Private AI Document Search by Code Creator

Private AI Document Search by Code Creator is a self hosted document intelligence and semantic search server designed for customers who want private document retrieval running inside their own AWS account.

This AMI helps organizations upload PDFs, Word documents, text files, Markdown files, policies, manuals, reports, technical documentation, contracts, support notes, and internal knowledge files into a private searchable knowledge base. The system converts documents with Docling, extracts searchable text, indexes the content into Qdrant vector search, and lets users search or retrieve relevant passages through a simple browser interface.

The product is designed for teams that want AI document search capabilities without immediately sending sensitive documents into a third party SaaS platform. It is useful for internal knowledge bases, technical documentation, support documentation, compliance records, operations playbooks, research files, business records, customer service references, and AI agent retrieval experiments.

By default, the server runs in private retrieval mode. No external LLM key is required to upload, index, search, and retrieve source backed passages. Without a configured model provider, the product returns the most relevant private document passages with source names and similarity scores instead of generating polished AI summaries. Optional generated answers can be enabled later by connecting an external or local model provider.

The application includes a public IP based web interface, first boot password generation, Basic Auth protection, an indexed document library, Docling UI access, Qdrant vector storage, Docker Compose services, helper commands, status checks, backup tooling, and MCP ready retrieval positioning for future AI agent workflows.

Uploaded documents remain visible in the indexed document library after upload. Customers do not need to reupload documents every time they search or ask questions. The browser file picker may clear after upload, but indexed documents remain stored and searchable until the customer removes or rebuilds the instance.

After first boot, Docling may take approximately 3 to 5 minutes to fully initialize. The web page may appear before document conversion is ready. If document conversion is not ready immediately, customers should wait a few minutes and refresh the page.

Only ports 22 and 80 need to be opened for the initial Marketplace deployment. Docling, Qdrant, and the private backend application are bound to localhost or internal Docker networking.

This AMI is built for customers who want a practical private AI document search starter server with a simple monthly software charge and normal AWS infrastructure charges. This is a repackaged open source software product wherein additional charges are applied for the deployment of the application and AMI support and compliance.