New Research: Supply Chain Attack on Axios Pulls Malicious Dependency from npm.Details →
Socket
Book a DemoSign in
Socket

webauto-pipelineframework

Package Overview
Dependencies
Maintainers
1
Versions
1
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

webauto-pipelineframework

WebAuto Pipeline Framework for creating multi-provider LLM pipelines with configuration-driven compatibility. Supports Anthropic, OpenAI, and other providers with tool calling and streaming capabilities.

latest
npmnpm
Version
0.0.1
Version published
Maintainers
1
Created
Source

WebAuto Pipeline Framework

A flexible framework for creating multi-provider LLM pipelines with configuration-driven compatibility. Supports Anthropic, OpenAI, and other providers with tool calling and streaming capabilities.

Features

  • Multi-Provider Support: Seamlessly integrate with Anthropic, OpenAI, and other LLM providers
  • Protocol Transformation: Convert between different LLM API formats (Anthropic ↔ OpenAI)
  • Tool Calling: Full support for function calling across different providers
  • Streaming: Support for streaming responses from non-streaming providers
  • Configuration-Driven: Easy setup with JSON configuration files
  • Modular Architecture: Extensible pipeline nodes for custom processing

Installation

npm install webauto-pipelinecframework

Quick Start

const { PipelineManager } = require('webauto-pipelinecframework');

// Create a pipeline manager
const pipelineManager = new PipelineManager();

// Create a pipeline configuration
const config = {
  name: 'anthropic-to-openai',
  inputProtocol: 'anthropic',
  llmSwitch: {
    name: 'protocol-switch',
    transformer: {
      type: 'pass-through'
    }
  },
  compatibility: {
    configPath: './config/openai-passthrough.config.json'
  },
  provider: {
    name: 'openai',
    apiKey: 'your-api-key',
    apiEndpoint: 'https://api.openai.com/v1/chat/completions'
  }
};

// Create and execute pipeline
const pipeline = pipelineManager.createPipeline(config);
const result = await pipelineManager.executePipeline('anthropic-to-openai', {
  sourceProtocol: 'anthropic',
  targetProtocol: 'openai',
  data: {
    model: 'claude-3-5-sonnet-20240620',
    messages: [
      {
        role: 'user',
        content: 'Hello, world!'
      }
    ],
    max_tokens: 1024
  }
});

Key Components

Pipeline Nodes

  • LLMSwitchNode: Handles protocol field bidirectional conversion
  • WorkflowNode: Handles streaming responses for non-streaming requests
  • CompatibilityNode: Wraps compatibility transformations
  • ProviderNode: Communicates with actual AI service providers

Transformers

  • AnthropicTransformer: Converts between Anthropic API format and unified format
  • OpenAITransformer: Handles OpenAI API format with parameter validation
  • PassThroughTransformer: Transparent transmission with configurable adjustments
  • UnifiedChatRequest/Response: Standard formats for cross-provider compatibility

License

MIT

Keywords

pipeline

FAQs

Package last updated on 13 Sep 2025

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts