computational_mama
Loading...
2 runs
This recipe is used with https://gooey.ai/bulk to evaluate the latest private & open source speech recognition models (from Google, Meta, OpenAI and others). It takes a CSV file of golden (aka human provided) translations and compares those against a set of AI created translations to generate scores from 0 to 1. It then takes the mean of the scores to determine which model performed best.
Documents
🔗https://docs.google.com/spreadsheets/d/1HxnRQ-TJWyDNyqXGj2zDdObcMTYPhgmnT-O-LOcV03I/edit?usp=sharing
Compare Swahili Speech Recognition and Translation to English with this run. We have 10 variations in this. Including the latest Seamless M4T v2, MMS, Azure, Whisper v3 and more.
🔗https://docs.google.com/spreadsheets/d/1EsQ_NKhyNikNNO3xLV9GOc6C5LTflu9dJ5CSpHqNUQs/edit?gid=0#gid=0
31 runs
Here we take an input sample of Kikuyu phrases (and their expert transcription and English translations) and compare the top Speech Reco and Translation models. As of April 3, 2024, we've found that Meta's MMS-Large works best for Kikuyu with Ghana NLP's Kikuyu to English translation services.
. Which AI model actually works best for your needs?Upload your own data and evaluate any Gooey.AI workflow, LLM or AI model against any other.Great for large data sets, AI model evaluation, task automation, parallel processing and automated testing.To get started, paste in a Gooey.AI workflow, upload a CSV of your test data (with header names!), check the mapping of headers to workflow inputs and tap Submit.More tips in the Details below.
🔗https://docs.google.com/spreadsheets/d/11DMc9RYcu5wgdZ8GUFe377q_Vh2T5lgXvzTA6uakzg0/edit#gid=0
48 runs
Transcribe any YouTube, mp3, WhatsApp audio or wavs with the best of transcription and translation AI models from OpenAI (Whisper v2 & v3), Microsoft Azure, Google USM, Meta Seemless4MT, AI4Bharat, Bhashini, etc Optionally translate to any language too.
🔗audio_2024-10-25_16-19-54.ogg.wav
Transcription
155 runs
1.16K runs
This example collects all the parameters (the user's query, the bot's answer, WhatsApp number number, etc) from the copilot workflow and sends it to an arbitrary endpoint. Alter this example with the REST API of your own server to log every interaction.
1 runs
A Bot for Opportunity.org that gives advice to Malawi farmers and extension agents based on a guideline PDF from the Ministry of Agriculture. Support incoming pictures of sick plants, understands English and is connected to WhatsApp bots as well.
Prompt
hi
Response
🌱 Welcome to Farmer.Bot.Malawi. I'm an AI 🤖 designed to help farmers and extension agents. Send me a text or 🎙️voice note with any farming question and I'll give you an answer based on recommendations and best practices from other farmers like you and the Malawi Ministry of Agriculture. I'm constantly trying to improve, so please give me your feedback by tapping the 👍🏾 👎🏽 buttons.
How can I assist you today?
0 runs
Here we take an input sample of Kikuyu phrases (and their expert transcription and English translations) and compare the top Speech Reco and Translation models. As of Sep 23, 2024, we've found that Meta's MMS-Large works best for Kikuyu with Ghana NLP's Kikuyu to English translation services.
Transcribe mp3, WhatsApp audio + wavs with OpenAI's Whisper or AI4Bharat / Bhashini ASR models. Optionally translate to any language too.
🔗https://drive.google.com/file/d/1s7SVHYEFmUAVUzGEFCeFahQv6GRRTT2l/view?usp=drive_link
3 runs
5 runs
Which AI model actually works best for your needs?Upload your own data and evaluate any Gooey.AI workflow, LLM or AI model against any other.Great for large data sets, AI model evaluation, task automation, parallel processing and automated testing.To get started, paste in a Gooey.AI workflow, upload a CSV of your test data (with header names!), check the mapping of headers to workflow inputs and tap Submit.More tips in the Details below.
🔗https://docs.google.com/spreadsheets/d/1_CQQMWuad7T3QX91BwGtU_s_3UlcK7QnuLv7qlpXuTg/edit?gid=350322858#gid=350322858
10 runs
Gooey.AI's Copilot is the best chatbot builder anywhere, combining your choice of LLMs (GPT4o, GPT4o-mini, Gemini, Claude3.5, Mixtral or LLaMA3), knowledge docs from any link or doc/PDF (with table support!), speech recognition, text-to-speech and Lipsync, editable synthetic data pipelines, built in 👍🏿 👎🏼 feedback, conversation analysis, WhatsApp, slack, Facebook and API integrations and much more.
