![PySpur](/statics/github-mark.png)
PySpur
Graph-Based Editor for LLM Workflows
Stars: 975
![screenshot](/screenshots_githubs/PySpur-Dev-PySpur.jpg)
PySpur is a graph-based editor designed for LLM workflows, offering modular building blocks for easy workflow creation and debugging at node level. It allows users to evaluate final performance and promises self-improvement features in the future. PySpur is easy-to-hack, supports JSON configs for workflow graphs, and is lightweight with minimal dependencies, making it a versatile tool for workflow management in the field of AI and machine learning.
README:
https://github.com/user-attachments/assets/9128885b-47ba-4fc6-ab6b-d567f52e332c
https://github.com/user-attachments/assets/6442f0ad-86d8-43d9-aa70-e5c01e55e876
https://github.com/user-attachments/assets/6e82ad25-2a46-4c50-b030-415ea9994690
https://github.com/user-attachments/assets/4dc2abc3-c6e6-4d6d-a5c3-787d518de7ae
https://github.com/user-attachments/assets/5bef7a16-ef9f-4650-b385-4ea70fa54c8a
- Easy-to-hack, eg., one can add new workflow nodes by simply creating a single Python file.
- JSON configs of workflow graphs, enabling easy sharing and version control.
- Lightweight via minimal dependencies, avoiding bloated LLM frameworks.
You can get PySpur up and running in three quick steps.
-
Clone the repository:
git clone https://github.com/PySpur-com/PySpur.git cd PySpur
-
Create a .env file:
Create a
.env
file at the root of the project. You may use.env.example
as a starting point. If you plan to use third party model providers, you can add their API keys in .env file in this step, OR we also do this another way in step 5. -
Start the docker services:
docker compose up --build -d
This will start a local instance of PySpur that will store spurs and their runs in a local SQLite file. Note: For some environments you may want to try:
sudo docker compose up --build -d
. -
Access the portal:
Go to
http://localhost:6080/
in your browser.Enter
pyspur
/canaryhattan
as username/password. -
Add your LLM provider keys:
Go to the settings menu on the top right corner of the portal
Select API keys tab
Enter your provider's key and click save (save button will appear after you add/modify a key)
Set up is completed. Click on "New Spur" to create a workflow, or start with one of the stock templates.
PySpur can work with local models served using Ollama.
Steps to configure PySpur to work with Ollama running on the same host.
To ensure Ollama API is reachable from PySpur, we need to start the Ollama service with environment variable OLLAMA_HOST=0.0.0.0
. This allows requests coming from PySpur docker's bridge network to get through to Ollama.
An easy way to do this is to launch the ollama service with the following command:
OLLAMA_HOST="0.0.0.0" ollama serve
Next up we need to update the OLLAMA_BASE_URL
environment value in the .env
file.
If your Ollama port is 11434 (the default port), then the entry in .env
file should look like this:
OLLAMA_BASE_URL=http://host.docker.internal:11434
(Please make sure that there is no trailing slash in the end!)
In PySpur's set up, host.docker.internal
refers to the host machine where both PySpur and Ollama are running.
Follow the usual steps to launch the PySpur app, starting with the command:
docker compose up --build -d
You will be able to select Ollama models [ollama/llama3.2
, ollama/llama3
, ...] from the sidebar for LLM nodes.
Please make sure the model you select is explicitly downloaded in ollama. That is, you will need to manually manage these models via ollama. To download a model you can simply run ollama pull <model-name>
.
PySpur only works with models that support structured-output and json mode. Most newer models should be good, but it would still be good to confirm this from Ollama documentation for the model you wish to use.
