> ## 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.
# Search file content via RAG-KAG and return scored snippets
> Scored-chunk content search across the user's eligible IP Vault
(personal + current institution + account-shared siblings). Returns
~200-char snippets centered on matched tokens, with a relevance score
per chunk and a `rag` | `kag` | `fused` source label. Confidential
institution files surface a 🔒 placeholder snippet rather than raw
chunk text. `selectedUploadIds` is optional — when provided, it
intersects with the user's scope; foreign or malformed ids are
silently dropped (never 403). Rate-limited per user (default 20/min).
Results now include KAG graph matches when KAG is enabled for a vault in
scope, and each result carries the full `content` plus KAG evidence
(`matchedEntities`, `trace`) for inline expansion.
## OpenAPI
````yaml /mdx/api-reference/runtime/runtime-api.json post /api/user/files/search-content
openapi: 3.0.0
info:
title: Pria Runtime API
version: 2.0.1
description: >-
Pria API Documentation Praxis's developer platform is a core part of our
mission to empower organizations to grow better. Our APIs are designed to
enable teams of any shape or size to build robust integrations that help
them customize and get the most value out of Pria. All Pria APIs are built
using REST conventions and designed to have a predictable URL structure.
They use many standard HTTP features, including methods (POST,
GET, PUT, DELETE) and error response codes.
All API calls are
made under https://hiimpria.ai/api and all responses return standard JSON.
In these docs, you'll find lists of all available endpoints for a given API,
along with interactive code blocks for building requests. For walkthroughs
of basic usage for these APIs, check out the API guides.
servers:
- url: https://pria.praxislxp.com
description: Pria API Server
security: []
tags:
- name: Authentication
description: User authentication, registration, and password management (/api/auth)
- name: OAuth
description: OAuth authentication providers - Google, GitHub, SSO (/api/auth/oauth)
- name: User
description: User profile management and account operations (/api/user)
- name: User Institutions
description: User institution memberships and switching (/api/user/institution)
- name: User Tools
description: Available tools for authenticated users (/api/user/tools)
- name: Institutions
description: Institution settings and configuration (/api/user/institution)
- name: Conversation
description: AI conversation and Q&A endpoints (/api/ai)
- name: Realtime
description: Real-time voice AI and WebRTC sessions (/api/ai/rt)
- name: Assistant
description: AI assistant configuration and management (/api/user/assistant)
- name: History
description: Conversation history and favorites (/api/user/history)
- name: RAG
description: >-
Document upload, embedding, and retrieval-augmented generation
(/api/user/files, /api/user/rag)
- name: Setting
description: Instance variables and settings management (/api/user/setting)
- name: Branding
description: Digital twin branding and customization (/api/agent/branding)
- name: Agent
description: Agent engagement and session management (/api/agent)
- name: SDK Launch
description: >-
SDK launch token signing and verification for secure iframe embedding
(/api/auth/sdk-sign, /api/auth/sdk-verify)
- name: Testing
description: Health checks, diagnostics, and test endpoints (/api/test)
- name: Admin Accounts
description: Account management for super admins (/api/admin/account)
- name: Admin Institutions
description: Institution management for admins (/api/admin/institution)
- name: Admin Users
description: User management for admins (/api/admin/user)
- name: Admin Entitlements
description: >-
User-institution relationships and permissions
(/api/admin/userInstitution)
- name: Admin Sessions
description: Session management for admins (/api/admin/session)
- name: Admin Histories
description: Conversation history management and analytics (/api/admin/history)
- name: Admin Assistants
description: AI assistant management for admins (/api/admin/assistant)
- name: Admin Questions
description: Institution question and prompt management (/api/admin/question)
- name: Admin Tools
description: Tool configuration management (/api/admin/tool)
- name: Admin AI Models
description: AI model configuration (/api/admin/aimodel)
- name: Admin MCP Servers
description: Model Context Protocol server management (/api/admin/mcpserver)
- name: Admin Feedbacks
description: User feedback management (/api/admin/feedback)
- name: Admin Uploads
description: Upload management (/api/admin/upload)
- name: Admin Charts
description: Analytics and visualization chart management (/api/admin/chart)
- name: Audio Notes
description: Capture and ingest spoken notes into the personal vault
- name: Memory
description: User-facing memory parameters (personal + shared instance memory).
- name: My Data
description: >-
GDPR controls — personal-scope counts, async ZIP-by-email export, and
scoped soft-delete. Every endpoint pins `user = req.user._id` AND
`institution: null`; institution-scoped data is governed by the
institution's own retention policy and never reached from here.
- name: Questions
description: >-
User-facing read of the onboarding question bank used by the "create a
digital twin" wizard.
