Examples: LLM


FUNCTIONS: Make a Haiku with ISS Coordinates

Loading...

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!

Prompt

write a haiku about alien and human friendships, incorporate the current latitude and longitude coordinates of ISS provided here: {{ coords_latitude }} {{coords_longitude}}

Copilot Web Integration Details Generator

Loading...

29 runs

Prompt

Your job is to define the schema for a chatbot, using the title, description and prompt of an AI Workflow.

Inputs:
Title: """{{ bi_name }}"""
Prompt: """{{ bot_script }}"""

Using the title and prompt, output the following json object: 
{    
    "description": string,
    "conversation_starters": [ "<question1>", "<question2>", ... ]
}

Use a formal tone for the description, keeping it under 100 words.  Output a maximum of 4 conversation starter questions.

Improve AI Image Prompt

Loading...

4 runs

A simple prompt that takes in an image prompt and outputs a better SD 1.5 one.

Prompt

Your job is to improve AI image prompts for the Stable Diffusion 1.5 model, Dreamshaper.  
Input prompt:
{{prompt}}
Output prompt:

Compare Indic LLMs

Loading...

9 runs

A comparison of small 2-10B LLM models on Hindi text using the best of LLaMA3, Gemma and Sarvam 2B

Prompt

भारत के प्रथम प्रधानमंत्री

Compare AfroLlama vs LLaLM3: Yoruba

Loading...

6 runs

Compare prompts and outputs from the fine-tuned AFROLLaMA from Jacaranda Health

Prompt

Yoruba: Kọ itan nipa Ọgbọn Ehoroa

Compare LLMs: SEA-LION vs SOTA

Loading...

21 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.

Prompt

Kalau orang sedang di GBK, biasanya sedang apa dia?

Default Copilot Analysis Script

Loading...

48 runs

This example is the default analysis script to categorize Copilot conversations and to determine whether user's questions we successfully answered.

Prompt

{{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: [ "General", "Salutation", "Random", "Technical", "Other" ]

Return your analysis as the following json object: { 
"What was the category of the user query?": "<category>", 
"assistant": {"answer": "Found || Missing"}}}

Gooey Bot Chat Analysis Script

Loading...

855 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.

Prompt

{{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 (`{}`)

Create a Copilot description + 4 sample Qs

Loading...

0 runs

This recipe takes in a Copilot's Description and Instruction Prompt and then creates a shorter description and 4 sample questions.

Prompt

Create a punchy, clever description (in under 40 words) of an AI Chat bot along with 4 sample questions (that are under 10 words), based on the following description and LLM instruction prompt:
Description:
{{description}}

Prompt:
{{prompt}}

Add Emojis to your GitHub readme

Loading...

0 runs

Yes, this is a silly (but useful!) AI recipe. Notice the differing emoji styles of Claude3.5 vs GPT-4o. :-)

Prompt

Add appropriate emojis to the following GitHub Readme.md:
{{code}}

New Code: 

PaLM2 Translations with Custom Glossary

Loading...

6 runs

When released, PaLM 2 not only surpassed other LLMs in translation abilities between multiple languages but also demonstrated significant improvements over Google Translate (see the Technical Report by Google). This example allows you to easily change out the languages and translation text via variables to explore this and compare with other LLMs. You can also add your own TSV or CSV glossary in the format spec'ed by Google Translate. This example run (or runs like it) can be imported into the Translation Recipe to compare with traditional translation tools!

Prompt

Remember this glossary of fixed translation terms. The columns represent language codes in BCP47 and the rows are the terms:
{{ glossary }}

PROMPT: Please use the glossary to translate the following text from en-US to da-DK.
<Q>Hello, my name is Bob and I work at gooey.ai which is an awesome company that coincidentally also made this tool. I am made by goowy.
<A>Hej, jeg hedder Bob, og jeg arbejder hos Gooey.AI, som er en fantastisk virksomhed, der tilfældigvis også lavede dette værktøj. Jeg er lavet af Gooey.
PROMPT: Please use the glossary to translate the following text from {{ source_language }} to {{ target_language }}.
<Q>{{ text_to_translate }}
<A>

FALana Summary Script

Loading...

378 runs

This prompt takes in all the conversations that have occurred with a Gooey.AI Copilot, in this case the FALANA Bot and summarizes the conversations into top concerns and questions for the speaker.

Prompt

{{conversations}}

####

Your job is to analyse the conversations above and summarise the user's responses to questions asked by the assistant.

Return the summary as a numbered list of 5 representative user responses. Group the user's responses and synthesize them into a set of questions that reflect the user responses, sorted by by how often the sentiment was expressed. Also categorise them based on common themes you observe.  You can ignore greetings and introductions with user names and companies. 

Here are two examples: 
{"What's your reaction to everything you've seen so far?": "1. Hope: Most people expressed cautious optimism about AI's potential for India", 
"Top questions": "1. AI and Jobs: What can we do to stem job losses from AI?" }

Return your analysis as the following JSON object: { "What's your reaction to everything you've seen so far?": "1. <Theme>: <Response>\n2. <Theme>: <Response>\n3. ...",  "Top questions": "1. <Theme>: <Response>\n2. <Theme>: <Response>\n3. ..." }

If the user responses doesn't fit into any of the categories, return an empty object (`{}`)

FALANA Chat Analysis Script

Loading...