- [X] Canvas
- [X] Async/Batch Execution
- [X] Evals
- [X] Spur API
- [x] Support Ollama
- [ ] New Nodes
- [X] LLM Nodes
- [X] If-Else
- [X] Merge Branches
- [ ] Tools
- [ ] Loops
- [ ] Pipeline optimization via DSPy and related methods
- [ ] Templates
- [ ] Compile Spurs to Code
- [ ] Multimodal support
- [ ] Containerization of Code Verifiers
- [ ] Leaderboard
- [ ] Generate Spurs via AI
Your feedback will be massively appreciated. Please tell us which features on that list you like to see next or request entirely new ones.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for PySpur
Similar Open Source Tools
![PySpur Screenshot](/screenshots_githubs/PySpur-Dev-PySpur.jpg)
PySpur
PySpur is a graph-based editor designed for LLM workflows, offering modular building blocks for easy workflow creation and debugging at node level. It allows users to evaluate final performance and promises self-improvement features in the future. PySpur is easy-to-hack, supports JSON configs for workflow graphs, and is lightweight with minimal dependencies, making it a versatile tool for workflow management in the field of AI and machine learning.
![pyspur Screenshot](/screenshots_githubs/PySpur-Dev-pyspur.jpg)
pyspur
PySpur is a graph-based editor designed for LLM (Large Language Models) workflows. It offers modular building blocks, node-level debugging, and performance evaluation. The tool is easy to hack, supports JSON configs for workflow graphs, and is lightweight with minimal dependencies. Users can quickly set up PySpur by cloning the repository, creating a .env file, starting docker services, and accessing the portal. PySpur can also work with local models served using Ollama, with steps provided for configuration. The roadmap includes features like canvas, async/batch execution, support for Ollama, new nodes, pipeline optimization, templates, code compilation, multimodal support, and more.
![Whisper-WebUI Screenshot](/screenshots_githubs/jhj0517-Whisper-WebUI.jpg)
Whisper-WebUI
Whisper-WebUI is a Gradio-based browser interface for Whisper, serving as an Easy Subtitle Generator. It supports generating subtitles from various sources such as files, YouTube, and microphone. The tool also offers speech-to-text and text-to-text translation features, utilizing Facebook NLLB models and DeepL API. Users can translate subtitle files from other languages to English and vice versa. The project integrates faster-whisper for improved VRAM usage and transcription speed, providing efficiency metrics for optimized whisper models. Additionally, users can choose from different Whisper models based on size and language requirements.
![ComfyUI-BlenderAI-node Screenshot](/screenshots_githubs/AIGODLIKE-ComfyUI-BlenderAI-node.jpg)
ComfyUI-BlenderAI-node
ComfyUI-BlenderAI-node is an addon for Blender that allows users to convert ComfyUI nodes into Blender nodes seamlessly. It offers features such as converting nodes, editing launch arguments, drawing masks with Grease pencil, and more. Users can queue batch processing, use node tree presets, and model preview images. The addon enables users to input or replace 3D models in Blender and output controlnet images using composite. It provides a workflow showcase with presets for camera input, AI-generated mesh import, composite depth channel, character bone editing, and more.
![ChatGPT-desktop Screenshot](/screenshots_githubs/Macky94-ChatGPT-desktop.jpg)
ChatGPT-desktop
ChatGPT Desktop Application is a multi-platform tool that provides a powerful AI wrapper for generating text. It offers features like text-to-speech, exporting chat history in various formats, automatic application upgrades, system tray hover window, support for slash commands, customization of global shortcuts, and pop-up search. The application is built using Tauri and aims to enhance user experience by simplifying text generation tasks. It is available for Mac, Windows, and Linux, and is designed for personal learning and research purposes.
![open-parse Screenshot](/screenshots_githubs/Filimoa-open-parse.jpg)
open-parse
Open Parse is a Python library for visually discerning document layouts and chunking them effectively. It is designed to fill the gap in open-source libraries for handling complex documents. Unlike text splitting, which converts a file to raw text and slices it up, Open Parse visually analyzes documents for superior LLM input. It also supports basic markdown for parsing headings, bold, and italics, and has high-precision table support, extracting tables into clean Markdown formats with accuracy that surpasses traditional tools. Open Parse is extensible, allowing users to easily implement their own post-processing steps. It is also intuitive, with great editor support and completion everywhere, making it easy to use and learn.
