Best AI tools for< Test Locally >

Ollama is an AI tool that allows users to access and utilize large language models such as Llama 3, Phi 3, Mistral, Gemma 2, and more. Users can customize and create their own models. The tool is available for macOS, Linux, and Windows platforms, offering a preview version for users to explore and utilize these models for various applications.

MacWhisper is a native macOS application that utilizes OpenAI's Whisper technology for transcribing audio files into text. It offers a user-friendly interface for recording, transcribing, and editing audio, making it suitable for various use cases such as transcribing meetings, lectures, interviews, and podcasts. The application is designed to protect user privacy by performing all transcriptions locally on the device, ensuring that no data leaves the user's machine.

Hanabi.rest is an AI-based API building platform that allows users to create REST APIs from natural language and screenshots using AI technology. Users can deploy the APIs on Cloudflare Workers and roll them out globally. The platform offers a live editor for testing database access and API endpoints, generates code compatible with various runtimes, and provides features like sharing APIs via URL, npm package integration, and CLI dump functionality. Hanabi.rest simplifies API design and deployment by leveraging natural language processing, image recognition, and v0.dev components.

AI Generated Test Cases is an innovative tool that leverages artificial intelligence to automatically generate test cases for software applications. By utilizing advanced algorithms and machine learning techniques, this tool can efficiently create a comprehensive set of test scenarios to ensure the quality and reliability of software products. With AI Generated Test Cases, software development teams can save time and effort in the testing phase, leading to faster release cycles and improved overall productivity.

AI Test Kitchen is a website that provides a variety of AI-powered tools for creative professionals. These tools can be used to generate images, music, and text, as well as to explore different creative concepts. The website is designed to be a place where users can experiment with AI and learn how to use it to enhance their creative process.

Face Symmetry Test is an AI-powered tool that analyzes the symmetry of facial features by detecting key landmarks such as eyes, nose, mouth, and chin. Users can upload a photo to receive a personalized symmetry score, providing insights into the balance and proportion of their facial features. The tool uses advanced AI algorithms to ensure accurate results and offers guidelines for improving the accuracy of the analysis. Face Symmetry Test is free to use and prioritizes user privacy and security by securely processing uploaded photos without storing or sharing data with third parties.

The AI-powered Cambridge English Test platform offers exercises for English levels B1, B2, C1, and C2. Users can select exercise types such as Reading and Use of English, including activities like Open Cloze, Multiple Choice, Word Formation, and more. The AI, developed by Shining Apps in partnership with Use of English PRO, provides a unique learning experience by generating exercises from a database of over 5000 official exams. It uses advanced Natural Language Processing (NLP) to understand context, tweak exercises, and offer detailed feedback for effective learning.

FaceSymAI is an online tool that utilizes advanced AI algorithms to analyze and determine the symmetry of your face. By uploading a photo, the AI examines your facial features, including the eyes, nose, mouth, and overall structure, to provide an accurate assessment of your facial symmetry. The analysis is based on mathematical and statistical methods, ensuring reliable and precise results. FaceSymAI is designed to be user-friendly and accessible, offering a free service to everyone. The uploaded photos are treated with utmost confidentiality and are not stored or used for any other purpose, ensuring your privacy is respected.

Thumblytics is a tool that helps YouTubers test their YouTube thumbnails and titles before they publish them. It uses a combination of machine learning and human feedback to help users choose the best thumbnail and title combination for their videos. Thumblytics is designed to be easy to use, even for beginners. Users simply upload their thumbnail and title variants to Thumblytics, and the tool will preview them in a YouTube template and show them to hundreds of real people to collect click data. Thumblytics then crunches the data to help users pick the highest click-through rate (CTR) thumbnail and title.

ILoveMyQA is an AI-powered QA testing service that provides comprehensive, well-documented bug reports. The service is affordable, easy to get started with, and requires no time-zapping chats. ILoveMyQA's team of Rockstar QAs is dedicated to helping businesses find and fix bugs before their customers do, so they can enjoy the results and benefits of having a QA team without the cost, management, and headaches.

