Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Docling is a user-friendly, self-sufficient, open-source toolkit licensed under MIT that facilitates the transformation of disorganized documents into structured data, thereby enhancing subsequent document and AI workflows. This versatile tool can interpret a wide array of document types, including PDF, DOCX, PPTX, XLSX, HTML, Markdown, AsciiDoc, CSV, images, audio files, and even scanned documents using any preferred OCR engine. Docling proficiently identifies and processes various elements such as tables, formulas, reading sequences, bounding boxes, headers, footers, images, captions, code snippets, list items, paragraphs, and overall document architecture, which significantly aids in the searchability and integration of the extracted content into AI systems, retrieval-augmented generation, and agent-based applications. Furthermore, it allows for exporting the parsed output in formats like JSON, plain text, Markdown, HTML, and Doctags, thus providing developers with versatile options for their development pipelines and applications. By efficiently organizing and managing components based on reading sequence, Docling breaks down documents into manageable, continuous text segments, optimizing the processing experience.
Description
DocsGPT, built by Arc53, gives organisations private AI agents, assistants and enterprise search over their own documents, with every answer cited to the passage it came from. It runs in four places: Arc53's EU cloud, a dedicated managed instance, the organisation's own data centre, or an air-gapped network with no outbound traffic.
Knowledge comes from uploaded files (PDF, Office documents, scanned pages read with OCR) and from connected services such as SharePoint, Google Drive, Confluence, GitHub and Amazon S3. Agents use tools and APIs, and each action can be allowed, held for approval or switched off. A visual editor chains agents, conditions and code into workflows.
Models are interchangeable: cloud providers including OpenAI, Anthropic and Google, or local models served by Ollama or vLLM. Administrators get OIDC single sign-on, SCIM 2.0, roles, guardrails, per-user quotas and an append-only activity log with export. MIT-licensed, 18,000+ GitHub stars.
API Access
Has API
No
API Access
Has API
Yes
Integrations
Amazon S3
No
Azure OpenAI Service
No
Claude
No
Confluence
No
Datadog
No
Google Drive
No
Google Sheets
Yes
Langfuse
No
Microsoft SharePoint
No
Milvus
No
Integrations
Amazon S3
Yes
Azure OpenAI Service
Yes
Claude
Yes
Confluence
Yes
Datadog
Yes
Google Drive
Yes
Google Sheets
No
Langfuse
Yes
Microsoft SharePoint
Yes
Milvus
Yes
Pricing Details
Free
Free Trial
No
Free Version
Yes
Pricing Details
$20/seat/month (Cloud); self-h
Self-hosted: free (open source, MIT). Cloud: free tier, then $20/seat/month. Managed: from $2,000/month. On-premises and Air-gapped: from $10,000, one-time or recurring.
Free Trial
Yes
Free Version
Yes
Deployment
Web-Based
No
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
Yes
Mac
Yes
Linux
Yes
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
Yes
iPhone App
No
iPad App
No
Android App
No
Windows
Yes
Mac
Yes
Linux
Yes
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
Yes
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
Yes
In Person
No
Vendor Details
Company Name
Docling
Country
United States
Website
www.docling.ai/
Vendor Details
Company Name
Arc53
Founded
2019
Country
Edinburgh, United Kingdom
Website
www.docsgpt.cloud/
Product Features
OCR
Batch Processing
No
Convert to PDF
No
ID Scanning
No
Image Pre-processing
No
Indexing
No
Metadata Extraction
No
Multi-Language
No
Multiple Output Formats
No
Text Editor
No
Zone Selection Tool
No