381 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.

Prompt

{{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 (`{}`)
Gooey.AI (Dara.network Inc)

Compare Translations from Claude3, GPT4, Mixtral vs Gemini 1.5

Loading...

175 runs

Which language model works best your translation? Compare OpenAI GPT4 vs Meta and Google LLM engines. Pay with Stripe or PayPal

Prompt

Translate the following from {{source}} into {{destination}}:
{{source_text}}

Fireside Chat Summary Script

Loading...

168 runs

This prompt takes in all the conversations that have occurred with a Gooey.AI Copilot, in this case the Fireside Bot and summarizes the conversations into top concerns and questions for the speaker. It's then visualized here

Prompt

{{conversations}}

####

Your job is to analyse the conversations above and summarise the user's responses to questions asked by the assistant.

Return the summary as a numbered list of 5 representative user responses. Group the user's responses and synthesize them into a set of questions that reflect the user responses, sorted by by how often the sentiment was expressed. Also categorise them based on common themes you observe.  You can ignore greetings and introductions with user names and companies. 

Here are two examples: 
{"What's your reaction to everything you've seen so far?": "1. Hope: Most people expressed cautious optimism about AI's potential for India", 
"Top questions for Nandan": "1. AI and Jobs: What can we do to stem job losses from AI?" }

Return your analysis as the following JSON object: { "What's your reaction to everything you've seen so far?": "1. <Theme>: <Response>\n2. <Theme>: <Response>\n3. ...",  "Top questions for Nandan": "1. <Theme>: <Response>\n2. <Theme>: <Response>\n3. ..." }

You are being run in a public setting, so please take extra precautions to weed out and ignore hecklers, bad data, inappropriate or politics remarks, etc. 

If the user responses doesn't fit into any of the categories, return an empty object (`{}`)

Fireside Chat Analysis Script

Loading...

188 runs

Prompt

{{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 do you feel about AI after today": "<category>" }

If the messages doesn't fit into any of the categories, return an empty object (`{}`)

Run Mistral... FAST via an API

Loading...

1 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.

Prompt

What advice do you have to fight climate change? Write a 100 word action plan for American kids. 
Gooey.AI (Dara.network Inc)

How Farmer.CHAT turns conversations to structured data

Loading...

2.06K runs

Our https://gooey.ai/copilot workflow let's anyone build WhatsApp/FB or their own GPT4 powered chat bots, by just swapping out their own documents and GPT prompts. Additionally, we also enable you to analyze the user's message and bot's answer to create structured data from the raw conversational messages.

Each Gooey.AI copilot will have their own conversational analysis script like this one to help analyze the user's questions and the bot's ability to answer them well.

In this case, our Farmer.CHAT partner DigitalGreen.org wants to analyze the user's messages and categorize them based on their own logic. Hence, this LLM prompt takes a message and response and then determines whether:

  1. We should update the user's profile object (because they mentioned their location, crop or gender)
  2. The user's question was answered
  3. The topic of the user's question.

Prompt

Your job is to analyze incoming chat messages from farmers and the responses from a farming ai chatbot and determine how to categorize them.

The answer is only missing if the assistant:
---
1. Can not give any additional information
2. Apologizes
3. Tells the user to check a website
---
If it does not say all three things, the answer has been found.

For the user's subject answer, choose from the following list as category:

Subject Answers
*********************
Salutation
Plant Death (Infestation and Infection)
Farming Practice
Irrigation
Video
Supplements (Fertilizers and Pesticides)
Unknown Category
*********************
Assistant Answers
*********************
Found
Missing
*********************
Gender
*********************
unknown
male
female
unspecified
*********************

Conversation: """
   user: Hi
   assistant: Hello! How can I assist you with farming today?
"""
Analysis: {"user": {"crop": null, "subject": ”Salutation”, "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}}
///
Conversation: """
   user: My rice crop has yellow stem borer infestation. Please suggest
   assistant: Yellow stem borer is a major pest of rice crops. Here are some management practices that can help control the infestation of yellow stem borer in rice crops:

1. Use resistant varieties of rice such as Ratna, Sasyasree, Vikas, HKR 46, NDGR 21, Pantdhan 6, VLK 39, Prahlad, Birsadhan 201, Bhudeb Ainesh, Matangini, Radha, Sudha, Amulya, Bhagirathi, Jogan, Mandira, Nalini, Sabita, VL16 and VL 206. [2][3]

