Powered byLightning AI
All blueprintsSearch & Knowledge AI workflow blueprint

AI Company Knowledge Search workflow blueprint

Ingest documents into an existing knowledge base, then answer questions with cited RAG evidence

See where this blueprint fits in the production workflow lifecycle
Agent Tools
RAG
KB
OCR
Document Processing
Use this blueprint
Pattern
Agent Tools
Agents
1
Functions
2
MCP servers
1

What the Company Knowledge Search blueprint does

Suggested starting request

Attach one or more files, provide an existing knowledge base ID, and ask a question.

Inputs for the Company Knowledge Search workflow

Provide the following information when starting this workflow. Required inputs are validated before the first workflow stage runs.

  • Files

    Required

    File paths (e.g. 'default/docs/report.pdf')

    Type: Array

  • Query

    Required

    Research question

    Type: String

  • Kb Id

    Required

    Existing knowledge base ID that will receive every file

    Type: String

Input template

This request shape is generated from the blueprint's input schema. Angle-bracket values are placeholders; defaults and examples appear only when the source blueprint defines them.

{
  "files": "<required array>",
  "query": "<required string>",
  "kb_id": "<required string>"
}

How the Company Knowledge Search AI workflow works

This search & knowledge blueprint uses a agent tools workflow with 1 agent, 2 functions, and 1 MCP server. Open it in GraphN to customize the resources, inputs, and workflow behavior for your use case.

  1. Resolve

    Function using Resolve Files

  2. Ingest Loop

    For Each

  3. Search

    Mcp Tool

  4. Synthesize

    Agent using Synthesizer

Blueprint resources and prerequisites

These are the actual agents, functions, and MCP servers declared by the blueprint. If an MCP server connects to an external system, configure the required connection and credentials in your GraphN workspace before running the workflow.

AI agent

Synthesizer

Function

Ingest Document

Function

Resolve Files

MCP server

RAG Tools

Tools: Semantic Search

Workflow output contract

The completed workflow makes the following output available to downstream steps, applications, or API clients:

Result

Frequently asked questions

What does the Company Knowledge Search blueprint do?
Ingest documents into an existing knowledge base, then answer questions with cited RAG evidence
What inputs does the Company Knowledge Search workflow use?
The workflow uses Files, Query, Kb Id. Required fields and their expected formats are listed on this page.
What resources are included in the Company Knowledge Search blueprint?
The blueprint contains 1 AI agent, 2 functions, 1 MCP server. Its workflow pattern is Agent Tools.
Can I customize the Company Knowledge Search blueprint in GraphN?
Yes. Open the blueprint in GraphN to customize its inputs, models, resources, and workflow behavior before deployment.

Related Search & Knowledge blueprints

View all rag & knowledge workflows

Competitive Intelligence Tracker

Monitor competitor docs, pricing pages, and press releases. Get a weekly digest

Meeting Knowledge Base

Upload meeting recordings/transcripts, search decisions and action items by topic

Multi-Source Research Assistant

Pull insights from PDFs, spreadsheets, and web pages into one cohesive briefing

FAQ Bot Builder

Upload your docs and get a Q&A bot that answers customer questions with citations