParse combines regex detection with AI-powered semantic analysis to identify sensitive information beyond simple text matching.
Email Threading
Parent and thread IDs preserve message relationships across PST extractions.
OCR for Scanned PDFs
Tesseract-backed OCR is used when installed and PDFs contain little to no text.
Smart Chunking
Email-aware and document-aware chunking supports retrieval and AI workflows.
Elasticsearch
Stream indexed items in bulk while ingesting, or run with local output only.
SDK
Run ingestion and iterate output items for local automation.
Path Mirroring
Output folders mirror source structure so lineage and provenance stay auditable.
How It Works
Integrate NexusParse into your existing workflows with CLI and Python SDK support.
- 1
Point NexusParse at your source folder
Use include/exclude filtering with recursive scanning for archives and attachments.
- 2
Run one batch command
nexusparse --source ./input --output ./output --format json --verbose - 3
Consume structured outputs
Each item is written as unified JSON, and you can optionally export centralized RAG JSONL chunks.
Unified Schema
Extracted items follow a consistent structure:
{
"content": "...",
"metadata": { "...": "..." },
"source": { "...": "..." },
"attachments": [],
"parent_id": "...",
"thread_id": "..."
}FAQ
Does data leave our environment?
No. NexusParse is designed for local-first processing. Files are processed within your environment and output is written to a destination you specify. No external data transfer is required.
Can NexusParse be automated?
Yes. NexusParse is designed for automated ingestion workflows. Run jobs through the CLI or Python SDK and integrate them with CI/CD pipelines, scheduled jobs, internal data pipelines, and existing orchestration systems.
What about OCR dependencies?
OCR is optional and used only when Tesseract is installed on your host.
Does NexusParse require a database?
No. PostgreSQL is not required. NexusParse can write processed output to a destination you specify, with optional integration for streaming data to Elasticsearch.
Can NexusParse process sensitive or confidential data?
Yes. NexusParse is designed for environments where data control and locality are important. Processing can be performed within your own infrastructure, helping keep sensitive documents and extracted data under your control.
Can NexusParse integrate with existing systems?
Yes. NexusParse provides CLI and Python SDK interfaces so ingestion can be incorporated into existing applications, pipelines, automation, and data processing workflows.
Where can NexusParse be deployed?
NexusParse is designed to run within your own environment, allowing you to deploy it alongside your existing infrastructure and data workflows.
What types of workloads is NexusParse designed for?
NexusParse is designed for high-volume unstructured data ingestion, including document repositories, email archives, legal collections, eDiscovery datasets, and data preparation workflows for AI and RAG systems.
Contact Sales
Tell us about your data volume and ingestion needs, and our team will help you find the right NexusParse setup and pricing.