Build Internal and Customer Facing Data Apps
Maintain semantic layer and chat with db accurately
pip install dataneuron
Choose Your Integration
Python SDK
from dataneuron import DataNeuron
dn = DataNeuron(db_config='database.yaml', context='your_context')
dn.initialize()
# Optional: Set client context for multi-tenant scenarios
dn.set_client_context("client_123")
result = dn.query("How many users signed up last month?")
print(f"SQL: {result['sql']}")
print(f"Result: {result['result']}")
API Endpoint
Server: dnn --server
Request: POST /chat
{
"messages": [
{"role": "user", "content": "How many users signed up last month?"}
],
"context_name": "your_context",
"client_value": "client_123" // Optional: For multi-tenant scenarios
}
Response:
{
"sql": "SELECT COUNT(*) FROM users WHERE ...",
"result": {"count": 1234},
"explanation": "Last month, 1234 new users signed up."
}
Chat using CLI
Semantic Layer
The framework to maintain your semantic layer
Key Features
Semantic Layer
Easily maintain and improve your data context using YAML files, ensuring accurate and relevant query responses.
Natural Language to SQL
Convert plain English questions into precise SQL queries effortlessly.
Multiple Databases
Support for SQLite, PostgreSQL, MySQL, MSSQL, CSV files (via DuckDB), and Clickhouse.
Multi-Tenant Support
Easily manage client-specific data access and queries within a single instance.
Flexible Integration
Use as a Python SDK, deploy as an API endpoint, or interact via CLI for versatile integration options.
LLM Integration
Powered by major Language Models like Claude (default), OpenAI, LLAMA, and more.
Get Started
Ready to transform how you interact with your data?
View Documentation