Skip to main content

A pipeline execution framework with MongoDB and ChromaDB integration for AI workflows

Project description

ContextChain

GitHub License Python Version PyPI Version Build Status

ContextChain is an open-source, pipeline-based execution framework designed to orchestrate AI and full-stack workflows. It enables developers to define, manage, and execute complex task chains with support for various task types (e.g., API calls, local processing, LLM tasks) in a structured and versioned manner. Built with Python, it leverages MongoDB for persistence and provides a command-line interface (CLI) for easy interaction.

Features

  • Pipeline Management: Define and execute workflows as pipelines with multiple tasks.
  • Task Types: Supports GET, POST, PUT, LLM, and LOCAL task types with configurable inputs and outputs.
  • Versioning: Track and rollback schema versions using MongoDB.
  • Extensibility: Easily extend with custom task endpoints and configurations.
  • CLI Interface: Manage pipelines interactively or via scripts.
  • Validation: Ensures schema integrity with built-in validators.

Installation

Via PyPI

ContextChain is available on PyPI. Install it with pip:

pip install contextchain

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

contextchain-1.2.0.tar.gz (39.4 kB view details)

Uploaded Source

Built Distribution

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

contextchain-1.2.0-py3-none-any.whl (47.7 kB view details)

Uploaded Python 3

File details

Details for the file contextchain-1.2.0.tar.gz.

File metadata

  • Download URL: contextchain-1.2.0.tar.gz
  • Upload date:
  • Size: 39.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for contextchain-1.2.0.tar.gz
Algorithm Hash digest
SHA256 03b959bd67b4ea02e8a52167989b2e1b22c2410753cdbf80e3e590fe0458b391
MD5 7cdc01c67b62dab2abda9816c4386daa
BLAKE2b-256 fb1fce8e244b0e3aae9e5c87bb19e76c84eb0f39e2163a980ada2c83630328ae

See more details on using hashes here.

File details

Details for the file contextchain-1.2.0-py3-none-any.whl.

File metadata

  • Download URL: contextchain-1.2.0-py3-none-any.whl
  • Upload date:
  • Size: 47.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for contextchain-1.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 32f328bb501617450c9f8964ad580bd8f3d6ab24cf721454c5179a8a4e52ff5b
MD5 3b199b458615a274faa41ef97281a01d
BLAKE2b-256 077ae745e70a0a83befb4b37116c2d55861cea5561533c1128c4a19313c08a24

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