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-1.2.5.tar.gz (41.2 kB view details)

Uploaded Source

Built Distribution

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

contextchain-1.2.5-py3-none-any.whl (49.3 kB view details)

Uploaded Python 3

File details

Details for the file contextchain-1.2.5.tar.gz.

File metadata

  • Download URL: contextchain-1.2.5.tar.gz
  • Upload date:
  • Size: 41.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for contextchain-1.2.5.tar.gz
Algorithm Hash digest
SHA256 d4adea6eb4364eb9dd4a37fc0a796c019a2bda7575ba784d41b7ccdc300b2a6a
MD5 ba32b4ee66ed31e08ac9bc68fb2d9139
BLAKE2b-256 2bf5dd2b214a36b12444a8d8486adc1cc2bca5438d37c04d5e48895e128720dd

See more details on using hashes here.

File details

Details for the file contextchain-1.2.5-py3-none-any.whl.

File metadata

  • Download URL: contextchain-1.2.5-py3-none-any.whl
  • Upload date:
  • Size: 49.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for contextchain-1.2.5-py3-none-any.whl
Algorithm Hash digest
SHA256 5d875b79681bd8a45fe1a4024de810cd928f5744d517f1cf5d22302b6da98894
MD5 37cb9bf960e687c819ef0ddee68298ed
BLAKE2b-256 894aae92e7924fec61b5c483e2b6a06b9418334667e9b1eb71268cc61a76f657

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