Overview
Private AI Document Search - Self-Hosted Document Intelligence on AWS
Private AI Document Search by Code Creator is a self-hosted document intelligence and semantic search server that runs entirely inside your own AWS account. Upload, index, and search your sensitive documents without sending them to a third-party SaaS platform.
Who This Product Is For
This AMI is built for teams that need AI-powered document retrieval while maintaining full control over their data. Whether you manage internal knowledge bases, technical documentation, compliance records, operations playbooks, research files, or customer service references, this product gives you a private, searchable knowledge base on infrastructure you own.
Example Workflow: Technical Documentation Team
Imagine an engineering or operations team managing hundreds of internal documents - runbooks, architecture guides, incident reports, and policy manuals. Today, finding the right passage means manually searching through folders or relying on basic keyword matching. With Private AI Document Search, that team uploads their documents through a browser interface, the system automatically converts and indexes them using Docling and Qdrant vector search, and within minutes any team member can run semantic queries that return the most relevant passages with source names and similarity scores. Documents remain indexed and searchable until you choose to remove them - no need to re-upload between searches.
How It Works
- Upload documents - Support for PDFs, Word documents, text files, Markdown files, policies, manuals, reports, contracts, support notes, and internal knowledge files
- Automatic conversion and indexing - Docling converts documents and extracts searchable text, which is then indexed into Qdrant vector storage
- Semantic search and retrieval - Search your knowledge base through a simple browser interface and retrieve relevant passages with source attribution and similarity scores
- Persistent document library - Uploaded documents remain visible in the indexed document library and stay searchable across sessions
- Optional AI-generated answers - By default, the server runs in private retrieval mode with no external LLM key required. Connect an external or local model provider later to enable generated summaries
- MCP-ready retrieval - Positioned for future AI agent workflows and retrieval-augmented generation experiments
Security and Network Architecture
This product is designed with privacy as a core principle. Key security features include:
- Localhost-bound services - Docling, Qdrant, and the private backend application are bound to localhost or internal Docker networking, not exposed to the public internet
- Minimal port exposure - Only ports 22 (SSH) and 80 (HTTP) need to be opened for the initial deployment
- First-boot password generation - Unique credentials are generated automatically on first launch
- Basic Auth protection - The web interface is protected by authentication out of the box
- Your infrastructure, your data - All documents and vector indexes remain on your EC2 instance within your AWS account
Buyers handling sensitive documents should consider additional hardening steps such as enabling EBS encryption, configuring TLS for HTTPS access, restricting access via VPN or IP allowlisting, and reviewing AWS security best practices for their specific compliance requirements.
Deployment and Getting Started
Deployment is straightforward with automated first-boot provisioning:
- Launch the AMI from AWS Marketplace and open ports 22 and 80
- Connect via SSH and retrieve your auto-generated first-boot password
- Access the web interface through your instance's public IP
- Wait 3-5 minutes for Docling to fully initialize on first boot (the web page may appear before document conversion is ready)
- Begin uploading and searching your documents immediately
The environment runs on Docker Compose and includes helper commands, status checks, and backup tooling to simplify ongoing operations.
What Is Included
Code Creator provides the fully integrated and AWS Marketplace-ready AMI environment, including:
- Automated first-boot provisioning and credential generation
- Private document indexing workflow with Docling conversion services
- Qdrant vector storage and semantic search
- Indexed document library and browser-based search interface
- Docling UI access for document conversion management
- Operational helper tools, status checks, and backup functionality
- MCP-ready retrieval configuration for AI agent integration
Normal AWS infrastructure charges for your EC2 instance and associated resources apply separately.
Get Started Today
Subscribe through AWS Marketplace to launch your private document search server in minutes.
Highlights
- Keep sensitive documents inside your AWS account instead of sending them to a third-party SaaS platform. Upload PDFs, Word documents, text files, Markdown files, policies, manuals, reports, contracts, and internal knowledge files. All documents are stored, indexed, and searchable within your own infrastructure, giving you full control over data residency and access. No external LLM key is required for private retrieval mode, so your content never leaves your environment.
- Powered by Docling document intelligence and Qdrant vector search to deliver accurate semantic retrieval across your private knowledge base. Docling converts multiple document formats into searchable text, while Qdrant indexes extracted content for fast vector-based similarity search. Browse uploaded files in an indexed document library, search by meaning rather than exact keywords, and retrieve relevant passages from across your entire document collection.
- MCP-ready retrieval foundation designed to integrate with AI agent workflows. Use the built-in private retrieval mode today with no external model dependency, then optionally connect an external or local LLM provider for generated answers when ready. The Docker Compose deployment includes automated first-boot credential generation, Basic Auth protection, backup tooling, and helper commands to simplify ongoing operations.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimensions summary
Top-of-mind questions for buyers
Vendor refund policy
No contracts. We do not currently support refunds, but you can cancel at any time.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Private AI Document Search by Code Creator gives organizations a fast way to launch their own private document retrieval server on AWS. Instead of uploading sensitive PDFs, Word files, policies, manuals, and business records into a third-party SaaS tool, customers can run document conversion, vector indexing, and semantic search inside their own cloud account. It is practical on day one, useful without an external LLM key, and positioned for the next wave of AI-agent retrieval workflows.
Additional details
Resources
Vendor resources
Support
Vendor support
For support inquiries related to Private AI Document Search by Code Creator, please contact the Code Creator team by email at info@codecreator.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.