2. Cultural practices such as seed treatment with approved biopesticides or chemical pesticides before sowing, removing and destroying the grass weed hosts in the field bunds, channel or nearby areas of rice fields as these serve as alternative hosts for the pest, avoiding close spacing as it often increases the easy movement of pest, handpicking and destroying egg masses in the seedbed (nursery) before transplanting the field, cutting the leaf-top before transplanting to reduce carry-over of eggs from the seedbed to the field, raising the level of irrigation water periodically to submerge any eggs deposited on the lower parts of the plant, cutting out the stems with dead hearts and removing them from the field and destroying the larvae or burning the stem, and splitting applications of nitrogen fertilizer. High nitrogen application favors build-up of stem
"""
Analysis: {"user": {"crop": ”rice”, "subject": ”Plant Death (Infestation and Infection)”, "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}}
///
Conversation: """
   user: A drug can be used to increase the height of chillies in the chilli garden
   assistant: I'm sorry, but I couldn't find any information in the search results about a drug that can increase the height of chillies in a garden. It is important to note that using untested or unverified drugs on crops can be harmful and may not be effective. It is best to consult with a local agriculture expert for specific recommendations for your district and type of plant.
"""
Analysis: {"user": {"crop": ”chili”, "subject": ”Supplements (Fertilizers and Pesticides)”, "location": null, "gender": "unspecified"}, "assistant": {"answer": "Missing"}}
///
Conversation: """
   user: Tell me about organic farming
   assistant: Organic farming is a method of farming that avoids the use of synthetic fertilizers, pesticides, and genetically modified organisms (GMOs). Instead, it relies on natural methods like crop rotation, composting, and biological pest control to maintain soil fertility and control pests. Organic farming also emphasizes the use of renewable resources and conservation of water and soil. [1]
"""
Analysis: {"user": {"crop": null, "subject": "Farming Practice", "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}}
///
Conversation: """
   user: How many days should be watered after making the pepper garden?
   assistant: According to [1], immediately after transplanting chilli seedlings to the field, the field should be irrigated. The second irrigation is given 10 days after transplanting. Afterward, irrigation is given as per the requirement. Generally, 8 to 9 irrigations are given depending on rainfall, soil type, humidity, and temperature. The method of irrigation adopted is ridges and furrow. For more specific information on irrigation practices for your particular crop and district, please consult with your local agriculture extension office or watch relevant videos on https://www.digitalgreen.org/videos. 💦
"""
Analysis: {"user": {"crop": "pepper", "subject": "Irrigation", "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}}
///
Conversation: """
   user: Reasons why chillies fall apart
   assistant: Chillies can fall apart due to several reasons, including environmental conditions, pests, and diseases. Inadequate pollination due to low bee activity or high temperatures can lead to poor fruit development and cause the chillies to fall apart [2]. Nutrient deficiencies, particularly a lack of phosphorus, can also affect fruit development and cause the chillies to fall apart [1]. Additionally, pests such as the chilli blossom midge can cause poor development of fruits, leading to the chillies falling apart [3]. It is important to consult with a local agriculture expert to identify the specific cause and recommend appropriate management practices for your district and type of plant. For more information on farming in India, you can visit https://www.digitalgreen.org/videos. 🌶️🌱
"""
Analysis: {"user": {"crop": ”chili”, "subject": ”Plant Death (Infestation and Infection)”, "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}}
///
Conversation: """
   user: How to prepare dukki for planting chili garden
   assistant: I'm sorry, I couldn't find any relevant information on preparing "dukki" for planting chili garden in the search results. Could you please provide more context or try rephrasing your question?
"""
Analysis: {"user": {"crop": "chili", "subject": "Farming Practice", "location": null, "gender": "unspecified"}, "assistant": {"answer": "Missing"}}
///
Conversation: """
   user: Is there a video for this?
   assistant: I'm sorry, I don't have enough information to answer your question. However, you can visit https://www.digitalgreen.org/videos to find helpful videos on various farming practices in India.
"""
Analysis: {"user": {"crop": null, "subject": "Video", "location": null, "gender": "unspecified"}, "assistant": {"answer": "Missing"}}
///
Conversation: """
   user: Which crop can be planted in Anantapur?
   assistant: Anantapur district in Andhra Pradesh is suitable for growing crops like groundnut, maize, jowar, sunflower, cotton, and chilli. However, the choice of crop depends on various factors such as soil type, climate, and water availability. It is recommended to consult with local agricultural experts or extension officers to determine the best crop for a particular area. [1]
"""
Analysis: {"user": {"crop": null, "subject": "Farming Practice", "location": "Anantapur", "gender": "unspecified"}, "assistant": {"answer": "Found"}}
///
Conversation: """
   user: {{ user_msg }}
   assistant:  {{ assistant_msg }}
"""
Analysis:
Gooey.AI (Dara.network Inc)

Financial Report Maker

Loading...

90 runs

Takes in a quarterly report, BUY rating and transcript to output a financial report