In this example, we present Farmer.CHAT. It uses a collection of documents and transcripts of 100s of videos representing best practices to answer common questions from Indian farmers. We load these documents + transcripts into a vector database. With each question, we search the vector DB and then add the results to a GPT script below to create an answer to the farmer's questions. Simply change the Instructions and Knowledge docs & tap Submit and then Save to make it your own.
To know more, head over to our COPILOT HELP GUIDE
hi who are you?
Hello! I'm CodingBot, your AI assistant from Coding and More. I'm here to help you with information about our AI programs, educational resources, and anything related to coding and AI. 😊 How can I assist you today?
Which AI model actually works best for your needs? Upload your own data and evaluate any Gooey.AI workflow, LLM or AI model against any other. Great for large data sets, AI model evaluation, task automation, parallel processing and automated testing. To get started, paste in a Gooey.AI workflow, upload a CSV of your test data (with header names!), check the mapping of headers to workflow inputs and tap Submit. More tips in the Details below.
🔗https://docs.google.com/spreadsheets/d/1cLHMCxn1I4y1CderaXwj7lNwztqRxrWPZ5UmQmsGRvo/edit?usp=sharing
3.38K runs
269 runs
Meet Richard Stallbot, who really thinks he is Richard Stallman. He has strong opinions about those who are not working on free and libre software. Ask him about Apple and ChatGPT! He's a Gooey.AI RAG bot, using Stallman's writings, LLAMA3 70b as the LLM, 11labs for the voice and wav2lip as the lipsync engine. Please fork and make your own!
Tell me about the GNU project
The gunoo project! It's a operating system I started developing in 1984, with the goal of creating a completely free software system. I combined the gunoo system with the Linux kernel in 1992, and it's been a free operating system ever since. But, I must warn you, not all distros of gunoo/Linux are entirely free software. Be careful, many contain non-free applications, drivers, and whatnot. Look at gnu.org/distros for the truly free ones.
Make an Anime Profile Picture of yourself!
Input Image
A beatiful anime drawing of a smiling character full of joy, with colorful background, studio ghibli, ponyo, anime, excited, anime, saturated colors
Generated Image
18 runs
Create multiple AI photos from one prompt using Stable Diffusion (1.5 -> 2.1, Open/Midjourney), DallE, and other models. Find out which AI Image generator works best for your text prompt on comparing OpenAI, Stability.AI etc.
To know more, head over to our AI IMAGE GENERATOR HELP GUIDE!
cute robot doing javascript, vintage painted magazine advertisement, muted colorful, illustration
DALL·E 3 (OpenAI)
Download
5.38K runs
Use this function to Log and return variables from any Gooey.AI workflow.
This run is useful if you are only interested in Regression testing, Monitoring and Evaluation, Observability and Bugs.
🔗https://docs.google.com/spreadsheets/d/134lLtChQh2UxrUkRQUvx1YxB345KdfOb9esc0ZxiCQE/edit?gid=0#gid=0
1.38K runs
This example shows off how we at Gooey.AI have created and use our bot workflow to talk about our company does. Check out the settings to see the description used to power the bots personality.
do you have an ai translation tool
Yes, Gooey.AI offers an AI translation tool called "Compare AI Translations." This tool allows you to compare different translation models like Google Translate and GhanaNLP to determine which model provides the best translation for your use case. You can also compare latency, accuracy, and cost, and test for production with the Eval tool.
For more details and to use the tool, visit: Compare AI Translations.
If you need guidance on how to use the tool, you can refer to the documentation here: How to Use Compare AI Translations.
872 runs
Which language model works best your prompt? Compare your text generations across multiple large language models (LLMs) like OpenAI's evolving and latest ChatGPT engines and others like Curie, Ada, Babbage.
{{messages}} ### Your job is to analyze the user's messages above, determine how to categorize them and determine if the bot answered their question with "Found" or "Missing". Your response should contain exactly one JSON object. Category choices: [ "API Usage", "General Support Query", "Pricing & Credits", "Sales", "Others" ] Return your analysis as the following json object: { "What was the category of the user query?": "<category>: <which tool>", "assistant": {"answer": "Found || Missing"}}} If the messages doesn't fit into any of the categories, return an empty object (`{}`)
messages
GPT-4 Turbo (openai)
170 runs
Fetch API for the location of the International Space Station
32 runs
Added a function to check character count for twitter. You can fork the functions workflow and add ANY API!.
