orch

Rust framework for LLM orchestration

Stars: 178

Visit

orch is a library for building language model powered applications and agents for the Rust programming language. It can be used for tasks such as text generation, streaming text generation, structured data generation, and embedding generation. The library provides functionalities for executing various language model tasks and can be integrated into different applications and contexts. It offers flexibility for developers to create language model-powered features and applications in Rust.

README:

orch

orch is a library for building language model powered applications and agents for the Rust programming language. It was primarily built for usage in magic-cli, but can be used in other contexts as well.

[!NOTE]

If the project gains traction, this can be compiled as an addon to other languages such as Python or a standalone WebAssembly module.

Installation

cargo add orch
cargo add orch_response

Alternatively, add orch as a dependency to your Cargo.toml file:

[dependencies]
orch = "*" # Substitute with the latest version
orch_response = "*" # Substitute with the latest version

Basic Usage

Simple Text Generation

use orch::execution::*;
use orch::lm::*;

#[tokio::main]
async fn main() {
  let lm = OllamaBuilder::new().try_build().unwrap();
  let executor = TextExecutorBuilder::new().with_lm(&lm).try_build().unwrap();
  let response = executor.execute("What is 2+2?").await.expect("Execution failed");
  println!("{}", response.content);
}

Streaming Text Generation

use orch::execution::*;
use orch::lm::*;
use tokio_stream::StreamExt;

#[tokio::main]
async fn main() {
  let lm = OllamaBuilder::new().try_build().unwrap();
  let executor = TextExecutorBuilder::new().with_lm(&lm).try_build().unwrap();
  let mut response = executor.execute_stream("What is 2+2?").await.expect("Execution failed");
  while let Some(chunk) = response.stream.next().await {
    match chunk {
      Ok(chunk) => print!("{chunk}"),
      Err(e) => {
        println!("Error: {e}");
        break;
      }
    }
  }
  println!();
}

Structured Data Generation

use orch::execution::*;
use orch::lm::*;
use orch::response::*;

#[derive(Variants, serde::Deserialize)]
pub enum ResponseVariants {
    Answer(AnswerResponseVariant),
    Fail(FailResponseVariant),
}

#[derive(Variant, serde::Deserialize)]
#[variant(
    variant = "Answer",
    scenario = "You know the capital city of the country",
    description = "Capital city of the country"
)]
pub struct AnswerResponseVariant {
    #[schema(
        description = "Capital city of the received country",
        example = "London"
    )]
    pub capital: String,
}

#[derive(Variant, serde::Deserialize)]
#[variant(
    variant = "Fail",
    scenario = "You don't know the capital city of the country",
    description = "Reason why the capital city is not known"
)]
pub struct FailResponseVariant {
    #[schema(
        description = "Reason why the capital city is not known",
        example = "Country 'foobar' does not exist"
    )]
    pub reason: String,
}

#[tokio::main]
async fn main() {
    let lm = OllamaBuilder::new().try_build().unwrap();
    let executor = StructuredExecutorBuilder::new()
    .with_lm(&lm)
    .with_preamble("You are a geography expert who helps users understand the capital city of countries around the world.")
		.with_options(Box::new(variants!(ResponseVariants)))
    .try_build()
    .unwrap();
    let response = executor
        .execute("What is the capital of Fooland?")
        .await
        .expect("Execution failed");

    println!("Response:");
    match response.content {
        ResponseVariants::Answer(answer) => {
            println!("Capital city: {}", answer.capital);
        }
        ResponseVariants::Fail(fail) => {
            println!("Model failed to generate a response: {}", fail.reason);
        }
    }
}

Embedding Generation

use orch::execution::*;
use orch::lm::*;

#[tokio::main]
async fn main() {
  let lm = OllamaBuilder::new().try_build().unwrap();
  let executor = TextExecutorBuilder::new()
    .with_lm(&lm)
    .try_build()
    .unwrap();
  let embedding = executor
    .generate_embedding("Phrase to generate an embedding for")
    .await
    .expect("Execution failed");

  println!("Embedding:");
  println!("{:?}", embedding);
}

More Examples

See the examples directory for usage examples.

For Tasks:

Click tags to check more tools for each tasks

generate text stream text generate structured data generate embedding execute language model tasks

For Jobs:

software developer data scientist machine learning engineer ai researcher natural language processing engineer

Alternative AI tools for orch

Similar Open Source Tools

orch

github

: 178

agent-kit

AgentKit is a framework for creating and orchestrating AI Agents, enabling developers to build, test, and deploy reliable AI applications at scale. It allows for creating networked agents with separate tasks and instructions to solve specific tasks, as well as simple agents for tasks like writing content. The framework requires the Inngest TypeScript SDK as a dependency and provides documentation on agents, tools, network, state, and routing. Example projects showcase AgentKit in action, such as the Test Writing Network demo using Workflow Kit, Supabase, and OpenAI.