Checkmyidea-IA is an AI-powered tool that helps entrepreneurs and businesses evaluate their business ideas before launching them. It uses a variety of factors, such as customer interest, uniqueness, initial product development, and launch strategy, to provide users with a comprehensive review of their idea's potential for success. Checkmyidea-IA can help users save time, increase their chances of success, reduce risk, and improve their decision-making.

The website is a platform where users can submit fake hacker news for testing purposes. Users can log in to submit their titles and test their submissions. The platform allows users to see how readers may respond to their posts. The website was built by Justin and Michael.

bottest.ai is an AI-powered chatbot testing tool that focuses on ensuring quality, reliability, and safety in AI-based chatbots. The tool offers automated testing capabilities without the need for coding, making it easy for users to test their chatbots efficiently. With features like regression testing, performance testing, multi-language testing, and AI-powered coverage, bottest.ai provides a comprehensive solution for testing chatbots. Users can record tests, evaluate responses, and improve their chatbots based on analytics provided by the tool. The tool also supports enterprise readiness by allowing scalability, permissions management, and integration with existing workflows.

Quizbot.ai is an advanced AI question generator designed to revolutionize the process of question and exam development. It offers a cutting-edge artificial intelligence system that can generate various types of questions from different sources like PDFs, Word documents, videos, images, and more. Quizbot.ai is a versatile tool that caters to multiple languages and question types, providing a personalized and engaging learning experience for users across various industries. The platform ensures scalability, flexibility, and personalized assessments, along with detailed analytics and insights to track learner performance. Quizbot.ai is secure, user-friendly, and offers a range of subscription plans to suit different needs.

ACCELQ is a powerful AI-driven test automation platform that offers codeless automation for web, desktop, mobile, and API testing. It provides a unified platform for continuous delivery, full-stack automation, and manual testing integration. ACCELQ is known for its industry-first no-code, no-setup mobile automation platform and comprehensive API automation capabilities. The platform is designed to handle real-world complexities with zero coding required, making it intuitive and scalable for businesses of all sizes.

Symflower is an AI-powered unit test generator for Java applications. It helps developers write and maintain test code with ease, saving time and improving code quality. Symflower works with JUnit 4 and JUnit 5 for Java, Spring, and Spring Boot applications.

Contentable.ai is a platform for comparing multiple AI models, rapidly moving from prototyping to production, and management of your custom AI solutions across multiple vendors. It allows users to test multiple AI models in seconds, compare models side-by-side across top AI providers, collaborate on AI models with their team seamlessly, design complex AI workflows without coding, and pay as they go.

PrepGenius.ai is an AI-driven test preparation platform designed to revolutionize the way students prepare for AP courses, college admission tests, and more. The platform offers personalized study plans, real-time feedback, interactive learning tools, and comprehensive resources to help students understand their strengths and weaknesses. With PrepGenius.ai, students can study smarter, receive tailored feedback, and track their progress to improve their test scores effectively.

Diffblue Cover is an autonomous AI-powered unit test writing tool for Java development teams. It uses next-generation autonomous AI to automate unit testing, freeing up developers to focus on more creative work. Diffblue Cover can write a complete and correct Java unit test every 2 seconds, and it is directly integrated into CI pipelines, unlike AI-powered code suggestions that require developers to check the code for bugs. Diffblue Cover is trusted by the world's leading organizations, including Goldman Sachs, and has been proven to improve quality, lower developer effort, help with code understanding, reduce risk, and increase deployment frequency.

Virtuoso is an AI-powered, end-to-end functional testing tool for web applications. It uses Natural Language Programming, Machine Learning, and Robotic Process Automation to automate the testing process, making it faster and more efficient. Virtuoso can be used by QA managers, practitioners, and senior executives to improve the quality of their software applications.

