{
    "response": {
        "marketplace_eligible__boolean": true,
        "appname_text": "mistralai",
        "deleted_boolean": false,
        "license_text": "Commercial",
        "screenshot_image": "//meta-q.cdn.bubble.io/f1738853372346x488698222064033660/Groq-AI-Assistant.png",
        "Created Date": "2023-12-14T19:41:46.192Z",
        "price_number": 39,
        "name_text": "Groq, Llama & Claude AI",
        "description_text": "NEW: I've added the brand new compound-beta model to the template\n\n\"While LLMs excel at generating text, compound-beta takes the next step. It's an advanced AI system that is designed to solve problems by taking action and intelligently uses external tools - starting with web search and code execution - alongside the powerful Llama 4 models and Llama 3.3 70b model. This allows it access to real-time information and interaction with external environments, providing more accurate, up-to-date, and capable responses than an LLM alone.\n\nWhen the API is called, it will intelligently decide when to use search or code execution to best answer the user's query. These tool calls are performed on the server side, so no additional setup is required on your part to use agentic tooling.\n\nWith this prompt \"What is the current weather in Tokyo?\", the API will use its build in web search tool to find the current weather in Tokyo. If you didn't use agentic tooling, you might have needed to add your own custom tools to make API requests to a weather service, then perform multiple API calls to Groq to get a final result. Instead, with agentic tooling, you can get a final result with a single API call.\n\"\n\n\nYou also can create longer prompts with the Speech to Text element. It uses the new real time Speech model from Groq and a very lightweight audio recorder. Because it's a reusable Bubble element you can use it also on other pages or Bubble apps for other use cases. Now with whisper-large-v3-turbo. Much faster. \n\nYou can also use the brand new Claude Sonnet 3.7 Model from Anthropic for your assistant.\nAlso with the brand new llama-3.1-8b-instant model from Meta.\nInsane performance!\nLook at this video: https://www.loom.com/share/1b7dcb778dcb429da4f59a4c8dc40456\n\nThis template connects your Bubble app to Groq LPU Inference Engine. It works with the LLM from Google, Meta and Mistral.\nNow with a better UI/UX and the brand new Llama3 model from Meta. \nAfter some responsive design optimization users who are working in the field  can use AI-Assistants, no matter where their work takes them. AI-Assistants to go.\n\nMost if not all LLMs return text formated as markdown. Therefore this template now uses a wonderful free plugin which converts markdown to bb-code.\n\nThis is what Groq says about their LIGHTNING FAST engine:\n\"Welcome to Groq®! We created the LPU™ Inference Engine - the first and fastest of its kind - serving the real-time AI market. Our solution for inference (not training) makes us the AI performance leader, in regards to speed and precision, in the compute center.\n\nUnlike other providers, we aren't brokering a cloud service. We built our own chip, compiler and software, systems, and GroqCloud™. Our first-gen GroqChip™, a Language Processing Unit™ (LPU), is a new processor category. That's one part of our secret sauce.\n\nOur performance enables a greater potential for AI across multiple industries. It's about real-time AI, low-latency, low batch size solutions. Try GroqChat yourself!\nThis is the first Bubble template for the Mistral-AI API. https://mistral.ai/news/about-mistral-ai/\nThis template connects your Bubble app to the Mistral-AI API. The Mistral-AI is Open Source and based in Europe.\"\n\nTo work with the template you need an Groq developer account.  https://groq.com\nCreate an account and click on API keys on the left side. Create an API key and copy it. Now go to your Bubble site and install the API connector plugin. Expand the API call. On the top you'll find a shared header. Paste your API key in the value field of the Authorization key.\n\nIf you want to use Claude Sonnet 3.7 Model from Anthropic you need an API key for Claude.\nYou can get one here: https://www.anthropic.com/api\n\nIf you use DeepSeek no data will be send to servers in China.\n\"Note that Groq is a US-based company and when you send a query via DeepSeek-R1-Distill-Llama-70b on GroqCloud, we’ve deployed it on our infrastructure. In particular, when you send a query (inputs/outputs) to any model instance via GroqCloud™, we temporarily store it in memory and clear it as soon as your session is completed. We do this because we don’t do training – we do inference. While Groq has no incentive to keep your data, customers who want storage can work with their own provider to meet their application needs.\n\nThis means your data won’t be sent to any DeepSeek servers in China. We take privacy seriously at Groq and you can learn more about that commitment at trust.groq.com.\"\n\n\n---\nThis template mimics AI driven assistants. \n\n    - Create an Assistant or choose one from the assistants dropdown.\n    - Create a new thread or select an existing thread.\n    - Create new messages in the active thread.\n\nThese are Bubble database things and allows you to create a better structure for your chats. \n\nYou can create unlimeted assistants. Then you can add unlimited named threads to an assistant. And every thread can have unlimited messages. Messages consists of prompts from you and answers from the Mistral AI.\n\nTemplate is sold as is. Any bugs will be fixed ASAP. I'll continue the development of this template.\nFor customization requests please email m.droste@mdwp.de\n",
        "commercial_price_number": 139,
        "first_publication_date": "2024-01-09T16:39:33.580Z",
        "published_boolean": true,
        "Modified Date": "2025-06-04T15:26:50.566Z",
        "sale_number": 3,
        "owner_user": "1537725591408x727526328060776000",
        "copy_db_boolean": true,
        "hidden_by_admin_boolean": false,
        "paid_plugins_list_custom_plugins": [],
        "rating_average_number": 5,
        "rating_count_number": 1,
        "new_responsive__boolean": true,
        "template_category_option_template_category": "Chat",
        "quick_start__boolean": false,
        "community_link_text": "https://forum.bubble.io/t/new-template-for-the-opensource-mistral-ai-api/301464",
        "documentation_link_text": null,
        "ease_of_use_option_ease_of_use": "Beginner",
        "features_list_custom_template_features": [
            "1749050808728x902492199314522100",
            "1749050808728x828064006107299800",
            "1749050808728x239765754355646460",
            "1749050808728x922688334080245800",
            "1749050808728x779928493103513600",
            "1749050808728x474983127160717300"
        ],
        "gallery_list_file": [],
        "suggest_paid_plan__boolean": false,
        "summary_text": "This is the first Bubble template for the Groq-AI API.\nThis template connects your Bubble app to Groq LPU Engine. It works with the LLM from Google, Meta, Mistral or Deepseek.",
        "tutorial_link_text": null,
        "last_install_date": "2025-04-12T17:00:24.527Z",
        "Slug": null,
        "featured_new_responsive__boolean": false,
        "owner_s_builder_name__lowercase__text": "meinolf droste",
        "tep___color_primary_text": null,
        "tep___color_secondary_text": null,
        "tep___preview_url_text": null,
        "tep___all_images_list_image": [],
        "tep___free_plugin_ids_list_text": [],
        "tep___primary_image_image": null,
        "tep___free_plugin_count_number": null,
        "_id": "1702582904772x752999749022384100"
    }
}