Building Your Knowledgebase and Collections

The Knowledgebase is your library of documents and websites that Privata uses to provide context to AI tools. This context helps the platform generate better answers, proposals, summaries, and images such as architecture diagrams.

The Knowledgebase is organized into collections. Each collection should group related material together so the right information can be used for the right activity.

What a Collection Is

A collection is a specific grouping of documents and website content inside the Knowledgebase. Collections are used to organize supporting material that can later be associated with a project.

Good collection examples include:

• A specific product and its user guides
• Company background information
• Pricing tables
• Completed RFIs
• Proposal responses
• Statements of work
• Technical reference documents

While it is possible to place your entire document library into a single collection, that is not the recommended approach. Smaller, more focused collections make it easier to attach the right context to the right project and improve the relevance of AI-generated results.

TIP

Build collections around clear topics, products, business units, or response types. Focused collections are easier to manage and usually produce more targeted AI output.

How Collections Work with Projects

Collections are associated with projects so you can control which supporting documents are used for a bid, contract, or sales opportunity.

When you are working on a project, you can select the collections that should be used by the answer generator, proposal tools, and other AI features. This helps Privata use only the most relevant material for that response effort.

Collections and projects work together as follows:

• Projects hold your source documents, such as RFIs and RFPs
• Collections hold the supporting Knowledgebase content used as context
• The selected collections inform the AI tools when generating answers, proposals, and other project content

Creating a Collection

When creating a collection, a Name is required. You can also add an optional description, which is recommended so users can quickly understand what content is included.

Collections can be created from several places in Privata:

• From the Knowledgebase page using the navigation link at the top right of the browser
• From an existing project using Add Collection
• From the New Project Wizard during the second step

INFO

Use descriptive collection names so it is obvious what material should be attached to a project. A short description is useful when multiple collections cover similar subjects.

Uploading and Indexing Documents

When a document is uploaded to a collection, Privata indexes it. Indexing means the document is processed into smaller sections such as words, phrasing, sentences, and content groupings that can be searched and matched by common traits.

This indexing process makes it possible for Privata to retrieve related sections of your documents when you ask an AI tool to generate an answer, create a proposal, summarize content, or produce an image based on your stored knowledge.

In practical terms, indexing allows the platform to find the most relevant parts of your uploaded material and use them as supporting context during AI generation.

Supported File Types

Privata currently supports the following file types for collection uploads:

• PDF
• DOC and DOCX
• XLS, XLSX, and CSV
• PPT and PPTX
• JPG, JPEG, PNG, TIFF, and BMP
• MD and Text files

Additional document types will continue to be added over time. If you need support for a file type that is not currently listed, contact support@sky-path.ai.

Adding Website Content

Collections can also include website content. To add a webpage to a collection, use the Add Website button and enter the URL of the page you want to include.

Privata will index the content found at that destination link so it can be used as part of your Knowledgebase. This is a useful way to include:

• White papers
• User guides
• Case studies
• Public reference material

Website indexing is especially useful when important supporting content already exists online and does not need to be uploaded as a separate file.

Best Practices for Managing Collections

• Create collections around a clear subject area instead of placing everything into one large collection
• Add descriptions so other users understand the purpose of each collection
• Associate only the collections that are relevant to the current project
• Keep product, pricing, background, and proposal material grouped in a way that matches your sales workflow
• Review collection contents regularly so outdated information does not affect AI output

Deleting a Collection

Collections should be deleted carefully.

DANGER

When you delete a collection, all indexed data in that collection and all associated uploaded documents are permanently removed. This action cannot be undone.

What to Do Next

After creating a collection, the next step is usually to attach it to a project and begin using it with your source documents and AI tools.

For related guidance, continue to the Projects and Project Wizard pages.