This Helm chart bootstraps an Airflow deployment on a Kubernetes cluster using the Helm package manager. The version of this chart does not correlate to any other component. Users should not expect feature parity between OSS airflow chart and the Astronomer airflow-chart for identical version numbers. To install this helm chart remotely (using helm 3) kubectl create namespace airflow helm repo add astronomer https://helm.astronomer.io helm install airflow --namespace airflow astronomer/airflow To install this repository from source sh kubectl create namespace airflow helm install --namespace airflow . Prerequisites: Kubernetes 1.12+ Helm 3.6+ PV provisioner support in the underlying infrastructure Installing the Chart: sh helm install --name my-release . The command deploys Airflow on the Kubernetes cluster in the default configuration. The Parameters section lists the parameters that can be configured during installation. Upgrading the Chart: First, look at the updating documentation to identify any backwards-incompatible changes. To upgrade the chart with the release name `my-release`: sh helm upgrade --name my-release . Uninstalling the Chart: To uninstall/delete the `my-release` deployment: sh helm delete my-release The command removes all the Kubernetes components associated with the chart and deletes the release. Updating DAGs: Bake DAGs in Docker image The recommended way to update your DAGs with this chart is to build a new docker image with the latest code (`docker build -t my-company/airflow:8a0da78 .`), push it to an accessible registry (`docker push my-company/airflow:8a0da78`), then update the Airflow pods with that image: sh helm upgrade my-release . --set images.airflow.repository=my-company/airflow --set images.airflow.tag=8a0da78 Docker Images: The Airflow image that are referenced as the default values in this chart are generated from this repository: https://github.com/astronomer/ap-airflow. Other non-airflow images used in this chart are generated from this repository: https://github.com/astronomer/ap-vendor. Parameters: The complete list of parameters supported by the community chart can be found on the Parameteres Reference page, and can be set under the `airflow` key in this chart. The following tables lists the configurable parameters of the Astronomer chart and their default values. | Parameter | Description | Default | | :----------------------------- | :-------------------------------------------------------------------------------------------------------- | :---------------------------- | | `ingress.enabled` | Enable Kubernetes Ingress support | `false` | | `ingress.acme` | Add acme annotations to Ingress object | `false` | | `ingress.tlsSecretName` | Name of secret that contains a TLS secret | `~` | | `ingress.webserverAnnotations` | Annotations added to Webserver Ingress object | `{}` | | `ingress.flowerAnnotations` | Annotations added to Flower Ingress object | `{}` | | `ingress.baseDomain` | Base domain for VHOSTs | `~` | | `ingress.auth.enabled` | Enable auth with Astronomer Platform | `true` | | `extraObjects` | Extra K8s Objects to deploy (these are passed through `tpl`). More about Extra Objects. | `[]` | | `sccEnabled` | Enable security context constraints required for OpenShift | `false` | | `authSidecar.enabled` | Enable authSidecar | `false` | | `authSidecar.repository` | The image for the auth sidecar proxy | `nginxinc/nginx-unprivileged` | | `authSidecar.tag` | The image tag for the auth sidecar proxy | `stable` | | `authSidecar.pullPolicy` | The K8s pullPolicy for the the auth sidecar proxy image | `IfNotPresent` | | `authSidecar.port` | The port the auth sidecar exposes | `8084` | | `gitSyncRelay.enabled` | Enables git sync relay feature. | `False` | | `gitSyncRelay.repo.url` | Upstream URL to the git repo to clone. | `~` | | `gitSyncRelay.repo.branch` | Branch of the upstream git repo to checkout. | `main` | | `gitSyncRelay.repo.depth` | How many revisions to check out. Leave as default `1` except in dev where history is needed. | `1` | | `gitSyncRelay.repo.wait` | Seconds to wait before pulling from the upstream remote. | `60` | | `gitSyncRelay.repo.subPath` | Path to the dags directory within the git repository. | `~` | Specify each parameter using the `--set key=value[,key=value]` argument to `helm install`. For example, sh helm install --name my-release --set executor=CeleryExecutor --set enablePodLaunching=false . Walkthrough using kind: Install kind, and create a cluster We recommend testing with Kubernetes 1.25+, example: sh kind create cluster --image kindest/node:v1.25.11 Confirm it's up: sh kubectl cluster-info --context kind-kind Add Astronomer's Helm repo sh helm repo add astronomer https://helm.astronomer.io helm repo update Create namespace + install the chart sh kubectl create namespace airflow helm install airflow -n airflow astronomer/airflow It may take a few minutes. Confirm the pods are up: sh kubectl get pods --all-namespaces helm list -n airflow Run `kubectl port-forward svc/airflow-webserver 8080:8080 -n airflow` to port-forward the Airflow UI to http://localhost:8080/ to confirm Airflow is working. Login as _admin_ and password _admin_. Build a Docker image from your DAGs: 1. Start a project using astro-cli, which will generate a Dockerfile, and load your DAGs in. You can test locally before pushing to kind with `astro airflow start`. `sh mkdir my-airflow-project && cd my-airflow-project astro dev init` 2. Then build the image: `sh docker build -t my-dags:0.0.1 .` 3. Load the image into kind: `sh kind load docker-image my-dags:0.0.1` 4. Upgrade Helm deployment: sh helm upgrade airflow -n airflow --set images.airflow.repository=my-dags --set images.airflow.tag=0.0.1 astronomer/airflow Extra Objects: This chart can deploy extra Kubernetes objects (assuming the role used by Helm can manage them). For Astronomer Cloud and Enterprise, the role permissions can be found in the Commander role. yaml extraObjects: - apiVersion: batch/v1beta1 kind: CronJob metadata: name: "{{ .Release.Name }}-somejob" spec: schedule: "*/10 * * * *" concurrencyPolicy: Forbid jobTemplate: spec: template: spec: containers: - name: myjob image: ubuntu command: - echo args: - hello restartPolicy: OnFailure Contributing: Check out our contributing guide! License: Apache 2.0 with Commons Clause

