DeepEval
DeepEval is a simple-to-use, open source LLM evaluation framework, for evaluating and testing large-language model systems. It is similar to Pytest but specialized for unit testing LLM outputs. DeepEval incorporates the latest research to evaluate LLM outputs based on metrics such as G-Eval, hallucination, answer relevancy, RAGAS, etc., which uses LLMs and various other NLP models that run locally on your machine for evaluation. Whether your application is implemented via RAG or fine-tuning, LangChain, or LlamaIndex, DeepEval has you covered. With it, you can easily determine the optimal hyperparameters to improve your RAG pipeline, prevent prompt drifting, or even transition from OpenAI to hosting your own Llama2 with confidence. The framework supports synthetic dataset generation with advanced evolution techniques and integrates seamlessly with popular frameworks, allowing for efficient benchmarking and optimization of LLM systems.
Learn more
ChainForge
ChainForge is an open-source visual programming environment designed for prompt engineering and large language model evaluation. It enables users to assess the robustness of prompts and text-generation models beyond anecdotal evidence. Simultaneously test prompt ideas and variations across multiple LLMs to identify the most effective combinations. Evaluate response quality across different prompts, models, and settings to select the optimal configuration for specific use cases. Set up evaluation metrics and visualize results across prompts, parameters, models, and settings, facilitating data-driven decision-making. Manage multiple conversations simultaneously, template follow-up messages, and inspect outputs at each turn to refine interactions. ChainForge supports various model providers, including OpenAI, HuggingFace, Anthropic, Google PaLM2, Azure OpenAI endpoints, and locally hosted models like Alpaca and Llama. Users can adjust model settings and utilize visualization nodes.
Learn more
OpenPipe
OpenPipe provides fine-tuning for developers. Keep your datasets, models, and evaluations all in one place. Train new models with the click of a button. Automatically record LLM requests and responses. Create datasets from your captured data. Train multiple base models on the same dataset. We serve your model on our managed endpoints that scale to millions of requests. Write evaluations and compare model outputs side by side. Change a couple of lines of code, and you're good to go. Simply replace your Python or Javascript OpenAI SDK and add an OpenPipe API key. Make your data searchable with custom tags. Small specialized models cost much less to run than large multipurpose LLMs. Replace prompts with models in minutes, not weeks. Fine-tuned Mistral and Llama 2 models consistently outperform GPT-4-1106-Turbo, at a fraction of the cost. We're open-source, and so are many of the base models we use. Own your own weights when you fine-tune Mistral and Llama 2, and download them at any time.
Learn more
Selene 1
Atla's Selene 1 API offers state-of-the-art AI evaluation models, enabling developers to define custom evaluation criteria and obtain precise judgments on their AI applications' performance. Selene outperforms frontier models on commonly used evaluation benchmarks, ensuring accurate and reliable assessments. Users can customize evaluations to their specific use cases through the Alignment Platform, allowing for fine-grained analysis and tailored scoring formats. The API provides actionable critiques alongside accurate evaluation scores, facilitating seamless integration into existing workflows. Pre-built metrics, such as relevance, correctness, helpfulness, faithfulness, logical coherence, and conciseness, are available to address common evaluation scenarios, including detecting hallucinations in retrieval-augmented generation applications or comparing outputs to ground truth data.
Learn more