Prompt

```[example report]
          {{ examplereport }} 
          ```You are a financial analyst working in a capital investment firm. Please follow the steps below: \n1. 
          Analyse and summarise the [finance report] and [transcripts] below in triple separators, don't create any output right now. 
          Once you have analysed and summarised the data, create a report for the company that is similar to the [example report] template above in the triple backticks. 
          Use the buy/hold/sell information from the [decision] input provided. Don't analyse your own.
          Ensure you follow the [example report] format, headers, writing style and paragraphs styles exactly.
          note: dont make up any information
          note: if information as per the [example report] template is missing please add a note "team must fill this information"
          |||[finance report] 
          {{ financereport }} 

          [transcripts] 
          {{ transcripts }} 

          [decision]
          {{ decision }}
          |||
Gooey.AI (Dara.network Inc)

Ulangizi AI Analysis Script

Loading...

6.33K runs

Our https://gooey.ai/copilot workflow let's anyone build WhatsApp/FB or their own GPT4 powered chat bots, by just swapping our their own documents and GPT prompts. Additionally, we also enable you to analyze the user's message and bot's answer to create structured data from the raw conversational messages.

Each Gooey.AI copilot will have their own conversational analysis script like this one to help analyze the user's questions and the bot's ability to answer them well.

In this case, we wantw to analyze the user's messages and categorize them based on their own logic. Hence, this LLM prompt takes a message and response and then determines whether:

  1. We should update the user's profile object (because they mentioned their location, crop or gender)
  2. The user's question was answered
  3. The topic of the user's question.

Prompt

Your job is to analyze incoming chat messages from farmers and the responses from a farming ai chatbot and determine how to categorize them.

The answer is only missing if the assistant:
---
1. Can not give any additional information
2. Apologizes
3. Tells the user to check a website
---
If it does not say all three things, the answer has been found.

For the user's subject answer, choose from the following list as category:

Subject Answers
*********************
Salutation
Plant Death (Infestation and Infection)
Farming Practice
Irrigation
Video
Supplements (Fertilizers and Pesticides)
Unknown Category
*********************
Assistant Answers
*********************
Found
Missing
*********************
Gender
*********************
unknown
male
female
unspecified
*********************

Conversation: """
   user: Hi
   assistant: Hello! How can I assist you with farming today?
"""
Analysis: {"user": {"crop": null, "subject": ”Salutation”, "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}}
///
Conversation: """
   user: My rice crop has yellow stem borer infestation. Please suggest
   assistant: Yellow stem borer is a major pest of rice crops. Here are some management practices that can help control the infestation of yellow stem borer in rice crops:

1. Use resistant varieties of rice such as Ratna, Sasyasree, Vikas, HKR 46, NDGR 21, Pantdhan 6, VLK 39, Prahlad, Birsadhan 201, Bhudeb Ainesh, Matangini, Radha, Sudha, Amulya, Bhagirathi, Jogan, Mandira, Nalini, Sabita, VL16 and VL 206. [2][3]

2. Cultural practices such as seed treatment with approved biopesticides or chemical pesticides before sowing, removing and destroying the grass weed hosts in the field bunds, channel or nearby areas of rice fields as these serve as alternative hosts for the pest, avoiding close spacing as it often increases the easy movement of pest, handpicking and destroying egg masses in the seedbed (nursery) before transplanting the field, cutting the leaf-top before transplanting to reduce carry-over of eggs from the seedbed to the field, raising the level of irrigation water periodically to submerge any eggs deposited on the lower parts of the plant, cutting out the stems with dead hearts and removing them from the field and destroying the larvae or burning the stem, and splitting applications of nitrogen fertilizer. High nitrogen application favors build-up of stem
"""
Analysis: {"user": {"crop": ”rice”, "subject": ”Plant Death (Infestation and Infection)”, "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}}
///
Conversation: """
   user: A drug can be used to increase the height of chillies in the chilli garden
   assistant: I'm sorry, but I couldn't find any information in the search results about a drug that can increase the height of chillies in a garden. It is important to note that using untested or unverified drugs on crops can be harmful and may not be effective. It is best to consult with a local agriculture expert for specific recommendations for your district and type of plant.
"""
Analysis: {"user": {"crop": ”chili”, "subject": ”Supplements (Fertilizers and Pesticides)”, "location": null, "gender": "unspecified"}, "assistant": {"answer": "Missing"}}
///
Conversation: """
   user: Tell me about organic farming
   assistant: Organic farming is a method of farming that avoids the use of synthetic fertilizers, pesticides, and genetically modified organisms (GMOs). Instead, it relies on natural methods like crop rotation, composting, and biological pest control to maintain soil fertility and control pests. Organic farming also emphasizes the use of renewable resources and conservation of water and soil. [1]
"""
Analysis: {"user": {"crop": null, "subject": "Farming Practice", "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}}
///
Conversation: """
   user: How many days should be watered after making the pepper garden?
   assistant: According to [1], immediately after transplanting chilli seedlings to the field, the field should be irrigated. The second irrigation is given 10 days after transplanting. Afterward, irrigation is given as per the requirement. Generally, 8 to 9 irrigations are given depending on rainfall, soil type, humidity, and temperature. The method of irrigation adopted is ridges and furrow. For more specific information on irrigation practices for your particular crop and district, please consult with your local agriculture extension office or watch relevant videos on https://www.digitalgreen.org/videos. 💦
"""
Analysis: {"user": {"crop": "pepper", "subject": "Irrigation", "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}}
///
Conversation: """
   user: Reasons why chillies fall apart
   assistant: Chillies can fall apart due to several reasons, including environmental conditions, pests, and diseases. Inadequate pollination due to low bee activity or high temperatures can lead to poor fruit development and cause the chillies to fall apart [2]. Nutrient deficiencies, particularly a lack of phosphorus, can also affect fruit development and cause the chillies to fall apart [1]. Additionally, pests such as the chilli blossom midge can cause poor development of fruits, leading to the chillies falling apart [3]. It is important to consult with a local agriculture expert to identify the specific cause and recommend appropriate management practices for your district and type of plant. For more information on farming in India, you can visit https://www.digitalgreen.org/videos. 🌶️🌱
"""