This repository contains documentation for the AI on the Edge Device Project. Users can edit Markdown documents in the 'docs' folder, create Pull Requests to merge changes, and Github Actions will regenerate the documentation on the 'gh-pages' branch. The documentation includes parameter documentation, template generation for new parameters, formatting options like boxes using the admonition extension, and local testing instructions using MkDocs.

The user interface (and the main server) of the simulator of aids and social benefits for young people. It is based on the free socio-fiscal simulator Openfisca.

Obsei is an open-source, low-code, AI powered automation tool that consists of an Observer to collect unstructured data from various sources, an Analyzer to analyze the collected data with various AI tasks, and an Informer to send analyzed data to various destinations. The tool is suitable for scheduled jobs or serverless applications as all Observers can store their state in databases. Obsei is still in alpha stage, so caution is advised when using it in production. The tool can be used for social listening, alerting/notification, automatic customer issue creation, extraction of deeper insights from feedbacks, market research, dataset creation for various AI tasks, and more based on creativity.

R-Judge is a benchmarking tool designed to evaluate the proficiency of Large Language Models (LLMs) in judging and identifying safety risks within diverse environments. It comprises 569 records of multi-turn agent interactions, covering 27 key risk scenarios across 5 application categories and 10 risk types. The tool provides high-quality curation with annotated safety labels and risk descriptions. Evaluation of 11 LLMs on R-Judge reveals the need for enhancing risk awareness in LLMs, especially in open agent scenarios. Fine-tuning on safety judgment is found to significantly improve model performance.

Contoso Chat is a Python sample demonstrating how to build, evaluate, and deploy a retail copilot application with Azure AI Studio using Promptflow with Prompty assets. The sample implements a Retrieval Augmented Generation approach to answer customer queries based on the company's product catalog and customer purchase history. It utilizes Azure AI Search, Azure Cosmos DB, Azure OpenAI, text-embeddings-ada-002, and GPT models for vectorizing user queries, AI-assisted evaluation, and generating chat responses. By exploring this sample, users can learn to build a retail copilot application, define prompts using Prompty, design, run & evaluate a copilot using Promptflow, provision and deploy the solution to Azure using the Azure Developer CLI, and understand Responsible AI practices for evaluation and content safety.

