Skip to main content
When you ask Pria a question, it can either answer from its general training — the same way a stock AI model would — or ground its answer in your own uploaded files. That second mode is called “knowledge retrieval”, and it’s what makes a Digital Twin feel like an expert in your material. The Knowledge entry in the [+] menu (the button at the left of the message box) lets you choose how Pria searches.

​
What knowledge retrieval does

Behind the scenes, every file you put in your IP Vault (your personal vault, your Digital Twin’s shared vault, and the account-wide vault) is processed and indexed. When you ask a question with retrieval turned on, Pria:
  1. Searches the indexed content for the passages most relevant to your question.
  2. Hands those passages to the model as context.
  3. The model composes an answer that quotes or paraphrases your material and cites the source files.
The result: answers that reflect your documents, not just the model’s training cut-off. Citations let you jump straight to the original passage to verify.
Knowledge retrieval is the foundation of Pria as a knowledge worker tool. Most Digital Twins leave it on by default.

​
Where the Knowledge controls live

Open the [+] (Actions) menu to the left of the input pill and choose Knowledge. The panel expands inline with everything that shapes a reply’s context:
The Knowledge submenu showing a Remember History dropdown, a Manage Memory link, File Vault options Disabled and RAG, and a Search Only output toggle.

The [+] Actions menu → Knowledge panel: Remember History, the Memory switches with Manage Memory beneath them, the File Vault choice, and the Search Only output toggle.

  • Remember History — how many recent exchanges stay in context (see Conversation History).
  • Memory — the switches first, then the door to what they govern:
    • Enable User Memory — whether Pria remembers personal facts about you (see User Memory).
    • Enable Long-term Memory — whether this Digital Twin keeps its own memories; a platform administrator’s switch, shown read-only to twin administrators (see Twin Memory).
    • Manage Memory… — sits under the two switches; opens the Memory panel with everything stored, while either kind of memory is on.
  • File Vault — whether and how Pria reads your files (below). This section was called Sources until September 2026.
  • Search Only — an output toggle (below).
Knowledge isn’t a separate sidebar panel — it’s a section of the [+] Actions menu, so it’s always one click from the message box while you chat.

​
File Vault: how Pria searches

File Vault is the core choice: whether Pria reads your files at all, and how. Where a knowledge graph is available it offers three choices — Disabled, RAG and RAG + KAG Fusion — and Pria uses RAG + KAG Fusion unless you choose RAG. Where there is no graph, it offers Disabled and RAG.

Disabled

No retrieval at all. The model answers from its training data alone, with no reference to your files. Handy for off-topic questions or when you specifically want the model’s own knowledge.

RAG

Retrieval on. Pria compares the meaning of your question against every passage of your files and pulls out the closest matches — matching by meaning, not by exact words — then hands them to the AI. Good for everyday “what does this say about X” questions. Where a knowledge graph is available, choose RAG to leave the graph out.

RAG + KAG Fusion

What the on state becomes when the vault you’re searching has a knowledge graph — a map of the people, organisations and ideas your documents mention and how they connect. Pria runs a second search over that map and merges the two sets of results into one ranked list. Better for “how does X relate to Y” or “who works on Z” questions, where the answer is about connections. Pria uses it wherever a graph is available unless you choose RAG, and it is always an addition to RAG, never a replacement.

Search Only (toggle)

A separate Output toggle, not a source. With it on, Pria returns the matching passages exactly as they are — without asking the AI to write a reply. Useful when you want to skim the raw hits and pick your own quote. It only applies while File Vault is on.
So the menu is really two settings: File Vault (Disabled, RAG, or — where a knowledge graph is available — RAG + KAG Fusion) and the Search Only output switch. Turning Search Only on or off doesn’t change your File Vault choice.
A knowledge graph is available for your personal vault once you opt in (under Settings → Personal → Knowledge, below), or for a Digital Twin when an admin enables it. Once a graph exists you can browse it directly: open the Files panel and switch the Display selector to Tree of Knowledge to explore the extracted themes, entities, relationships, and source files. See Managing Files.
Whoever administers the Digital Twin enables the graph under Instance Settings → Knowledge → Enable KAG Fusion (members can’t). The same tab tunes how new files are prepared: Chunk keyword enrichment adds a few key words to each passage so it is easier to find later, and Sanitize chunks cleans menus, headers and scanning errors out of a passage before it is filed.
The Instance Settings Knowledge tab describing the IP Vault and showing ingestion toggles — Chunk keyword enrichment, Sanitize chunks — and an Enable KAG Fusion for your Digital Twin toggle.

Instance Settings → Knowledge: an admin enables KAG Fusion (file search plus knowledge-graph search) and tunes file preparation for the Twin's vault.

For your personal vault you control it yourself. Open [+] → Settings → Personal → Knowledge and turn on Enable KAG Fusion for my files (new accounts start with it on). Once on, files you add to your personal library are organized into a knowledge graph, so RAG + KAG Fusion becomes available for your personal files — turning it on also sets your Retrieval Mode to RAG + KAG Fusion. The same tab carries the personal Retrieval Mode and Search Only controls — the same two settings the [+] menu exposes.
The Your Profile Knowledge tab showing Retrieval Mode (Disabled / RAG + KAG Fusion), a Search Only toggle, and an “Enable KAG Fusion for my files” toggle switched on.