github

: 603

modelfusion

ModelFusion is an abstraction layer for integrating AI models into JavaScript and TypeScript applications, unifying the API for common operations such as text streaming, object generation, and tool usage. It provides features to support production environments, including observability hooks, logging, and automatic retries. You can use ModelFusion to build AI applications, chatbots, and agents. ModelFusion is a non-commercial open source project that is community-driven. You can use it with any supported provider. ModelFusion supports a wide range of models including text generation, image generation, vision, text-to-speech, speech-to-text, and embedding models. ModelFusion infers TypeScript types wherever possible and validates model responses. ModelFusion provides an observer framework and logging support. ModelFusion ensures seamless operation through automatic retries, throttling, and error handling mechanisms. ModelFusion is fully tree-shakeable, can be used in serverless environments, and only uses a minimal set of dependencies.

github

: 918

lagent

Lagent is a lightweight open-source framework that allows users to efficiently build large language model(LLM)-based agents. It also provides some typical tools to augment LLM. The overview of our framework is shown below:

github

: 2.1k

openapi

The `@samchon/openapi` repository is a collection of OpenAPI types and converters for various versions of OpenAPI specifications. It includes an 'emended' OpenAPI v3.1 specification that enhances clarity by removing ambiguous and duplicated expressions. The repository also provides an application composer for LLM (Large Language Model) function calling from OpenAPI documents, allowing users to easily perform LLM function calls based on the Swagger document. Conversions to different versions of OpenAPI documents are also supported, all based on the emended OpenAPI v3.1 specification. Users can validate their OpenAPI documents using the `typia` library with `@samchon/openapi` types, ensuring compliance with standard specifications.

github

: 89

jsgrad

jsgrad is a modern ML library for JavaScript and TypeScript that aims to provide a fast and efficient way to run and train machine learning models. It is a rewrite of tinygrad in TypeScript, offering a clean and modern API with zero dependencies. The library supports multiple runtime backends such as WebGPU, WASM, and CLANG, making it versatile for various applications in browser and server environments. With a focus on simplicity and performance, jsgrad is designed to be easy to use for both model inference and training tasks.

github

: 54

DeRTa

DeRTa (Refuse Whenever You Feel Unsafe) is a tool designed to improve safety in Large Language Models (LLMs) by training them to refuse compliance at any response juncture. The tool incorporates methods such as MLE with Harmful Response Prefix and Reinforced Transition Optimization (RTO) to address refusal positional bias and strengthen the model's capability to transition from potential harm to safety refusal. DeRTa provides training data, model weights, and evaluation scripts for LLMs, enabling users to enhance safety in language generation tasks.

github

: 59

Janus

Janus is a series of unified multimodal understanding and generation models, including Janus-Pro, Janus, and JanusFlow. Janus-Pro is an advanced version that improves both multimodal understanding and visual generation significantly. Janus decouples visual encoding for unified multimodal understanding and generation, surpassing previous models. JanusFlow harmonizes autoregression and rectified flow for unified multimodal understanding and generation, achieving comparable or superior performance to specialized models. The models are available for download and usage, supporting a broad range of research in academic and commercial communities.

github

: 1.4k

bosquet

Bosquet is a tool designed for LLMOps in large language model-based applications. It simplifies building AI applications by managing LLM and tool services, integrating with Selmer templating library for prompt templating, enabling prompt chaining and composition with Pathom graph processing, defining agents and tools for external API interactions, handling LLM memory, and providing features like call response caching. The tool aims to streamline the development process for AI applications that require complex prompt templates, memory management, and interaction with external systems.

github

: 329

ai

The Vercel AI SDK is a library for building AI-powered streaming text and chat UIs. It provides React, Svelte, Vue, and Solid helpers for streaming text responses and building chat and completion UIs. The SDK also includes a React Server Components API for streaming Generative UI and first-class support for various AI providers such as OpenAI, Anthropic, Mistral, Perplexity, AWS Bedrock, Azure, Google Gemini, Hugging Face, Fireworks, Cohere, LangChain, Replicate, Ollama, and more. Additionally, it offers Node.js, Serverless, and Edge Runtime support, as well as lifecycle callbacks for saving completed streaming responses to a database in the same request.

github

: 21.9k

llm.nvim

llm.nvim is a neovim plugin designed for LLM-assisted programming. It provides a no-frills approach to integrating language model assistance into the coding workflow. Users can configure the plugin to interact with various AI services such as GROQ, OpenAI, and Anthropics. The plugin offers functions to trigger the LLM assistant, create new prompt files, and customize key bindings for seamless interaction. With a focus on simplicity and efficiency, llm.nvim aims to enhance the coding experience by leveraging AI capabilities within the neovim environment.

github

: 177

dynamiq

Dynamiq is an orchestration framework designed to streamline the development of AI-powered applications, specializing in orchestrating retrieval-augmented generation (RAG) and large language model (LLM) agents. It provides an all-in-one Gen AI framework for agentic AI and LLM applications, offering tools for multi-agent orchestration, document indexing, and retrieval flows. With Dynamiq, users can easily build and deploy AI solutions for various tasks.