- name: Transcription
description: >-
One-shot speech-to-text for in-place dictation. Audio blob in, transcript
out — no Upload / History / RAG embeddings are persisted. Use
`/audio-notes` for anything durable.
paths:
/api/user/files/search-content:
post:
tags:
- RAG
summary: Search file content via RAG-KAG and return scored snippets
description: |
Scored-chunk content search across the user's eligible IP Vault
(personal + current institution + account-shared siblings). Returns
~200-char snippets centered on matched tokens, with a relevance score
per chunk and a `rag` | `kag` | `fused` source label. Confidential
institution files surface a 🔒 placeholder snippet rather than raw
chunk text. `selectedUploadIds` is optional — when provided, it
intersects with the user's scope; foreign or malformed ids are
silently dropped (never 403). Rate-limited per user (default 20/min).
Results now include KAG graph matches when KAG is enabled for a vault in
scope, and each result carries the full `content` plus KAG evidence
(`matchedEntities`, `trace`) for inline expansion.
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- query
properties:
query:
type: string
maxLength: 500
description: The search query string.
example: quantum gravity
selectedUploadIds:
type: array
nullable: true
maxItems: 5000
items:
type: string
description: >-
Optional whitelist of upload ids. Intersected with the
user's eligible scope; foreign / malformed ids are silently
dropped.
minScore:
type: number
format: float
minimum: 0
maximum: 1
default: 0.1
description: >-
Minimum dense (vector) score floor. Ignored for KAG-fused
results.
limit:
type: integer
minimum: 1
maximum: 100
default: 50
description: Maximum number of results to return.
responses:
'200':
description: Content-search results
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
example: true
query:
type: string
example: quantum gravity
results:
type: array
items:
type: object
properties:
uploadId:
type: string
chunkId:
type: string
chunkIndex:
type: integer
snippet:
type: string
description: >-
Plain-text snippet, ~200 chars, centered on the
matched token. Confidential hits return `🔒 Private
content matched — open the file to view`.
content:
type: string
description: >-
Full matched chunk text for inline expansion.
Confidential hits return the same 🔒 placeholder as
`snippet`.
matchedEntities:
type: array
items:
type: string
description: >-
KAG graph entity names that matched this hit. Empty
unless the graph leg contributed (source kag/fused).
trace:
type: array
items:
type: object
properties:
list:
type: string
enum:
- dense
- graph
- lexical
rank:
type: integer
description: >-
RRF provenance — which retriever(s) and at what rank
produced this hit. Empty for dense-only results.
score:
type: number
format: float
description: >-
Relevance score (0..1 for dense, ~0.00..0.05 for
RRF-fused).
source:
type: string
enum:
- rag
- kag
- fused
- lexical
description: >-
Retrieval leg that produced the hit — rag
(semantic), lexical (keyword/BM25), kag (graph), or
fused (multiple legs via RRF).
upload:
type: object
properties:
_id:
type: string
originalname:
type: string
filesize:
type: integer
mimetype:
type: string
file_title:
type: string
institution:
type: string
nullable: true
account_shared:
type: boolean
description: >-
True when the upload is shared at the account
level (visible across sibling institutions).
is_private:
type: boolean
confidential:
type: boolean
description: >-
True when the upload's snippet is suppressed
(other-user is_private institution file).
totalScanned:
type: integer
description: >-
Number of raw results returned by searchRag before the
minScore filter.
uploadCount:
type: integer
description: Number of distinct uploads in the user's searchable scope.
tookMs:
type: integer
description: >-
Server-side elapsed time in milliseconds (outer wall-clock
incl. user/collection lookups).
searchPerf:
type: object
nullable: true
description: >-
Per-leg retrieval diagnostics (null when no fan-out ran —
empty scope / RAG disabled / error).
properties:
legs:
type: object
properties:
dense:
type: object
properties:
count:
type: integer
ms:
type: integer
enabled:
type: boolean
graph:
type: object
properties:
count:
type: integer
ms:
type: integer
enabled:
type: boolean
description: False when KAG fusion is off for this turn.
lexical:
type: object
properties:
count:
type: integer
ms:
type: integer
enabled:
type: boolean
description: False when the lexical (BM25) leg is off.
fused:
type: integer
description: Result count after RRF fusion.
totalMs:
type: integer
description: >-
Inner retrieval elapsed time (leg-config resolve +
parallel legs + RRF fusion).
k:
type: integer
description: RRF rank constant.
'400':
description: Validation error (missing or oversized query, server error)
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
example: false
message:
type: string
'401':
description: Authentication required
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
example: false
message:
type: string
example: Authentication Required
'429':
description: Rate limit exceeded (default 20 / minute / user)
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
example: false
message:
type: string
example: Too many content searches. Try again in a moment.
security:
- apiKeyAuth: []
components:
securitySchemes:
apiKeyAuth:
type: apiKey
in: header
name: x-access-token
description: JWT token passed in x-access-token header
````