Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.praxis-ai.com/llms.txt

Use this file to discover all available pages before exploring further.

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 menu in the sidebar lets you choose how aggressively 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 knowledge 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 institutions leave it on by default.

​
The four modes

Disabled

No retrieval at all. The model answers from its training data alone, with no reference to your files. Rarely useful when you actually have files in the vault — but handy for off-topic questions or when you specifically want the model’s own knowledge.

Normal (RAG)

The default. Pria runs a dense vector search over your file chunks to find the passages most similar in meaning to your question, then feeds them to the model. Works great for “what does this say about X” questions.

KAG Fusion

RAG plus a knowledge-graph search leg. Pria has extracted entities (people, organisations, concepts) and the relationships between them from your files. KAG Fusion searches both the text and the graph, then fuses the two ranked lists. Better for “how does X relate to Y” or “who works on Z” style questions where the answer is structural, not just textual.

RAG Search Only

Pure search, no answer. Pria returns the matched passages exactly as the model would have seen them — but doesn’t call the model to compose a reply. Useful when you want to skim the raw hits and pick your own quote.
KAG Fusion is an experimental capability. If you don’t see it in the picker, contact the Praxis AI team at humans@praxis-ai.com to request access.

​
When to use each mode

  • “What does the policy say about X?”
  • “Summarise the second chapter.”
  • “Find every place we mention vendor Y.”
  • Most everyday questions where the answer is somewhere in the text.
  • “How are X and Y related?”
  • “Who else works on the same projects as Jane?”
  • “What teams report into the same VP?”
  • Cross-document and multi-hop questions where the answer threads through several files.
  • Skimming for primary sources before writing your own draft.
  • Verifying a claim — get the passages without an LLM rephrasing.
  • Auditing what the retrieval layer is actually seeing.
  • Quick lookups where you trust your own reading over a synthesised 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.

​
The Knowledge sub-menu

1

Open the sidebar

Pin or expand the left sidebar.
2

Expand Settings

Click Settings to expand the configuration section.
3

Open Knowledge

The Knowledge sub-menu shows the four modes as radio buttons. The current selection is highlighted; click another to switch.
Your choice persists across conversations on this Digital Twin until you change it. Each Digital Twin remembers its own knowledge mode.
You’ll also see a small badge on each Pria reply showing which mode produced it (e.g. RAG Search results or KAG Search results), so you can tell at a glance how an answer was retrieved.

​
Showing or hiding retrieval segments

Pria can show you the actual passages retrieved alongside the answer — collapsible cards that quote the source files with a clickable citation. To toggle this:
  1. Click the Digital Twin name at the top of the chat to open instance settings.
  2. Find the Show retrieved passages toggle.
  3. Flip it on to see retrieval cards above the answer; off to keep the reply uncluttered.
In RAG Search Only mode the passages are the entire response — there’s no answer to hide them under.

​
File scope: which vault gets searched

Every retrieval call looks across the vaults you have access to:
VaultContentsWho sees it
Personal vaultFiles you uploaded outside any Digital TwinOnly you
Digital Twin vaultFiles attached to the current Digital TwinEveryone who can use this Twin
Account-shared vaultFiles marked as shared across sibling Twins under the same accountEveryone in your account
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, personal files stay searchable from the standalone “Personal Pria” but are invisible while you’re inside the institution twin.

​
Limitations

Knowledge retrieval has a few honest constraints worth knowing about.
  • Confidential files are scoped. Files marked Confidential are visible only to their owner. They never leak into shared retrieval for other users in the same Digital Twin, even when they’d otherwise be in scope.
  • 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 mode skips ALL files. Don’t leave it on by accident if you actually need grounded answers — your replies will go back to “general knowledge only”.
  • KAG Fusion needs RAG. KAG is always paired with the dense RAG leg; you can’t run “graph only”. If RAG is disabled, KAG is too.
  • Search quality depends on file quality. Scanned PDFs without OCR, password-locked files, and corrupt uploads can’t be indexed. Check the file status in the IP Vault to see what’s processed.
  • IP Vault — what the vault is and how scopes work.
  • Managing Files — uploading, organising, sharing, deleting.
  • Audio Notes — voice memos that flow through the same retrieval pipeline.
  • Switching AI Models — pick a model that handles long context well for richer retrieval.
  • Reasoning & Thinking — combine high effort with grounded retrieval for the best research answers.