github

: 1.0k

x

Ant Design X is a tool for crafting AI-driven interfaces effortlessly. It is built on the best practices of enterprise-level AI products, offering flexible and diverse atomic components for various AI dialogue scenarios. The tool provides out-of-the-box model integration with inference services compatible with OpenAI standards. It also enables efficient management of conversation data flows, supports rich template options, complete TypeScript support, and advanced theme customization. Ant Design X is designed to enhance development efficiency and deliver exceptional AI interaction experiences.

github

: 3.7k

ollama-ex

Ollama is a powerful tool for running large language models locally or on your own infrastructure. It provides a full implementation of the Ollama API, support for streaming requests, and tool use capability. Users can interact with Ollama in Elixir to generate completions, chat messages, and perform streaming requests. The tool also supports function calling on compatible models, allowing users to define tools with clear descriptions and arguments. Ollama is designed to facilitate natural language processing tasks and enhance user interactions with language models.

github

: 127

bellman

Bellman is a unified interface to interact with language and embedding models, supporting various vendors like VertexAI/Gemini, OpenAI, Anthropic, VoyageAI, and Ollama. It consists of a library for direct interaction with models and a service 'bellmand' for proxying requests with one API key. Bellman simplifies switching between models, vendors, and common tasks like chat, structured data, tools, and binary input. It addresses the lack of official SDKs for major players and differences in APIs, providing a single proxy for handling different models. The library offers clients for different vendors implementing common interfaces for generating and embedding text, enabling easy interchangeability between models.

github

: 57

Ollama

Ollama SDK for .NET is a fully generated C# SDK based on OpenAPI specification using OpenApiGenerator. It supports automatic releases of new preview versions, source generator for defining tools natively through C# interfaces, and all modern .NET features. The SDK provides support for all Ollama API endpoints including chats, embeddings, listing models, pulling and creating new models, and more. It also offers tools for interacting with weather data and providing weather-related information to users.

github

: 134

For similar tasks

orch

github

: 178

bce-qianfan-sdk

The Qianfan SDK provides best practices for large model toolchains, allowing AI workflows and AI-native applications to access the Qianfan large model platform elegantly and conveniently. The core capabilities of the SDK include three parts: large model reasoning, large model training, and general and extension: * `Large model reasoning`: Implements interface encapsulation for reasoning of Yuyan (ERNIE-Bot) series, open source large models, etc., supporting dialogue, completion, Embedding, etc. * `Large model training`: Based on platform capabilities, it supports end-to-end large model training process, including training data, fine-tuning/pre-training, and model services. * `General and extension`: General capabilities include common AI development tools such as Prompt/Debug/Client. The extension capability is based on the characteristics of Qianfan to adapt to common middleware frameworks.

github

: 342

Ollama

github

: 134

instructor-js

Instructor is a Typescript library for structured extraction in Typescript, powered by llms, designed for simplicity, transparency, and control. It stands out for its simplicity, transparency, and user-centric design. Whether you're a seasoned developer or just starting out, you'll find Instructor's approach intuitive and steerable.

github

: 299

awesome-ai-repositories

A curated list of open source repositories for AI Engineers. The repository provides a comprehensive collection of tools and frameworks for various AI-related tasks such as AI Gateway, AI Workload Manager, Copilot Development, Dataset Engineering, Evaluation, Fine Tuning, Function Calling, Graph RAG, Guardrails, Local Model Inference, LLM Agent Framework, Model Serving, Observability, Pre Training, Prompt Engineering, RAG Framework, Security, Structured Extraction, Structured Generation, Vector DB, and Voice Agent.

github

: 73

trex

Trex is a tool that transforms unstructured data into structured data by specifying a regex or context-free grammar. It intelligently restructures data to conform to the defined schema. It offers a Python client for installation and requires an API key obtained by signing up at automorphic.ai. The tool supports generating structured JSON objects based on user-defined schemas and prompts. Trex aims to provide significant speed improvements, structured custom CFG and regex generation, and generation from JSON schema. Future plans include auto-prompt generation for unstructured ETL and more intelligent models.

github

: 239

datalore-localgen-cli

Datalore is a terminal tool for generating structured datasets from local files like PDFs, Word docs, images, and text. It extracts content, uses semantic search to understand context, applies instructions through a generated schema, and outputs clean, structured data. Perfect for converting raw or unstructured local documents into ready-to-use datasets for training, analysis, or experimentation, all without manual formatting.

github

: 73

LLMStack

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

github

: 1.5k

For similar jobs

weave

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

github

: 1.1k

LLMStack

github

: 1.5k

VisionCraft

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

github

: 94

kaito

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

github

: 405

PyRIT

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

github

: 2.9k

tabby

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

github

: 32.9k

spear

SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

github

: 224

Magick

Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.

github

: 675