AI Document Search
Stop messy PDFs breaking your AI automationsSimply upload and we'll handle the rest
Ragextract is vision-based document search and retrieval pipelinebuilt for searching, citing and extracting from messy PDF, DocX and PPTX
Insurance Policies
Supplier Invoices
Financial Statements
Reconciliation Spreadsheets
Deep Research
Court Documents
Tenders & RFPs
Slide Decks
Sales Presentations
SEC Filings
Bills
Commercial Property Contracts
Legal Documents
Construction
Academic Papers
Technical Manuals
14 Days Free Trial
GDPR Compliant
30 days Refund Policy
We turn your complex documents into an API
Solutions & Use Cases
AI document processing that scales as you grow
The missing piece for infrastructure for your AI agents
50
%
Cost reduction when parsing applications, claim forms and insurance Policies
For Insurance, Underwriters and Brokers
Insurance managers wanting better control over their automation budgets
Development teams looking to reduce infrastructure costs and delivery reliably
Insuratech startups who need to launch to market faster
50
x
Productivity boost when handling multi-page contracts, court documents and research
For Legal Teams, Lawyers and Consultants
Legal departments needing to increase their document processing capacity
Consultants who need answers quickly and accurately from case files and court documents
Legal Firms to expand AI usage for their workflows
50
hrs
Time saved per month in validation and extraction jobs From tenders, quotes and contracts
For Property Managers and Sales Teams
Sales managers who want to expand their volume of tenders and leads in review
Property managers who need to their time back to focus on more important tasks
Proptech companies who process technical site plans, tables and architecture diagrams
How it works
Just drop in your files and we'll do the rest
Seemlessly integrates into your existing workflows
Simple REST API that works with n8n, Make, Zapier and more
1
Upload documents directly to Ragextract and we'll take care of
the storage, splitting, vectorizing and indexing in a matter of seconds.
curl -X POST https://api.ragextract.com/v1/vectorize \
--header 'x-api-key: $RAGEXTRACT_API_KEY' \
--form "file=insurance_claim_application.pdf"2
Search across 100s of pages instantly using natural language and Ragextract will
return only the relevant ones (score-based). No more praying you'll hit the right keywords and images also work - it's all contextual!
curl -X POST https://api.ragextract.com/v1/search \
--header 'x-api-key: $RAGEXTRACT_API_KEY' \
--data '{
"query": "Find motor vehicle details and registration of all parties involved in claim",
}'
3
Finally, pass those matching pages into an VLM/LLM of your choice.
You decide how and what gets extracted depending of your use-case. Ragextract keeps your data safe
from leaks by serving them as dynamic and expirying links.
curl https://api.openai.com/v1/responses \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-4.1",
"input": [
{
"role": "user",
"content": [
{ "type": "input_text", "text": "Extract claimant details in the following structure..." },
{
"type": "input_image", // Use Ragextract result here!
"image_url": "https://api.ragextract.com/v1/share/dsx_B5bsOBDzsXsqfmLo?token=kCThsH"
}
]
}
]
}'Why use Ragextract?
The smarter way to increase document processing capabilitiesenabling your team to do more with less
Search first, extract later
Prioritizing AI Document Search to optimise long document extraction
Ragextract challenges the popular document processing model of other providers by avoiding the "parse-first-search-later" approach. In fact, we do the opposite! We believe our method is faster, cheaper and less wasteful.
Instant large document pipeline
Expand beyond LLM context windows to enable smarter and better tuned AI agents
Ragextract handles the long and large documents that most LLMs typically struggle with - scanned Pdfs, technical manuals, image heavy reports etc. Our users typically prefer our more advanced RAG and retrieval setup as they can do more with the output.
Full control for better results
Specially designed for real world document scenarios just like yours
Not only does this reduce our costs significantly, our belief is that bundling models is unnecessary as AI Developers actually prefer to handle their own prompts. Ragextract is built for developers for more challenge document extraction workloads.