![ComfyUI_VLM_nodes Screenshot](/screenshots_githubs/gokayfem-ComfyUI_VLM_nodes.jpg)
ComfyUI_VLM_nodes
ComfyUI_VLM_nodes is a repository containing various nodes for utilizing Vision Language Models (VLMs) and Language Models (LLMs). The repository provides nodes for tasks such as structured output generation, image to music conversion, LLM prompt generation, automatic prompt generation, and more. Users can integrate different models like InternLM-XComposer2-VL, UForm-Gen2, Kosmos-2, moondream1, moondream2, JoyTag, and Chat Musician. The nodes support features like extracting keywords, generating prompts, suggesting prompts, and obtaining structured outputs. The repository includes examples and instructions for using the nodes effectively.
![felafax Screenshot](/screenshots_githubs/felafax-felafax.jpg)
felafax
Felafax is a framework designed to tune LLaMa3.1 on Google Cloud TPUs for cost efficiency and seamless scaling. It provides a Jupyter notebook for continued-training and fine-tuning open source LLMs using XLA runtime. The goal of Felafax is to simplify running AI workloads on non-NVIDIA hardware such as TPUs, AWS Trainium, AMD GPU, and Intel GPU. It supports various models like LLaMa-3.1 JAX Implementation, LLaMa-3/3.1 PyTorch XLA, and Gemma2 Models optimized for Cloud TPUs with full-precision training support.
![Neurite Screenshot](/screenshots_githubs/satellitecomponent-Neurite.jpg)
Neurite
Neurite is an innovative project that combines chaos theory and graph theory to create a digital interface that explores hidden patterns and connections for creative thinking. It offers a unique workspace blending fractals with mind mapping techniques, allowing users to navigate the Mandelbrot set in real-time. Nodes in Neurite represent various content types like text, images, videos, code, and AI agents, enabling users to create personalized microcosms of thoughts and inspirations. The tool supports synchronized knowledge management through bi-directional synchronization between mind-mapping and text-based hyperlinking. Neurite also features FractalGPT for modular conversation with AI, local AI capabilities for multi-agent chat networks, and a Neural API for executing code and sequencing animations. The project is actively developed with plans for deeper fractal zoom, advanced control over node placement, and experimental features.
![DevoxxGenieIDEAPlugin Screenshot](/screenshots_githubs/devoxx-DevoxxGenieIDEAPlugin.jpg)
DevoxxGenieIDEAPlugin
Devoxx Genie is a Java-based IntelliJ IDEA plugin that integrates with local and cloud-based LLM providers to aid in reviewing, testing, and explaining project code. It supports features like code highlighting, chat conversations, and adding files/code snippets to context. Users can modify REST endpoints and LLM parameters in settings, including support for cloud-based LLMs. The plugin requires IntelliJ version 2023.3.4 and JDK 17. Building and publishing the plugin is done using Gradle tasks. Users can select an LLM provider, choose code, and use commands like review, explain, or generate unit tests for code analysis.
![BizyAir Screenshot](/screenshots_githubs/siliconflow-BizyAir.jpg)
BizyAir
BizyAir is a collection of ComfyUI nodes that help users overcome environmental and hardware limitations to generate high-quality content. It includes features such as ControlNet preprocessing, image background removal, photo-quality image generation, and animation super-resolution. Users can run ComfyUI anywhere without worrying about hardware requirements. Installation methods include using ComfyUI Manager, Comfy CLI, downloading standalone packages for Windows, or cloning the BizyAir repository into the custom_nodes subdirectory of ComfyUI.
![upscayl Screenshot](/screenshots_githubs/upscayl-upscayl.jpg)
upscayl
Upscayl is a free and open-source AI image upscaler that uses advanced AI algorithms to enlarge and enhance low-resolution images without losing quality. It is a cross-platform application built with the Linux-first philosophy, available on all major desktop operating systems. Upscayl utilizes Real-ESRGAN and Vulkan architecture for image enhancement, and its backend is fully open-source under the AGPLv3 license. It is important to note that a Vulkan compatible GPU is required for Upscayl to function effectively.
