Skip to main content

A unified agent framework for connecting workflows, databases, and agents

Project description

DBConnector (Agenthink)

DBConnector is a database connectivity utility for the Agenthink platform.
It enables agents running on Agenthink to securely connect to external MySQL and MSSQL databases using credentials managed by Azure Blob Storage and Azure Key Vault.

Connections are cached per session and are designed for read-only access, allowing agents to safely query data without modifying source databases.

Purpose

This library allows Agenthink agents to:

  • Connect to user-registered databases on the Agenthink platform
  • Execute safe, read-only SQL queries
  • Reuse database connections across agent sessions

Features

  • Session-based connection caching for agents
  • Supports MySQL and MS SQL Server
  • Secure secret management via Azure Key Vault
  • Datastore metadata loaded from Azure Blob Storage
  • Read-only SQL enforcement (SELECT, SHOW, EXPLAIN, etc.)
  • Built-in logging for observability and debugging

Basic Usage (Agenthink Agent)

db = DBConnector.get(
    session_id="session_123",
    user_id="user1",
    workflow_id="workflowA"
)

result = db.execute_query(
    db_name="ritobhai",
    query="SELECT * FROM item LIMIT 10"
)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agenthink-0.1.12.tar.gz (6.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agenthink-0.1.12-py3-none-any.whl (6.2 kB view details)

Uploaded Python 3

File details

Details for the file agenthink-0.1.12.tar.gz.

File metadata

  • Download URL: agenthink-0.1.12.tar.gz
  • Upload date:
  • Size: 6.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.3

File hashes

Hashes for agenthink-0.1.12.tar.gz
Algorithm Hash digest
SHA256 a718cb14addcba34ef4b8aaef2b19f0196de7b781a079e3fbff62366dc9da23c
MD5 917b92afc288f7e9666091dfe6bc3985
BLAKE2b-256 1c78c0810db6b909f4a69ca67011fadcb70d2fe0ca46a6c799e78ac08e22eae9

See more details on using hashes here.

File details

Details for the file agenthink-0.1.12-py3-none-any.whl.

File metadata

  • Download URL: agenthink-0.1.12-py3-none-any.whl
  • Upload date:
  • Size: 6.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.3

File hashes

Hashes for agenthink-0.1.12-py3-none-any.whl
Algorithm Hash digest
SHA256 97ba16d767175671b683ad659f6723520f00cf840947cbaa0e629ba6dc8cb194
MD5 d8e79e9fbda7b1d86bd6ea8c31bf4474
BLAKE2b-256 1f96d757ce77f16486c387cc995938717e4c7a0b708a063ff430964c19e2e038

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page