Private AI Document Search by Code Creator
BerriAI · Operations & Productivity
Certification per AWS Marketplace.
Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
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.
Show the rest of the publisher’s description (7 more lines)
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.
Highlights
Highlighted by the publisher on AWS Marketplace.
Self hosted private document search running inside the customer AWS account. Upload PDFs, Word files, text files, Markdown files, policies, manuals, reports, and internal documents without relying on a third party SaaS document platform.
Built with Docling document intelligence and Qdrant vector search. Convert documents, index extracted text, search private knowledge, retrieve relevant passages, and keep uploaded files visible in an indexed document library.
MCP ready retrieval foundation for future AI agent workflows. Use private retrieval mode with no external LLM key required, then optionally connect an external or local model provider for generated answers later.
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment · as of 2026-08-13
Plans and pricing as listed
14 listed- Hrs
- Hrs
- Hrs
- Hrs
- Hrs
- Hrs
- Hrs
- Hrs
- Hrs
- Hrs
- Hrs
- Hrs
Refund terms
As stated by the publisher on AWS Marketplace.
No contracts. We do not currently support refunds, but you can cancel at any time.
Sources
Publisher resources
2 linksLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.