Knowledge Base integration

What the Knowledge Base package does

Query Robomotion Knowledge Bases from flows. Hybrid (vector + keyword) retrieval over locally cached sqlite-vec indexes, an optional Rerank node (Cohere / Voyage AI / Jina), plus a Knowledge Toolkit for Hermes agents. The same binary doubles as the ingestion worker used by robomotion-agent.

Namespace

Robomotion.KnowledgeBase

Latest version

0.1.7 (6 versions published)

Written in

Python

Categories

Artificial Intelligence

Knowledge Base nodes (3)

These are the node IDs an agentic flow or an RPA bot uses, exactly as they appear in the Flow Designer and in flow code. The Toolkit node hands an agent several of the package operations at once.

Platforms

The Knowledge Base package runs on Windows, macOS and Linux robots. Any Robomotion robot on these operating systems can run a flow that uses it.

How to install the Knowledge Base package

1. Open Packages in the Robomotion Flow Designer.
2. Search for Knowledge Base or Robomotion.KnowledgeBase, then click Install on its card.
3. The Knowledge Base nodes appear in the node palette for everyone in the workspace, because installation is per workspace.

From a terminal, the Robomotion CLI installs the same package:

robomotion install Robomotion.KnowledgeBase

Templates that use Knowledge Base

2 ready-made templates use Knowledge Base nodes in their flows. Open one to start from a working flow.

• Clinic Support Assistant

  A customer support assistant for a website, served to the page as one MCP tool. A visitor and a signed-in patient are answered by two different Hermes Agents, and the difference is not a prompt or a flag, it is two wires: the visitor's agent is wired to the practice documents and to nothing else, so nothing on that side of the canvas can reach a patient record whatever the model is asked. The signed-in tools take no arguments at all. They read the record number the website established from a session cookie, so the model cannot name a patient, and every turn is written to a dialog log the practice can read in the morning.

• Knowledge Base Endpoint

  Ask your own documents a question over HTTP. A Robomotion Knowledge Base is indexed by a workspace agent on your machine and searched locally by the robot; one Query Knowledge Base node returns the passages that answer a question, each with the document and heading it came from. Http In and Http Out turn the flow into a service anything can call, and a Min Score fence means it answers "I could not find that" instead of inventing something. Ships four sample documents and a thirty-line Python client.

Related integrations

Packages that share a category or keywords with Knowledge Base. It is filed under Artificial Intelligence.

• LanceDBStore and search embeddings in LanceDB - the embedded vector database. Works against a local directory, S3/GCS/Azure object storage or LanceDB Cloud. Vector, full-text and hybrid search, SQL filters, upserts, indexing, plus a Toolkit that hands the whole database to an AI agent.
• QdrantConnect to Qdrant vector database for similarity search, embeddings storage, and vector operations
• Document ProcessorParse and process documents for RAG applications. Supports PDF, DOCX, PPTX, TXT, HTML, Markdown and more. Extract text, chunk content for embeddings.
• PerplexityConnect to Perplexity AI for AI-powered search and chat completions with real-time web data
• PineconeProvides a simple interface to access the Pinecone API, Pinecone's vector database is fully-managed, developer-friendly, and easily scalable.
• SerperGoogle Search API powered by Serper - web, image, video, news, shopping, places, scholar search and more