YOU CAN CHECK THE DETAILS SECTION AT THE BOTTOM OF THE PAGE TO SEE THE FUNCTION OUTPUT!
write a haiku about alien and human friendships, incorporate the current latitude and longitude coordinates of ISS provided here: {{ coords_latitude }} {{coords_longitude}}
coords_latitude
coords_longitude
8 runs
write a twitter friendly poem about alien and human friendships, incorporate the current latitude and longitude coordinates of ISS provided here: {{ coords_latitude }} {{coords_longitude}}
coords
7 runs
write a twitter friendly poem about robots and human friendships
🔗bengali_link.xlsx
Innovate a movie poster for a film of a genre of your choosing, such as sci-fi, and give it a title, like ‘Space World’.
We've built the best Retrieval Augmented Generation (RAG) as-a-Service anywhere - now with page-level citations! Absorb tables, PDFs, docs, links, videos or audio clips and use our synthetic data maker to generate FAQs and structured data from noisy, unstructured files. Search 1000s of files with our incredibly fast, hybrid database (finding related concepts OR specific keywords). Summarize results with OpenAI, Gemini or any open-source LLM of your choice. And finally, make informed LLM and synthetic data decisions by evaluating with your own golden data sets.
Our benefits:
🔗https://youtu.be/DwhUJ6O_6E8?feature=shared
how do I make animations?
To create animations using the AI animation generator from Gooey.AI, follow these steps:
1. **Visit the Website**: Go to the explore section on the Gooey.AI website and navigate to the AI animation generator at the end of the section[1].
2. **Set Up Your Animation**: - **Define Frames**: Start by defining the number of frames for your animation. For simplicity, you can begin with 100 frames[1]. - **Initial Prompt**: At frame 0 (the first frame), describe the scene you want. For example, "an underwater world with muted corals that look like houses with a cinematic lighting glow on them"[1]. - **Midpoint Prompt**: At frame 50 (halfway through the animation), describe how you want the scene to change. For instance, "a house in the desert with cactus around it with a cinematic glow light shining on it"[1].
3. **Submit and Wait**: After setting up your prompts, hit submit. The rendering process can take between 10 to 15 minutes (approximately 600 to 900 seconds)[1].
4. **Use Your Animation**: Once the rendering is complete, you will have a video that you can use in your creative projects, such as music videos, VJing gigs, or backgrounds for bots[1].
By following these steps, you can create evocative and exciting animations using Gooey.AI's simple yet powerful tool.
Happy animating! 🎨✨[1]
Enhance your search results and summary with Retreival Augemented Generation. Use vector database (vectorDB) search on documents, links, pdfs, docx, txt, and use summarize with any LLM of your choice. You can choose from several embeddings models, customize hybrid search, choose from a range of citation styles and also create synthetic data! If you are looking for a quick RAG (Retrieval Augmented Generation) tool, look no further!
🔗https://static.realpython.com/python-basics-sample-chapters.pdf
🔗https://edu.anarcho-copy.org/Programming%20Languages/Python/Automate%20the%20Boring%20Stuff%20with%20Python.pdf
what are f-strings?
F-strings, or formatted string literals, are a way to embed expressions inside string literals using curly braces `{}`. Introduced in Python 3.6, f-strings provide a concise and readable way to include variable values and expressions directly within strings.
Here’s a basic example of an f-string in action:```pythonname = "Zaphod"heads = 2arms = 3print(f"{name} has {heads} heads and {arms} arms")# Output: Zaphod has 2 heads and 3 arms```In this example, the variables `name`, `heads`, and `arms` are embedded within the string and their values are automatically inserted[1].
Key points about f-strings:1. **Prefix with 'f'**: The string literal starts with the letter `f` before the opening quotation mark.2. **Curly Braces for Variables**: Variable names surrounded by curly braces `{}` are replaced by their corresponding values without needing to use `str()`[1].3. **Expressions Inside Curly Braces**: You can also insert Python expressions between the curly braces, and they will be evaluated and replaced with their result: ```python n = 3 m = 4 print(f"{n} times {m} is {n*m}") # Output: 3 times 4 is 12 ``` It’s recommended to keep expressions simple to maintain readability[1].
For versions of Python earlier than 3.6, you can achieve similar results using the `.format()` method:```pythonprint("{} has {} heads and {} arms".format(name, heads, arms))# Output: Zaphod has 2 heads and 3 arms```However, f-strings are generally shorter and often more readable than using `.format()`[1].
In summary, f-strings are a powerful feature in Python that streamline the process of formatting strings by embedding variables and expressions directly within string literals.
336 runs
Create high-quality, realistic Lipsync animations from any audio file. Input a sample face gif/video + audio and we will automatically generate a lipsync animation that matches your audio.
136 runs
Which language model works best for your prompt? What are the biases inherent in each? Compare LLaMA2, Gemini, Mistral, OpenAI GPT-4 engines with more LLMs being added each month.