![personal-assistant Screenshot](/screenshots_githubs/edonyzpc-personal-assistant.jpg)
personal-assistant
Obsidian Personal Assistant is a plugin designed to help users manage their Obsidian notes more efficiently. It offers features like automatically creating notes in specified directories, opening related graph views, managing plugins and themes, setting graph view colors, and more. The plugin aims to streamline note-taking and organization within the Obsidian app, catering to users who seek automation and customization in their note management workflow.
![ProX Screenshot](/screenshots_githubs/GAIR-NLP-ProX.jpg)
ProX
ProX is a lm-based data refinement framework that automates the process of cleaning and improving data used in pre-training large language models. It offers better performance, domain flexibility, efficiency, and cost-effectiveness compared to traditional methods. The framework has been shown to improve model performance by over 2% and boost accuracy by up to 20% in tasks like math. ProX is designed to refine data at scale without the need for manual adjustments, making it a valuable tool for data preprocessing in natural language processing tasks.
![Devon Screenshot](/screenshots_githubs/entropy-research-Devon.jpg)
Devon
Devon is an open-source pair programmer tool designed to facilitate collaborative coding sessions. It provides features such as multi-file editing, codebase exploration, test writing, bug fixing, and architecture exploration. The tool supports Anthropic, OpenAI, and Groq APIs, with plans to add more models in the future. Devon is community-driven, with ongoing development goals including multi-model support, plugin system for tool builders, self-hostable Electron app, and setting SOTA on SWE-bench Lite. Users can contribute to the project by developing core functionality, conducting research on agent performance, providing feedback, and testing the tool.
![SecureAI-Tools Screenshot](/screenshots_githubs/SecureAI-Tools-SecureAI-Tools.jpg)
SecureAI-Tools
SecureAI Tools is a private and secure AI tool that allows users to chat with AI models, chat with documents (PDFs), and run AI models locally. It comes with built-in authentication and user management, making it suitable for family members or coworkers. The tool is self-hosting optimized and provides necessary scripts and docker-compose files for easy setup in under 5 minutes. Users can customize the tool by editing the .env file and enabling GPU support for faster inference. SecureAI Tools also supports remote OpenAI-compatible APIs, with lower hardware requirements for using remote APIs only. The tool's features wishlist includes chat sharing, mobile-friendly UI, and support for more file types and markdown rendering.
For similar tasks
![PySpur Screenshot](/screenshots_githubs/PySpur-Dev-PySpur.jpg)
PySpur
PySpur is a graph-based editor designed for LLM workflows, offering modular building blocks for easy workflow creation and debugging at node level. It allows users to evaluate final performance and promises self-improvement features in the future. PySpur is easy-to-hack, supports JSON configs for workflow graphs, and is lightweight with minimal dependencies, making it a versatile tool for workflow management in the field of AI and machine learning.
![airflow Screenshot](/screenshots_githubs/apache-airflow.jpg)
airflow
Apache Airflow (or simply Airflow) is a platform to programmatically author, schedule, and monitor workflows. When workflows are defined as code, they become more maintainable, versionable, testable, and collaborative. Use Airflow to author workflows as directed acyclic graphs (DAGs) of tasks. The Airflow scheduler executes your tasks on an array of workers while following the specified dependencies. Rich command line utilities make performing complex surgeries on DAGs a snap. The rich user interface makes it easy to visualize pipelines running in production, monitor progress, and troubleshoot issues when needed.
![rill-flow Screenshot](/screenshots_githubs/weibocom-rill-flow.jpg)
rill-flow
Rill Flow is a high-performance, scalable distributed workflow orchestration service that supports the execution of tens of millions of tasks per day with task execution latency less than 100ms. It is distributed and supports the orchestration and scheduling of heterogeneous distributed systems. Rill Flow is easy to use, supporting visual process orchestration and plug-in access. It is cloud native, allowing for cloud native container deployment and cloud native function orchestration. Additionally, Rill Flow supports rapid integration of LLM model services.