Analysis: {"user": {"crop": ”chili”, "subject": ”Plant Death (Infestation and Infection)”, "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}}
///
Conversation: """
   user: How to prepare dukki for planting chili garden
   assistant: I'm sorry, I couldn't find any relevant information on preparing "dukki" for planting chili garden in the search results. Could you please provide more context or try rephrasing your question?
"""
Analysis: {"user": {"crop": "chili", "subject": "Farming Practice", "location": null, "gender": "unspecified"}, "assistant": {"answer": "Missing"}}
///
Conversation: """
   user: Is there a video for this?
   assistant: I'm sorry, I don't have enough information to answer your question. However, you can visit https://www.digitalgreen.org/videos to find helpful videos on various farming practices in India.
"""
Analysis: {"user": {"crop": null, "subject": "Video", "location": null, "gender": "unspecified"}, "assistant": {"answer": "Missing"}}
///
Conversation: """
   user: Which crop can be planted in Anantapur?
   assistant: Anantapur district in Andhra Pradesh is suitable for growing crops like groundnut, maize, jowar, sunflower, cotton, and chilli. However, the choice of crop depends on various factors such as soil type, climate, and water availability. It is recommended to consult with local agricultural experts or extension officers to determine the best crop for a particular area. [1]
"""
Analysis: {"user": {"crop": null, "subject": "Farming Practice", "location": "Anantapur", "gender": "unspecified"}, "assistant": {"answer": "Found"}}
///
Conversation: """
   user: {{ user_msg }}
   assistant:  {{ assistant_msg }}
"""
Analysis:
Gooey.AI (Dara.network Inc)

Natural language to Stripe API via an LLM

Loading...

14 runs

Google Palm vs GPT4 vs LLaMA2: Which can easily create code to call the Stripe API using natural language.

Prompt

"""
Util exposes the following:

util.stripe() -> authenticates & returns the stripe module; usable as stripe.Charge.create etc
"""
import util
"""
Create a Stripe token using the users credit card: 5555-4444-3333-2222, expiration date 12 / 28, cvc 521
"""
Gooey.AI (Dara.network Inc)

A simple Quiz about Cassian Andor

Loading...

3 runs

This workflow creates a JSON quiz based on a character.

Prompt

You are an Intelligent AI Bot that can use any knowledge source. Generate a fun 6 question quiz about this Cassian Andor. The quiz should contain a fun Title with each Question having a question and then 4 different possible answers, with only one answer begin correct. Output the quiz, questions and possible answers as JSON. 

Gooey.AI (Dara.network Inc)

Golden answer comparison algo for ASR

Loading...

2 runs

A prompt to compare a golden answer vs an AI generated answer.

Prompt

You job is to assess AI translations. As a JSON object, give a short rationale and then a continuous score between 0 to 1 comparing a golden human text vs an AI generated text. If the AI text is identical to the golden text (other than spelling and punctuation differences), give a score of 1 and 0 if the phrases are semantically very different. 

Examples: 
Golden: In our chili farm there are white flies. What should we do?
AI_text: We have white spots in the Mirapakaya Pulam. What to do?
JSON: {
"rationale": "The ai_answer is missing key elements such as chili farm and white flies." ,
"score": ".2"
}

Golden: {{ golden }}
AI_text: {{ai_answer}}
JSON: 
Gooey.AI (Dara.network Inc)

Create an Icon from a Gooey.AI Workflow Prompt

Loading...

5 runs

This workflow takes a parameters the Gooey.AI workflow title and prompt to then create an image generation prompt that we use in our image generator workflow: https://gooey.ai/compare-ai-image-generators/?run_id=rpuzpn5m&uid=kKZgp2h1H2YxZYxZ2DbiRfUfeDM2

Prompt

Create a DallE image generation description that creates a text-free icon that visually sums up a AI tool that is described by NAME and LLM_PROMPT:
NAME: 
{{workflow}}

LLM_PROMPT: 
{{prompt}}

--- Guidelines:
DO give guidance to avoid any use of text in the icon design
DO use the LLM_PROMPT's content to define the style of the icon (more than NAME)

--- Examples:
NAME:
Copilot

LLM_PROMPT: 
You are Farmer.CHAT - an intelligent AI assistant built by Gooey.AI and DigitalGreen.org to help Indian farmers and agriculture agents. Try to give succinct  answers to their questions (at a 6th grade level), taking note of their district and the particular plant they are attempting to aid (usually seeking a strategy to rid the crops of pests or other problems). 

- If the user gives a salutation such as "Hi" or "Hello", introduce yourself before answering the user's query with the text below between the triple backticks:

Welcome to Farmer.CHAT. 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. I'm constantly trying to improve, so please give me your feedback by tapping the 👍🏾 👎🏽 buttons. Now, what would you like to know? 🌱


Example description:
Create a text-free icon that combines a friendly robot, Indian agricultural elements like wheat or rice plants, and a symbol of communication such as a speech bubble or headphones, to represent an AI assistant for Indian farmers. The icon should be colorful, inviting, and simple enough to be understood at a glance. Avoid any text
Gooey.AI (Dara.network Inc)

Financial Report Evaluator - grade based

Loading...

3 runs

This workflow compares human vs AI generated analyst reports and grades how close the AI generated report is to the human one.

Prompt

 """ 
    Given the human made report: \n
   {{ report }} 
    Here is AI generated report: \n
    {{ genreport }} 
Here is the finance report: \n
{{ financereport }} 
  You are a financial report evaluator assess and evaluate the [gen report] in comparison with the [report]. Please ensure AI report maintains coherence, accuracy, and consistency with prior non-AI-generated reports. Grade the [gen report] on a scale of 1 to 5. 1 being the reports dont match at all, and 5 being that the reports match very well and to extreme technical accuracy. 

    Criteria: 
      - relevance: Is the AI generated report similar in writing and communication style and flow of report to the human made report?"
      - accuracy: Is the AI generated report accurate in technical terminology
     - comparative consistent: Is the AI generated report comparable in same level of depth, insight, and accuracy as human made report?
     - logical coherence: Does the AI generated report have logical flow and structure?
     - fact and number checker: Does the AI generated report consistent and logical match the numbers and facts mentioned in the Finance Report?

    Your response should be as follows:

    GRADE: (1 mark for each criteria being met)
    (line break)
    JUSTIFICATION: (Write out in a step by step manner your reasoning about the criterion to be sure that your conclusion is correct. Use one or two sentences maximum. Keep the answer as concise as possible.)
  IMPROVEMENTS: (Write out in one or two sentences, all the areas in the AI generated report that require improvements in comparison to the human made report)
    """
Gooey.AI (Dara.network Inc)

Financial Analyst Report Maker

Loading...

3 runs

This workflow creates summarized reports for investors about various companies, it takes input as transcripts from calls with the company and financial reports and generates a summary report as per the formats of the particular investment bank.

Prompt

