MakRoya/YiVal

🚀 Evaluate and Evolve.🚀 YiVal is an open-source GenAI-Ops tool for tuning and evaluating prompts, configurations, and model parameters using customizable datasets, evaluation methods, and improvement strategies.

🧚🏻‍️ YiVal

Website · Producthunt · Documentation

⚡ Build any Generative AI application with evaluation and improvement ⚡

👉 Follow us: |

🤔 What is YiVal?

YiVal is an GenAI-Ops framework that allows you to iteratively tune your Generative AI model metadata, params, prompts and retrieval configs all at once with your preferred choices of test dataset generation, evaluation algorithms and improvement strategies.

Check out our quickstart guide! →

📣 What's Next?

Expected Features in Sep

• Add ROUGE and BERTScore evaluators
• Add support to midjourney
• Add support to LLaMA2-70B, LLaMA2-7B, Falcon-40B,
• Support LoRA fine-tune to open source models

🚀 Features

	🔧 Experiment Mode:	🤖 Agent Mode (Auto-prompting):
Workflow	Define your AI/ML application ➡️ Define test dataset ➡️ Evaluate 🔄 Improve ➡️ Prompt related artifacts built ✅	Define your AI/ML application ➡️ Auto-prompting ➡️ Prompt related artifacts built ✅
Features	🌟 Streamlined prompt development process 🌟 Support for multimedia and multimodel 🌟 Support CSV upload and GPT4 generated test data 🌟 Dashboard tracking latency, price and evaluator results 🌟 Human(RLHF) and algorithm based improvers 🌟 Service with detailed web view 🌟 Customizable evaluators and improvers	🌟 Non-code experience of Gen-AI application build 🌟 Witness your Gen-AI application born and improve with just one click

Model Support matrix

We support 100+ LLM ( gpt-4 , gpt-3.5-turbo , llama e.g.).

Different Model sources can be viewed as follow

Model	llm-Evaluate	Human-Evaluate	Variation Generate	Custom func
OpenAI	✅	✅	✅	✅
Azure	✅	✅	✅	✅
TogetherAI	✅	✅	✅	✅
Cohere	✅	✅	✅	✅
Huggingface	✅	✅	✅	✅
Anthropic	✅	✅	✅	✅
MidJourney		✅		✅

To support different models in custom func(e.g. Model Comparison) , follow our example

To support different models in evaluators and generators , check our config

Installation

pip install yival

Demo

Colab

Demo	Supported Features	Colab Link
🐯 Animal story with MidJourney	Multi-modal support of text and images
🌟 Model Comparison in QA ability	Easy model evaluation comparison thanks to LiteLLM
🔥 Startup Company Headline Generation Bot	Automated prompt evolution
🧳 Build Your Customized Travel Guide Bot	Automate prompt generation with retrieval methods
📖 Enhance Model Translation Capabilities	Finetune the translation performance of llama2 with replicate

Multi-model Mode

Yival has multimodal capabilities and can handle generated images in AIGC really well.

Find more information in the Animal story demo we provided.

yival run demo/configs/animal_story.yml

Basic Interactive Mode

To get started with a demo for basic interactive mode of YiVal, run the following command:

yival demo --auto_prompts

Once started, navigate to the following address in your web browser:

http://127.0.0.1:8073/interactive

Click to view the screenshot

For more details on this demo, check out the Basic Interactive Mode Demo.

Question Answering with expected result evaluator

yival demo --qa_expected_results

Once started, navigate to the following address in your web browser: http://127.0.0.1:8073/

Click to view the screenshot

For more details, check out the Question Answering with expected result evaluator.

Automatically generate prompts with evaluator

yival demo --basic_interactive

Once started, navigate to the following address in your web browser: http://127.0.0.1:8073/

Click to view the screenshot

Contributors

🌟 YiVal welcomes your contributions! 🌟

🥳 Thanks so much to all of our amazing contributors 🥳

Paper Implement

Paper	Author	Topics	YiVal Contributor
Large Language Models Are Human-Level Prompt Engineers	Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han	YiVal Evolver,Auto-Prompting	@Tao Feng
BERTScore: Evaluating Text Generation with BERT	Tianyi Zhang, Varsha Kishore, Felix Wu	YiVal Evaluator, bertscore, rouge	@crazycth