Enhances low code platforms
Push your automation further ensuring complex documents won't break your workflow
Many low code platforms aren't designed for heavy document / high cpu-consumption tasks. Typically, they exhaust their limits which then crash your instance. Ragextract pairs perfectly with these services to offer the necessary processing power to make business flow.
Saves you time and resources
From 3 months to 3 days, get your project up and running with just an API key
Document processing infrastructure consumes a large amount of your team's time, budget and reputation if not done correctly. Adopting Ragextract means you can focus on building a great AI experience for your users and reduce development time by weeks.
Pricing
Simple Pricing that Scales as You Grow
All Features. All APIs. No Hidden Fees.
Monthly
Annually
Save
Save 100%
$15/month
$0
/month
Billed $180 $0 annually
Starter
A limited time offer to use Ragextract for free! For internal operations, smaller documents and lighter workloads.
Features
Document processing for up to 100 pages
Multipart upload API for PDF, Docx, Pptx and Xlsx
Secure file storage and page-level retrieval API
Multimodal embeddings support and vector store
Document search API for text and image
Compatible with your favourite AI agents and workflows
Usage
Shared worker pool
10mb upload size limit
100 pages per document limit
100mb storage
14 day data retention
3 concurrent jobs
per workspace
1000 searches
per month
50000 retrievals
per month
Organisation
Up to 5 team members
Up to 30 workspaces
3 API keys
per workspace
Admin, manager, developer & readonly roles
SSO/OAuth Logins
Support
Community forum
Email support on best effort basis
No phone support or SLAs offered
Save 20%
$149/month
$119.20
/month
Billed $1788 $1430.40 annually
Standard
Best for daily documents, startups or integrating into proprietary and commercial apps.
Features
Large document processing pipeline for 100+ pages
Multipart upload API for PDF, Docx, Pptx and Xlsx
Secure file storage and page-level retrieval API
Multimodal embeddings support and vector store
Document search API for text and image
Compatible with your favourite AI agents and workflows
Usage
Shared worker pool
300mb upload size limit
500 pages per document limit
30gb storage
90 days data retention
20 concurrent jobs
per workspace
15000 searches
per month
750000 retrievals
per month
Organisation
Up to 30 team members
Up to 150 workspaces
10 API keys
per workspace
Admin, manager, developer & readonly roles
SSO/OAuth Logins
Support
Community forum
Email and chat support
Phone support and SLAs available (+fees)
Dedicated Support
Base Price
Custom
Quote tailored to requirements
On-prem or custom build
For stricter regulatory requirements where own-cloud or on-prem is desired. Tailored resources to match need.
Features
Large document processing pipeline for 100+ pages
Multipart upload API for PDF, Docx, Pptx and Xlsx
Secure file storage and page-level retrieval API
Multimodal embeddings support and vector store
Document search API for text and image
Compatible with your favourite AI agents and workflows
Usage
Dedicated worker pool
Custom upload size limit
Custom pages per document limit
Custom storage
Custom data rentention
Custom number of searches
Custom number of retrievals
Organisation
Custom quantity of team members
Custom quantity of workspaces
Custom quantity of API keys
per workspace
Custom concurrent jobs
per workspace
Admin, manager, developer & readonly roles
SSO/OAuth Logins
Support
Community forum
Email and chat support
Phone support and SLAs available (+fees)
14 Days Free Trial
Cancel Anytime
30 days Refund Policy
Migration Support Available
Help available for your document AI workflows!
Ragextract™ is brought to you by the document AI specialists at Subworkflow. We help automation teams, startups and small businesses get them their time back with simple AI automations that are easy to understand and maintain.
FAQs
Not Finding What You're Looking For? Contact Us!
What is Ragextract?
Ragextract is an AI-powered document search service which let's users upload documents and search them semantically afterwards via API. Ragextract helps handle upload, storage, indexing, embeddings, vector stores and providing retrieval and search APIs compatible with AI agents.
Is Ragextract right for my use case?
