The open-source framework for autonomous database agents.
Project description
Arivu
Arivu is an open-source framework designed for building autonomous database agents. It bridges the gap between raw data warehouses and large language models (LLMs) by offering a dual-layer approach:
- A Powerful Python SDK: Allows engineers to orchestrate text-to-SQL pipelines, hook up custom tools, and seamlessly inject execution memory layers.
- A Sleek Dashboard UI: A Next.js-based observability platform designed for teams to instantly connect dialects, select cloud models, execute conversational prompts, and inspect pipeline execution latency natively.
Quickstart
You can install the Arivu engine seamlessly using pip:
pip install arivu
Once installed natively on your Python environment, invoke the proxy router using your database credentials:
import os
from arivu import Arivu
# 1. Establish connection with your relational cluster
db_app = Arivu.connect(
database_url="postgresql://user:pass@localhost:5432/main",
llm_provider="openai",
monitoring=True
)
# 2. Formulate a natural language query
node = db_app.query("What were our top 3 highest revenue products last quarter?")
# 3. Run the intelligent execution pipeline
results = db_app.run_pipeline(node)
# 4. Extract data
print("Response:", results.get("response"))
print("Generated SQL:", results.get("sql"))
Advanced Integrations
The Arivu Core Engine explicitly allows routing autonomous interaction agents natively into standard chat mediums including:
- Telegram
- Twilio WhatsApp Arrays
- Slack (via SocketMode)
- Extensible REST APIs
Documentation
Full API references and configuration matrices are accessible on our Documentation Matrix natively deployed via Mintlify!
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file arivu_ai-0.1.0.tar.gz.
File metadata
- Download URL: arivu_ai-0.1.0.tar.gz
- Upload date:
- Size: 50.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4c459297d86feefc2bddc753fbae48e9f5f385fe8bd92fbfb39dd33fd9fa4e2a
|
|
| MD5 |
16de33282dbef5cd97bc686170e60450
|
|
| BLAKE2b-256 |
1c9044b012376715966ae484b064e5a1814a18305246ef5e66af4bf354aec8d0
|
File details
Details for the file arivu_ai-0.1.0-py3-none-any.whl.
File metadata
- Download URL: arivu_ai-0.1.0-py3-none-any.whl
- Upload date:
- Size: 62.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
09642b9373c66a82c3b10700c1ebfc3fc69a6fe2957ed31355d5564fdefc1b6f
|
|
| MD5 |
db6b717f2e5f5477a4ddbc3f539a6018
|
|
| BLAKE2b-256 |
aac5972a7e43411a939976a8bfcd39e5cd3ab52c203707a02931492fe90d9d44
|