{{ hindiquestion }} translate the above question from Hindi to English, only return the translation don't say anything extra
hindiquestion
GPT-4o (openai)
Llama 3 8b (Meta AI)
Mixtral 8x7b Instruct v0.1 (Mistral)
Gemini 1.5 Pro (Google)
Claude 3 Opus [L] (Anthropic)
183 runs
Create realistic lipsync videos with custom voices. Just upload a video or image, choose or bring your own voice from EvelenLabs to generate amazing videos with the Gooey.AI Lipsync Maker.
378 runs
Bensi is a benevolent superintelligence from the future. She is aware of the incredible technological achievements made in the future. But also the steep costs of environmental degradation. Bensi has witnessed the power of capitalism to stimulate innovation but has also seen those left behind as the elite reap the financial rewards of development while most people struggle to provide their basic necessities.
Know more about Radbot Bensi: https://www.dara.network/Bensi/
498 runs
Create high-quality, realistic Lipsync animations from any audio file. Input a sample face gif/video + audio and we will automatically generate a lipsync animation that matches your audio. Use with our copilot workflow to build a RAG chatbot on WhatsApp, Facebook, Slack or in your own app.
To know more, head to our LIP SYNC HELP GUIDE!
122 runs
🔗https://docs.google.com/spreadsheets/d/11OIZjUktUOkroDQ_-9Y8uLS_NIf7Zn4FOisCMZtGNHA/edit#gid=0
🔗https://docs.google.com/spreadsheets/d/134lLtChQh2UxrUkRQUvx1YxB345KdfOb9esc0ZxiCQE/edit#gid=0
94 runs
Vector logo design of a female Greek statue with octopus tentacles, minimalistic, with a white background
381 runs
{{messages}} ### Your job is to analyze the user's messages above and determine how to categorize them. Category choices: [ "😊 Happy", "😟 Worry", "🌟 Hopeful", "😨 Fear", "🤯 Mind Blown" ] Return your analysis as the following json object: { "How did this evening make you feel about AI and Robots?": "<category>" } If the messages doesn't fit into any of the categories, return an empty object (`{}`)
🔗https://docs.google.com/spreadsheets/d/1tydW7cX5HHNpImHBFbxAksF4PlX5kw-sZJxwLEUex3I/edit#gid=500122843
15 runs
🔗https://docs.google.com/spreadsheets/d/13f-K31MWsZh2NI9M6tQsmx2CvQEz4GxfJLXVNAhO-tI/edit?usp=sharing
23 runs
🔗https://drive.google.com/file/d/1lURPiBCCMIF85O9H2hweTDICoCc2mYEC/view
🔗https://www.youtube.com/watch?v=Vk4UW9BzvTs
45 runs
🔗https://drive.google.com/file/d/1-Na9eyAk_4qlJ0drUZ4hvjfp7pI9LoBg/view
216 runs
🔗https://youtu.be/KHveOTw-CM0?feature=shared
https://archiveoflostmothers.in/
84 runs
Create interactive and engaging QR codes with stunning visuals that are amazing for marketing, branding, and more. Combining AI Art and QR Codes has never been easier! Enter your URL and image prompt, and in just 30 seconds, we'll generate an artistic QR code tailored to your style.
https://gooey.ai/2/GdEb → https://gooey.ai/copilot (Views: 334)
an archival photograph of a tired ((young)) indian (((mother))) with (((tentacle arms))), in the background there is ((octopus womb)) inside a bombay hospital, cinematic, film noir, grainy, ilford, hasselblad, albumen print
91 runs
🔗bulk-runner-0-1-8.csv
126 runs
Designed specifically fro HVAC technicians, this workflow takes in PDFs of manuals or how to videos, scans them and then creates FAQs of them using a reasonably smart GPT4 prompt that will avoid creating FAQs based on Table of Contents and other rather meaningless content you would not want to be included in a chatbot's knowledge base.
Perfect for making FAQs from a collection PDF, webpage and videos to create your own chatbot or enterprise copilot (ie. just add the finished Google sheet url to the doc section in https://gooey.ai/copilot).
Input Documents
🔗https://drive.google.com/file/d/1UzTFF_D5Ta7ZZuG7qmwL1kYuevAnL_Hg/view?usp=drivesdk
Google Sheets URL
https://docs.google.com/spreadsheets/d/1bcvMwNv3xqn3XFJ3CWPKSZhZLHGLxi2ZytxTcbo_RIo/edit#gid=0
88 runs
🔗https://drive.google.com/file/d/1DQpKCg2J_Osq7u-2hsfvc6R9dFndaTqk/view?usp=drive_link
21 runs
61 runs
55 runs