Settings → Personal → Knowledge: turn on “Enable KAG Fusion for my files” to build a knowledge graph over your personal vault. Files inside an organization's Twin follow that Twin's setting instead.

​
When to use each

  • “What does the policy say about X?”
  • “Summarize the second chapter.”
  • “Find every place we mention vendor Y.”
  • “How are X and Y related?” / “Who else works on Jane’s projects?” — these use the knowledge graph when one’s available.
  • Most everyday questions where the answer is somewhere in your material.
  • Skimming for primary sources before writing your own draft.
  • Verifying a claim — get the passages without the AI rephrasing them.
  • Checking what Pria is actually finding in your files.
  • Quick lookups where you trust your own reading over a synthesized answer.
  • General knowledge questions unrelated to your files.
  • Comparing Pria’s “off-the-shelf” answer to a grounded one.
  • Speed runs where you don’t need the retrieval step at all.
  • Diagnosing whether a wrong answer was caused by retrieval picking the wrong passages.
Your choice is saved to your account: it applies to every conversation, in every Digital Twin you use, until you change it. A Digital Twin without a knowledge graph uses RAG wherever you would otherwise get RAG + KAG Fusion.
You’ll also see a small badge on each Pria reply showing how it was retrieved (e.g. RAG Search results or KAG Search results), so you can tell at a glance how an answer was grounded.

​
Showing or hiding retrieved passages

When retrieval runs, Pria can show you exactly what it pulled in — a collapsible panel beneath each answer, so you can verify the reply against its sources. Whether the panel appears is governed by the Display RAG/KAG Search Details toggle under Instance Settings → Conversation → Display Details (the same place as the thinking-display toggles). In Search Only mode the passages are the entire response — there’s nothing to hide them under.

​
KAG / RAG Search Results

Expand the KAG Search Results (or RAG Search Results) disclosure at the foot of a reply to see every passage that fed the answer. Each row shows the source file (and segment), a preview of the matched text, its Relevance score, and its Length, with numbered citations you can click to open the original.
An expanded KAG Search Results panel listing four retrieved segments from a patent planning document, each with a content preview, a Relevance percentage, and a Length in characters.

Expanding “KAG Search Results: (4)” reveals the four passages behind the answer — source file, preview, relevance %, and length.

In the example above, the question “Tell me more about Praxis’s patent” pulled four segments from the user’s own patent-application-update.md, scored ~50–52% relevant — the answer is built from those passages, and the citations jump straight to them.

​
Agent Details — what ran

When a reply also runs a tool — image generation, web search, an MCP connector, code — a separate Tool Details (Agent Details) disclosure appears. Expanded, it shows, per call: the tool name, a Success / failure status, the execution duration, the Arguments it was invoked with, and the Response it returned.
An expanded Tool Details panel for a generate_image call showing a Success status, a 57-second duration, the arguments passed, and the returned response.

Tool Details for a tool call: the tool name, Success status, duration, the arguments passed, and the response returned.

Together, KAG/RAG Search Results (what was retrieved) and Tool Details (what was run) let you trace exactly how an answer was produced — the verification habit at the heart of Best Practices.

​
File scope: which vault gets searched

Every retrieval call looks across the vaults you have access to: All three are searched concurrently and their results merged. See Managing Files for how to upload, mark shared, or move files between scopes.
An Admin can configure a Digital Twin to ignore your personal vault when chatting in that twin — useful for keeping personal notes out of an enterprise context. When that’s set, your personal files are still searchable in your own personal Pria, but are invisible while you’re inside that organisation’s Digital Twin.

​
Limitations

Knowledge retrieval has a few honest constraints worth knowing about.
  • Confidential files stay locked for everyone but their owner. A file marked Confidential can still lend its knowledge to answers, but other members never see its details — retrieval shows them a ”🔒 CONFIDENTIAL” marker and a short redacted snippet instead of the document. Only the owner gets full citations and preview. See What Confidential really means.
  • Very recent uploads may still be indexing. Large PDFs, audio, and video files take a few minutes to extract, chunk, and embed. If a brand-new file isn’t appearing in retrieval yet, give it a moment and check Files for processing status.
  • Disabled closes the vault completely. Don’t leave File Vault off by accident if you actually need grounded answers. Since September 2026 Disabled also stops Pria opening, listing or searching your files when you ask it to directly — not only the automatic search behind an answer. Ask for a file while it is off and Pria tells you the file vault is switched off, instead of half-answering. Switch File Vault back on and everything returns.
  • Fusion needs RAG. The knowledge-graph search always runs on top of the ordinary file search; there’s no “graph only”. With File Vault disabled, neither runs.
  • Search quality depends on file quality. Scanned PDFs with no readable text layer (no OCR), password-locked files, and corrupt uploads can’t be indexed. Check the file status in the IP Vault to see what’s processed.