Ragextract is a key abstraction for all AI document workflows where partial extraction of the contents is required. If you need to search for answers - not just keywords - within one or more documents then Ragextract is a perfect fit! Examples include extracting claimant details in insurace forms, filtering transcripts in case files and finding special clauses or signals in tenders or contracts.
Do you have a free plan?
Yes! Our free plan is designed to let you evaluate Ragextract but also functional for internal operations and occassional (weekly or monthly) documents processing. We recommend up upgrading for more capacity and production use cases.
How many documents can I upload per month?
As many as you like... just as long as you stay within the designated storage limit. We don't charge by the number of pages so whether 10k pages or 100k pages, the price stays the same.
Can I cancel my subscription at any time?
Yes of course! We want you to be happy to stay with us so if anything isn't working right, reach out and let's see if we can fix it or implement a new feature for you. Just head over to the billing page and you can manage your subscription from there.
Why is a credit card needed to sign up?
Though we'd like to offer an easier alternative, credit card registration is one of the few productive ways to protect the service from sign-up spam and fake users. This in-turn ensures better stability for the all users on our platform.
Will I get charged at the end of my trial?
Yes. If you're happy to continue with Ragextract, we'll automatically handle the billing and you don't need to take any further action. If it turns out Ragextract isn't for you, please cancel your subscription before the trial expires.
I'm not sure if Ragextract is for me. Can I get a demo?
Yes! Please reach out to us at sales@subworkflow.ai and we'll get back to you as soon as we can during business hours. Please include details of your organisation, team size and high level brief of what you're looking for as this will help us tailor the demo for you.
Ragextract is a AI document search for AI agents
© 2026 Subworkflow AI Limited
Everything Else
Follow for Updates
'%3e%3cpath%20d='M29.1053%200H2.89466C1.296%200%200%201.296%200%202.89466V29.1053C0%2030.704%201.296%2032%202.89466%2032H29.1053C30.704%2032%2032%2030.704%2032%2029.1053V2.89466C32%201.296%2030.704%200%2029.1053%200ZM9.90216%2027.6309C9.90216%2028.0962%209.52503%2028.4733%209.05977%2028.4733H5.47393C5.00867%2028.4733%204.63154%2028.0962%204.63154%2027.6309V12.5992C4.63154%2012.1339%205.00867%2011.7568%205.47393%2011.7568H9.05977C9.52503%2011.7568%209.90216%2012.1339%209.90216%2012.5992V27.6309ZM7.26685%2010.3399C5.38547%2010.3399%203.86027%208.81466%203.86027%206.93328C3.86027%205.0519%205.38547%203.5267%207.26685%203.5267C9.14823%203.5267%2010.6734%205.0519%2010.6734%206.93328C10.6734%208.81466%209.14831%2010.3399%207.26685%2010.3399ZM28.6417%2027.6988C28.6417%2028.1265%2028.2949%2028.4733%2027.8671%2028.4733H24.0193C23.5915%2028.4733%2023.2447%2028.1265%2023.2447%2027.6988V20.648C23.2447%2019.5962%2023.5533%2016.039%2020.496%2016.039C18.1246%2016.039%2017.6436%2018.4738%2017.547%2019.5665V27.6988C17.547%2028.1265%2017.2003%2028.4733%2016.7724%2028.4733H13.0509C12.6232%2028.4733%2012.2764%2028.1265%2012.2764%2027.6988V12.5314C12.2764%2012.1036%2012.6232%2011.7568%2013.0509%2011.7568H16.7724C17.2002%2011.7568%2017.547%2012.1036%2017.547%2012.5314V13.8428C18.4263%2012.5231%2019.7331%2011.5046%2022.5155%2011.5046C28.6769%2011.5046%2028.6417%2017.2609%2028.6417%2020.4237V27.6988Z'%20fill='%23000'/%3e%3c/g%3e%3cdefs%3e%3cclipPath%20id='clip0_145_134'%3e%3crect%20width='32'%20height='32'%20fill='%23000'/%3e%3c/clipPath%3e%3c/defs%3e%3c/svg%3e)
