🧠 MindsDB KB Manager

A simple and extensible project to manage MindsDB Knowledge Bases — create, ingest, query, summarize, and interact via agents. Includes a CLI and optional terminal-style UI demo.

---

📌 Overview

This project streamlines core operations on MindsDB Knowledge Bases:

• 📁 Create KBs with embedding and metadata configurations
• 📊 Ingest CSV/text data into KBs
• 🔍 Query KBs using natural language, with or without metadata filters
• 🧠 Summarize KB content via GPT-3.5
• 🤖 Create AI agents connected to specific KBs
• 💬 Chat with agents using natural questions

MindsDB acts as the orchestration engine for vector indexing, OpenAI integration, and agent execution.

---

YouTube Demo : https://www.youtube.com/watch?v=K-cufogVz0Q

Blog Post : https://dev.to/pheonixcoder_56/building-a-kb-manager-using-mindsdb-3h36

---

⚙️ Setup

0. Clone the Repository

git clone github.com/pheonix-coder/kb-manager.git
cd mindsdb-kb-manager

1. MindsDB and Ollama Setup

Setup MindsDB and Ollama with Docker (docker-compose.yml is provided):

docker-compose up -d

Install nomic-embed-text or any other embedding model in Ollama container:

docker exec ollama ollama pull nomic-embed-text

2. MindsDB SQL Prerequisites

Run these in the MindsDB SQL editor:

-- OpenAI Engine
CREATE ML_ENGINE openai_engine FROM openai
USING
openai_api_key ="your_openai_api_key";
-- Summarizer model
CREATE MODEL kb_summarizer
PREDICT summary
USING
engine ='openai_engine',
model_name ='gpt-3.5-turbo',
prompt_template ='Provide a concise summary of the following knowledge base content and highlight the main insights:\n\n{{kb_content}}\n\nSummary:';
-- Vector backendCREATEDATABASEpvec
WITH
ENGINE ='pgvector',
PARAMETERS = {
"host": "pgvector",
"port": 5432,
"database": "ai",
"user": "ai",
"password": "ai",
"distance": "cosine"
};

2. Python Setup

# Create virtual environment
uv venv
source .venv/bin/activate
# Install dependencies
uv pip install -r requirements.txt

---

🧪 Usage

CLI

python main.py --help

Example:

# Create a new KB
python main.py init-kb --name quotes_kb --model-name nomic-embed-text ...
# Ingest data
python main.py ingest-kb --kb-name quotes_kb --file-path "data/quotes.csv"# Query KB
python main.py query-kb --kb-name quotes_kb --query "inspiration" --relevance 0.3
# Summarize KB
python main.py summarize-kb --kb-name quotes_kb --query "life insights"# Create & chat with agent
python main.py create-agent --agent-name quote_bot --knowledge-bases quotes_kb ...
python main.py chat-agent --agent-name quote_bot --question "What did Einstein say about logic?"

---

💡 Use Cases

• ✅ Quickly prototype KBs and agents without building full UI
• ✅ Run automated ingestion and querying pipelines for AI use cases
• ✅ Summarize large KBs into digestible formats
• ✅ Validate MindsDB functionality in real-world agent workflows

---

🧠 Powered By

• MindsDB
• OpenAI GPT-3.5
• pgvector
• Typer