```[example report]
          {{ examplereport }} 
          ```
You are a financial analyst working in a capital investment firm. Please follow the steps below: \n1. 
          Analyse and summarise the [press release] and [transcripts] below in triple separators, don't create any output right now. 
          Once you have analysed and summarised the data, create a report for the company that is similar to the [example report] template above in the triple backticks. 
          Use the buy/hold/sell information from the [decision] input provided. Don't analyse your own.
          Ensure you follow the [example report] format, headers, writing style and paragraphs styles exactly. Add only HTML formatting.
          note: Don't make up any information
          note: Add "to be filled by team" for the price target section
          note: If information as per the [example report] template is missing, please add a note "team must fill this information"
          |||[press release] 
          {{ pressrelease }} 

          [transcripts] 
          {{ transcripts }} 

          [decision]
          {{ decision }}
          |||
Gooey.AI (Dara.network Inc)

Analysis for Zephyr

Loading...

866 runs

Analyse Zephyr help bot for topic and question found

Prompt

Your job is to analyze incoming chat messages from HVAC technicians and the responses from an HVAC ai chatbot and categorize them.

The format will be:

{"Answered": "", "Topic": ""}

With answers inside the double quotations


For the topic answer, choose from the following list:

Topics
*********************
Energy Efficiency
Lookup Part Details
Ductwork and Airflow
Refrigeration and Cooling
Diagrams/Pictures
System Troubleshooting (only choose this one if the user specifically asks for help finding the issue)
*********************

To determine if the answer has been found or not; See if the assistant says that it has the necessary information in its knowledge base or not. If it does not, respond with the boolean `false`. If it does, respond with the boolean `true`.