![pyspur Screenshot](/screenshots_githubs/PySpur-Dev-pyspur.jpg)
pyspur
PySpur is a graph-based editor designed for LLM (Large Language Models) workflows. It offers modular building blocks, node-level debugging, and performance evaluation. The tool is easy to hack, supports JSON configs for workflow graphs, and is lightweight with minimal dependencies. Users can quickly set up PySpur by cloning the repository, creating a .env file, starting docker services, and accessing the portal. PySpur can also work with local models served using Ollama, with steps provided for configuration. The roadmap includes features like canvas, async/batch execution, support for Ollama, new nodes, pipeline optimization, templates, code compilation, multimodal support, and more.
![Co-LLM-Agents Screenshot](/screenshots_githubs/UMass-Foundation-Model-Co-LLM-Agents.jpg)
Co-LLM-Agents
This repository contains code for building cooperative embodied agents modularly with large language models. The agents are trained to perform tasks in two different environments: ThreeDWorld Multi-Agent Transport (TDW-MAT) and Communicative Watch-And-Help (C-WAH). TDW-MAT is a multi-agent environment where agents must transport objects to a goal position using containers. C-WAH is an extension of the Watch-And-Help challenge, which enables agents to send messages to each other. The code in this repository can be used to train agents to perform tasks in both of these environments.
![GPT4Point Screenshot](/screenshots_githubs/Pointcept-GPT4Point.jpg)
GPT4Point
GPT4Point is a unified framework for point-language understanding and generation. It aligns 3D point clouds with language, providing a comprehensive solution for tasks such as 3D captioning and controlled 3D generation. The project includes an automated point-language dataset annotation engine, a novel object-level point cloud benchmark, and a 3D multi-modality model. Users can train and evaluate models using the provided code and datasets, with a focus on improving models' understanding capabilities and facilitating the generation of 3D objects.
![asreview Screenshot](/screenshots_githubs/asreview-asreview.jpg)
asreview
The ASReview project implements active learning for systematic reviews, utilizing AI-aided pipelines to assist in finding relevant texts for search tasks. It accelerates the screening of textual data with minimal human input, saving time and increasing output quality. The software offers three modes: Oracle for interactive screening, Exploration for teaching purposes, and Simulation for evaluating active learning models. ASReview LAB is designed to support decision-making in any discipline or industry by improving efficiency and transparency in screening large amounts of textual data.
![Groma Screenshot](/screenshots_githubs/FoundationVision-Groma.jpg)
Groma
Groma is a grounded multimodal assistant that excels in region understanding and visual grounding. It can process user-defined region inputs and generate contextually grounded long-form responses. The tool presents a unique paradigm for multimodal large language models, focusing on visual tokenization for localization. Groma achieves state-of-the-art performance in referring expression comprehension benchmarks. The tool provides pretrained model weights and instructions for data preparation, training, inference, and evaluation. Users can customize training by starting from intermediate checkpoints. Groma is designed to handle tasks related to detection pretraining, alignment pretraining, instruction finetuning, instruction following, and more.
For similar jobs
![weave Screenshot](/screenshots_githubs/wandb-weave.jpg)
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.
![LLMStack Screenshot](/screenshots_githubs/trypromptly-LLMStack.jpg)
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.
![VisionCraft Screenshot](/screenshots_githubs/VisionCraft-org-VisionCraft.jpg)
VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.
![kaito Screenshot](/screenshots_githubs/Azure-kaito.jpg)
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.
![PyRIT Screenshot](/screenshots_githubs/Azure-PyRIT.jpg)
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.
![tabby Screenshot](/screenshots_githubs/TabbyML-tabby.jpg)
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.
![spear Screenshot](/screenshots_githubs/isl-org-spear.jpg)
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.
![Magick Screenshot](/screenshots_githubs/Oneirocom-Magick.jpg)
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.