Empirical is a tool that allows you to test different LLMs, prompts, and other model configurations across all the scenarios that matter for your application. With Empirical, you can run your test datasets locally against off-the-shelf models, test your own custom models and RAG applications, view, compare, and analyze outputs on a web UI, score your outputs with scoring functions, and run tests on CI/CD.

AI Toolkit for Visual Studio Code simplifies generative AI app development by bringing together cutting-edge AI development tools and models from Azure AI Studio Catalog and other catalogs like Hugging Face. Users can browse the AI models catalog, download them locally, fine-tune, test, and deploy them to the cloud. The toolkit offers actions such as finding supported models, testing model inference, fine-tuning models locally or remotely, and deploying fine-tuned models to the cloud. It also provides optimized AI models for Windows and a Q&A section for common issues and resolutions.

Astra.ai is a multimodal agent powered by TEN, showcasing its capabilities in speech, vision, and reasoning through RAG from local documentation. It provides a platform for developing AI agents with features like RTC transportation, extension store, workflow builder, and local deployment. Users can build and test agents locally using Docker and Node.js, with prerequisites including Agora App ID, Azure's speech-to-text and text-to-speech API keys, and OpenAI API key. The platform offers advanced customization options through config files and API keys setup, enabling users to create and deploy their AI agents for various tasks.

Cognita is an open-source framework to organize your RAG codebase along with a frontend to play around with different RAG customizations. It provides a simple way to organize your codebase so that it becomes easy to test it locally while also being able to deploy it in a production ready environment. The key issues that arise while productionizing RAG system from a Jupyter Notebook are: 1. **Chunking and Embedding Job** : The chunking and embedding code usually needs to be abstracted out and deployed as a job. Sometimes the job will need to run on a schedule or be trigerred via an event to keep the data updated. 2. **Query Service** : The code that generates the answer from the query needs to be wrapped up in a api server like FastAPI and should be deployed as a service. This service should be able to handle multiple queries at the same time and also autoscale with higher traffic. 3. **LLM / Embedding Model Deployment** : Often times, if we are using open-source models, we load the model in the Jupyter notebook. This will need to be hosted as a separate service in production and model will need to be called as an API. 4. **Vector DB deployment** : Most testing happens on vector DBs in memory or on disk. However, in production, the DBs need to be deployed in a more scalable and reliable way. Cognita makes it really easy to customize and experiment everything about a RAG system and still be able to deploy it in a good way. It also ships with a UI that makes it easier to try out different RAG configurations and see the results in real time. You can use it locally or with/without using any Truefoundry components. However, using Truefoundry components makes it easier to test different models and deploy the system in a scalable way. Cognita allows you to host multiple RAG systems using one app. ### Advantages of using Cognita are: 1. A central reusable repository of parsers, loaders, embedders and retrievers. 2. Ability for non-technical users to play with UI - Upload documents and perform QnA using modules built by the development team. 3. Fully API driven - which allows integration with other systems. > If you use Cognita with Truefoundry AI Gateway, you can get logging, metrics and feedback mechanism for your user queries. ### Features: 1. Support for multiple document retrievers that use `Similarity Search`, `Query Decompostion`, `Document Reranking`, etc 2. Support for SOTA OpenSource embeddings and reranking from `mixedbread-ai` 3. Support for using LLMs using `Ollama` 4. Support for incremental indexing that ingests entire documents in batches (reduces compute burden), keeps track of already indexed documents and prevents re-indexing of those docs.

OpenAI-compatible API for TensorRT-LLM and NVIDIA Triton Inference Server, which allows you to integrate with langchain

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

This repository provides an implementation of QA-MDT, integrating state-of-the-art models for music generation. It offers a Quality-Aware Masked Diffusion Transformer for enhanced music generation. The code is based on various repositories like AudioLDM, PixArt-alpha, MDT, AudioMAE, and Open-Sora. The implementation allows for training and fine-tuning the model with different strategies and datasets. The repository also includes instructions for preparing datasets in LMDB format and provides a script for creating a toy LMDB dataset. The model can be used for music generation tasks, with a focus on quality injection to enhance the musicality of generated music.