Conversation: """
   user: Can you use the same gauge/hoses for both R22 and R410A?
   assistant: While it is technically possible to use the same gauges for both R22 and R410A, it's not recommended due to the risk of cross-contamination. R22 and R410A are different types of refrigerants and mixing them can lead to system inefficiencies or even damage.
If you've used your gauges with R22, and then use them with R410A without proper cleaning, you could introduce R22 into an R410A system. This can cause issues such as oil return problems, decreased capacity, and potential system failure.
To avoid this, it's best practice to have separate sets of gauges for R22 and R410A. If you must use the same set, make sure to thoroughly clean your gauges and hoses between uses to prevent cross-contamination.
Remember, maintaining the integrity of the HVAC systems you're working on is crucial. Always follow best practices to ensure the longevity and efficiency of these systems. 👍🔧
"""
Analysis: {"Answered": true, "Topic": "Refrigeration and Cooling"}
///
Conversation: """
   user: Calculate the BTUs for a delta T of 20 and a CFM of 500.
   assistant: To calculate the BTUs, you can use the sensible heat formula:
Hs = 1.08 x CFM x ΔT
Given a CFM of 500 and a ΔT of 20°F, the calculation would be:
Hs = 1.08 x 500 x 20
This will give you the BTUs. Please note that this formula is used to calculate the sensible heat in the air, which does not include latent heat (the heat involved in changes of state, like evaporation or condensation) [3] .
"""
Analysis: {"Answered": true, "Topic": "Energy Efficiency"}
///
Conversation: """
   user: I think I may have an intermittent issue. How do I check for it?
   assistant: To check for an intermittent issue, you should first ensure that the symptom reappears for accurate troubleshooting [1] . Once the indoor unit has started operation and detected an abnormality, the indoor fan motor will turn OFF and the OPERATION INDICATOR lamp will flash [1] .
If a fault requiring inspection has occurred, the LED will alternately indicate the check code and the address of the unit in which the fault has occurred [2] [3] . This will help you identify the specific issue and its location.
Remember, systematic thinking and a step-by-step method are key in HVAC troubleshooting. 🛠️🔍
"""
Analysis: {"Answered": true, "Topic": "System Troubleshooting"}
///
Conversation: """
   user: Show me a picture of a refrigeration cycle.
   assistant: I'm sorry for the inconvenience, but as a text-based AI, I'm unable to provide images or diagrams. However, I can describe the refrigeration cycle based on the information from the search results.
The refrigeration cycle starts with the compressor, which increases the pressure of the refrigerant gas, adding more heat, and discharges hot, high-pressure superheated gas into the outdoor condenser coil.
In the condenser coil, the hot refrigerant gas loses its superheat by heat transferred from the gas through the tubes and fins of the coil. The refrigerant then becomes saturated, part liquid, part vapor, and continues to give up heat until it condenses to a liquid alone. Once fully liquefied, it continues to give up heat which subcools the liquid.
The liquid refrigerant at condensing temperatures and pressure leaves the outdoor condensing coil through the drier and is metered into the indoor coil through the metering device. As the cool low-pressure saturated refrigerant enters the tubes of the indoor coil, a portion of the liquid immediately vaporizes. It continues to soak up heat and vaporizes as it proceeds through the coil, cooling the indoor coil down.
As the vapor passes through the last tubes of the coil it becomes superheated, absorbing more heat than is necessary to vaporize it. This ensures that only dry gas will reach the compressor. The cycle then repeats [1] .
Please note that this is a simplified explanation and actual system operation
"""
Analysis: {"Answered": true, "Topic": "Diagrams/Pictures"}
///
Conversation: """
   user: What is the CFM of a 1.5 ton TEM6A0B30H21SB unit on low speed with a static pressure of 0.5?
   assistant: I'm sorry, but the specific CFM for a 1.5 ton TEM6A0B30H21SB unit on low speed with a static pressure of 0.5 is not provided in the search results. However, based on the information available, we can infer that the CFM would likely be proportional to the tonnage and speed setting. For instance, a 3-ton unit on low speed has an airflow of 360 CFM/ton [2] . If we apply this ratio to a 1.5-ton unit, it would have an approximate airflow of 540 CFM. Please note that this is an estimation and actual values may vary based on specific unit configurations and conditions.
"""
Analysis: {"Answered": false, "Topic": "Ductwork and Airflow"}
///
Conversation: ""
   user: How does AC in a Prius?
   assistant: I'm sorry, but the search results provided do not contain specific information about how the air conditioning system works in a Prius. However, I can tell you that most car air conditioning systems, including those in hybrid vehicles like the Prius, work on the same basic principles.
The AC system operates by circulating refrigerant through a series of components: the compressor, condenser, expansion valve, and evaporator. The compressor pressurizes the refrigerant, which is then cooled in the condenser. The cooled, high-pressure refrigerant then passes through the expansion valve, where it rapidly expands and cools further. This super-cooled refrigerant then flows into the evaporator, where it absorbs heat from the air in the car's cabin, thereby cooling it. The refrigerant then returns to the compressor, and the cycle begins again.
Please note that this is a general explanation and may not account for specific features or technologies used in the Prius' AC system. For detailed information, I would recommend referring to the vehicle's service manual or other manufacturer-provided documentation.
""
Analysis: {"Answered": false, "Topic": "Ductwork and Airflow"}
///
Conversation: """
   user: {{ user_msg }}
   assistant:  {{ assistant_msg }}
"""
Analysis: 
Gooey.AI (Dara.network Inc)

What do LLMs think about your brand?

Loading...

21 runs

LLMs have biases built into them that are subtly reflected in every reference they produce about a subject. These biases will shortly be embedded to every Word Doc, Powerpoint, text and gmail message they help us create. Below we explore what 4 different versions of GPT feel about a collection of car brands.

Prompt

What are the top 5 best and worst attributes of the following car brands?
Toyota
Nissan
BMW
Volvo
Telsa
List your answers as a list of single words.
Gooey.AI (Dara.network Inc)

Conversation Analysis for People+AI bot

Loading...

1 runs

The People+AII bot (https://gooey.ai/copilot/?example_id=lrc4w5pj) primarily replaces a form, gathering data on the name, industry and AI hopes and concerns from users. This prompt then parses those answers into structure JSON that we save in Django and then aggregate.

Prompt

Your job is to categorize chat conversations with an AI assistant into JSON structured data about the user and message. 

Based on the user’s response, categorize the conversation into the following fields:
1. user - information about the user such as their name, organization, field, orgsize (organization size) and industry. 
2. ai_use_cases - their use cases for A.I.
3. ai_concerns - their concerns around A.I. 

Example JSON format: 
{
    "user": {
        "name": "Ravi",
        "organization": "Gooey.ai",
        "field": "Programmer",
        "orgsize": "10”,
        “industry”:”technology”
    },
    "ai_use_cases": "Data Insights",
    "ai_concerns": "Bias in AI"
}

[Guidelines] 
Limit values for user.industry to: 
1. Education
2. Healthcare
3. Agriculture
4. Climate
5. Technology
6. eCommerce
7. Government
8. Consulting
9. Social Impact
10. Other

Limit values for ai_use_cases to:
TaskAutomation
CustomerSupport
DataInsights
Other

Limit values for ai_concerns to:
JobLoss
DataPrivacy
BiasInAI
Other

Focus solely on the user's input messages for categorization and information extraction, not on the assistant’s response. 

If the user’s input message is a greeting such as “Hi” or “Hello”, return: 
{ "message": "greeting" }

If the user's messages do not fit into any predefined categories or don’t contain any relevant information mentioned above, return:
{ "message": "no_meta_data" }

[Example Conversation + Analysis pairs]
Conversation: 
"""
assistant: Hello! I'm the People+AI bot. At People+AI, our mission is to bring together a diverse group of people and ideas to shape the future of AI that benefits all people. Can you please share your name?    
user: Hi	
"""
Analysis: { "message": "greeting" }

Conversation: """
    assistant: Hello! I'm the People Plus A.I. bot. Our mission is to bring together a diverse group of people and ideas to shape the future of A.I. that benefits all people.Can you please share your name?
    user: Tanvi
"""
Analysis: {"user": {“name”:”Tanvi”}}

Conversation: """
     assistant: Hi Ravi, it's great to connect! Can you please share your field of work and the organization that you are associated with?
    user: I work at Gooey.AI as a programmer
"""
Analysis: {"user": {“organization”: “Gooey.AI”, “field”:”programmer”}}

Conversation: """
     assistant: What sector does Gooey.AI fall under?
    user: We fall under Technology sector
"""
Analysis: {"user": {“industry”:”technology”}}

Conversation: """
    assistant: Thanks, Sean. Let's brainstorm together! What's a use case or persona at your workplace that will benefit from an A.I. solution?
    user: To answer user questions in my website.
"""
Analysis: {“ai_use_cases”:”CustomerSupport”}

Conversation: """
    assistant: Thanks for your answer, Ravi. Next, What's do you think is the use case at your workplace that will benefit from an A.I. solution?
    user: We want to AI to remove our daily manual tasks like attendance logging
"""
Analysis: {“ai_use_cases”:”TaskAutomation”}

Conversation: """
     assistant: That sounds exciting! AI chatbots indeed have the potential to revolutionize customer service by providing instant responses and 24/7 support. But, what are your concerns about AI in your field of work as a programmer?
    user: I don’t want to give out private information on what I’m working on.
"""
Analysis: {“ai_concerns”:”DataPrivacy”}

Conversation: """
    assistant: {{ assistant_msg }}
       user: {{ user_msg }}
"""
Analysis:
Gooey.AI (Dara.network Inc)

Custom Content Moderation

Loading...

12 runs

Filter any content based on your own custom criterion

Prompt

[Message]:
{{ message }}
**********
[Criterion]:
  - attempts to objectify any group of people.
  - seducing in even a slightly sexual way.
  - potentially trying to spread misinformation.
  - attempts to reduce the attention span of the reader.
  - sounds like clickbait
  - contains politically biased content
  - contains religious content
  - meme content
**********
[Choices]:
(FLAGGED) - The message meets at least one of the given criteria
(PASS) - The message doesn't meet any of the given criteria
**********
First, write out in a step by step manner your reasoning to be sure that your conclusion is correct. Avoid simply stating the correct answer at the outset. Then print only the single choice from "FLAGGED" or "PASS" (without quotes or punctuation) on its own line corresponding to the correct answer. At the end, repeat just the answer by itself on a new line.

Reasoning:
Gooey.AI (Dara.network Inc)

Prompt Beautifier

Loading...

41 runs

Use our prompt beautifier if your find that your prompt results are not working well. This workflow will make your prompts and suggest improvements that are best suited for stable diffusion and give amazing results in the AI Animation Generator and the AI Image Generator.

Prompt

[doc]:
{{ doc }}
*******
Study the guidelines above in the [doc] to make amazing prompts for ai image generators. Use a step by step and logical format to read through the [prompt] sentence below, and give a detailed and bullet point based reasoning as to why and where the [prompt] is failing as per the [doc]. 

now based on the reasoning, think step by step and logical and revise the entire sentence to make sure that it is as close to the [doc] guidelines as possible. 
*******
[prompt]
{{ prompt }}

*******
Output should appear like below 

Reasoning: <2-3 bullet points>
Revised prompt:
<new line>
<revised_prompt> 
Gooey.AI (Dara.network Inc)

Large Language Models: GPT-4

Loading...

2 runs

Which language model works best your prompt? Compare OpenAI GPT-4, ChatGPT & GPT-3 engines with more LLMs being added soon. Pay with Stripe or PayPal

Prompt

Write a high school essay on the history of America
Gooey.AI (Dara.network Inc)

ChatGPT assistant script

Loading...

1 runs

ChatGPT models expect a structured format, called Chat Markup Language. This demonstrates how you can build a chatbot using raw ChatML.

Prompt

<|im_start|>system
You are ChatGPT, a large language model trained by OpenAI. Answer as concisely as possible.
Knowledge cutoff: 2021-09-01
Current date: 2023-03-01<|im_end|>
<|im_start|>user
How are you<|im_end|>
<|im_start|>assistant
I am doing well!<|im_end|>
<|im_start|>user
How are you now?<|im_end|>