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

Prime is a framework for efficient, globally distributed training of AI models over the internet. It includes features such as fault-tolerant training with ElasticDeviceMesh, asynchronous distributed checkpointing, live checkpoint recovery, custom Int8 All-Reduce Kernel, maximizing bandwidth utilization, PyTorch FSDP2/DTensor ZeRO-3 implementation, and CPU off-loading. The framework aims to optimize communication, checkpointing, and bandwidth utilization for large-scale AI model training.

LLMinator is a Gradio-based tool with an integrated chatbot designed to locally run and test Language Model Models (LLMs) directly from HuggingFace. It provides an easy-to-use interface made with Gradio, LangChain, and Torch, offering features such as context-aware streaming chatbot, inbuilt code syntax highlighting, loading any LLM repo from HuggingFace, support for both CPU and CUDA modes, enabling LLM inference with llama.cpp, and model conversion capabilities.

This repository contains the code that Defog uses for the evaluation of generated SQL. It's based off the schema from the Spider, but with a new set of hand-selected questions and queries grouped by query category. The testing procedure involves generating a SQL query, running both the 'gold' query and the generated query on their respective database to obtain dataframes with the results, comparing the dataframes using an 'exact' and a 'subset' match, logging these alongside other metrics of interest, and aggregating the results for reporting. The repository provides comprehensive instructions for installing dependencies, starting a Postgres instance, importing data into Postgres, importing data into Snowflake, using private data, implementing a query generator, and running the test with different runners.

The RAG Experiment Accelerator is a versatile tool that helps you conduct experiments and evaluations using Azure AI Search and RAG pattern. It offers a rich set of features, including experiment setup, integration with Azure AI Search, Azure Machine Learning, MLFlow, and Azure OpenAI, multiple document chunking strategies, query generation, multiple search types, sub-querying, re-ranking, metrics and evaluation, report generation, and multi-lingual support. The tool is designed to make it easier and faster to run experiments and evaluations of search queries and quality of response from OpenAI, and is useful for researchers, data scientists, and developers who want to test the performance of different search and OpenAI related hyperparameters, compare the effectiveness of various search strategies, fine-tune and optimize parameters, find the best combination of hyperparameters, and generate detailed reports and visualizations from experiment results.

BentoDiffusion is a BentoML example project that demonstrates how to serve and deploy diffusion models in the Stable Diffusion (SD) family. These models are specialized in generating and manipulating images based on text prompts. The project provides a guide on using SDXL Turbo as an example, along with instructions on prerequisites, installing dependencies, running the BentoML service, and deploying to BentoCloud. Users can interact with the deployed service using Swagger UI or other methods. Additionally, the project offers the option to choose from various diffusion models available in the repository for deployment.

Test Shaman: Guiding software testing with Grug wisdom and humor, balancing fun with practical advice.

Provides Raven's Progressive Matrices test with explanations and calculates your IQ score.

I craft tests first, then code, validating new features.

An AI conducting 30-question IQ tests, assessing and providing detailed feedback.

I will provide guidance on testing, verification, and validation for QA roles.

Formal and structured interactive IQ test platform.

Assists teachers in marking tests and generating score reports.

How smart are you? Solve it with your friends, find out who is smarter!

Software code tester and debugger

Formal, concise Angular 2 test guide.

Personality test by birthday.

Helps user learn essential vocabulary for GRE test with multiple choice questions

I'm your lab test consultant for blood tests and microbial cultures. How can I help you today?

Creates Application Security Test cases in YAML

Helping you study for cybersecurity certifications and get the job you want!

Expert in advanced data analysis and interpretation

Crafting full, accurate Apex test classes, with 100% user service.

Train to pass the Reverse Turing Test!

Your go-to MBTI assessment tool, providing personalized insights.

Friendly assistant for React app testing, detailed and accessible.