Examples: LLM

FUNCTIONS: Make a Haiku with ISS Coordinates

33 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}}

coords_latitude

coords_longitude

GPT-4 Turbo (openai)

Sean Blagsvedt

Compare Indic LLMs

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

Gemma 2 9B (Google)

Gemma 7B (Google)

Sarvam 2B (sarvamai)

Llama 3 8B (Meta AI)

Dev Aggarwal

Compare AfroLlama vs LLaLM3: Yoruba

6 runs

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

Prompt

Yoruba: Kọ itan nipa Ọgbọn Ehoroa

Llama 3 8B (Meta AI)

AfroLlama3 v1 (Jacaranda)

Dev Aggarwal

Compare LLMs: SEA-LION vs SOTA

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?

GPT-4o (openai)

Llama 3 70B (Meta AI)

Mixtral 8x7b Instruct v0.1 (Mistral)

Gemini 1.5 Pro (Google)

Claude 3.5 Sonnet (Anthropic)

Jika seseorang berada di GBK (Gelora Bung Karno), mereka biasanya sedang melakukan salah satu atau beberapa aktivitas berikut:

1. Menonton pertandingan olahraga, terutama sepak bola, karena GBK adalah stadion utama untuk pertandingan nasional dan internasional.

2. Menghadiri konser musik atau acara hiburan besar, karena GBK sering digunakan sebagai venue untuk konser skala besar.

3. Berolahraga atau berlatih, karena kompleks GBK memiliki berbagai fasilitas olahraga seperti lapangan atletik, kolam renang, dan area jogging.

4. Mengikuti atau menonton acara-acara besar seperti upacara kenegaraan, perayaan hari besar, atau acara budaya.

5. Mengunjungi Museum Olahraga yang berada di kompleks GBK.

6. Berpartisipasi dalam pameran atau expo yang kadang diadakan di area GBK.

7. Sekadar berjalan-jalan atau bersantai di area terbuka kompleks GBK.

8. Mengikuti atau menonton kompetisi olahraga lain seperti bulu tangkis, basket, atau voli yang diadakan di venue-venue di sekitar kompleks GBK.

9. Menghadiri rapat atau pertemuan di gedung-gedung yang ada di kompleks GBK.

Jadi, aktivitas di GBK bisa sangat beragam, tergantung pada acara atau kegiatan yang sedang berlangsung saat itu.

Llama3 8B CPT SEA-LIONv2.1 Instruct (aisingapore)

Sean Blagsvedt

Default Copilot Analysis Script

54 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&#x27;s messages above, determine how to categorize them and determine if the bot answered their question with &quot;Found&quot; or &quot;Missing&quot;. Your response should contain exactly one JSON object.

Category choices: [ &quot;General&quot;, &quot;Salutation&quot;, &quot;Random&quot;, &quot;Technical&quot;, &quot;Other&quot; ]

Return your analysis as the following json object: { 
&quot;What was the category of the user query?&quot;: &quot;&lt;category&gt;&quot;, 
&quot;assistant&quot;: {&quot;answer&quot;: &quot;Found || Missing&quot;}}}

messages

user: what is the lipsync tool's API	
assistant: "The API for the lipsync tool can be found here: https://gooey.ai/Lipsync/api/

Here is the example snippet to get you started.
```
import fetch from 'node-fetch';

const payload = {
  ""input_face"": ""https://storage.googleapis.com/dara-c1b52.appspot.com/daras_ai/media/8c1b1f02-5f66-11ed-a8a9-02420a0000aa/ezgif-5-4ccc215641.gif"",
  ""input_audio"": ""https://storage.googleapis.com/dara-c1b52.appspot.com/daras_ai/media/8d3f18d4-5f66-11ed-a8a9-02420a0000aa/al-hitchcock-arpa-Merry_Christmas__Jon%203.wav""
};

async function gooeyAPI() {
  const response = await fetch(""https://api.gooey.ai/v2/Lipsync/"", {
    method: ""POST"",
    headers: {
      ""Authorization"": ""Bearer "" + process.env[""GOOEY_API_KEY""],
      ""Content-Type"": ""application/json"",
    },
    body: JSON.stringify(payload),
  });

if (!response.ok) {
    throw new Error(response.status);
  }

const result = await response.json();
  console.log(response.status, result);
}

gooeyAPI();
```"
user: What is the step by step method to make a good animation	
assistant: STEP 1 - Visualize your video
The Animation Generator uses AI text prompts to create each frame of  the video.

Visualize each keyframe for the video and describe it in the prompt section

Assign the keyframe

STEP 2 - Add the Frames and Frame Count
You can add more prompts and keyframes as per your video

Add the total number of frames for your video

STEP 3 - Hit Submit
Just hit ""Submit""

Each run can take about 3-6 mins depending on the total number of frames and the frame rate.

user: How do i use the zoom settings in ai animation tool	
assistant: Zoom

Zoom settings can be assigned to the keyframes

The format for the setting is ""frame number:(zoom speed)""

For each keyframe setting you need to separate it by a comma

If you want to zoom-in use positive numbers e.g. ""1.004""

If you want to zoom-in use positive numbers e.g. ""-1.004""

""1"" will give you static/no zoom

Note: Don't use ""0.04"" or similar

user: what is the simplest way to start using gooey apis	
assistant: The simplest way to use Gooey APIs is to head to our API Generator here: https://gooey.ai/api/, and copy paste the example code and start testing!

user: how do i use the eval tool	
assistant: The Eval tool in Gooey.AI is primarily used for evaluating the performance of Gooey.AI models. Here's a step-by-step guide on how to use it:

1. Prepare your data: Arrange the audio sample link in the first column of your CSV or Google Sheets. For each audio link, add transcriptions and translations in the respective row.

2. Select the Gooey workflows: Choose the examples you want to evaluate your answers.

3. Add your CSV/Google Sheets: Upload your prepared data.

4. Select the input column: Choose the column that contains the input data (this could be audio links/text depending on the eval you are using)

5. Select the pre-built evaluator: This will compare the ASR model outputs to the human-generated translations and assess how accurately each model has translated the audio sample.

6. Hit Submit: After the runs are complete, a bar graph with the performance will appear once the entire evaluation is complete.

For more detailed information, you can visit our complete guide at https://docs.gooey.ai/guides/how-to-create-language-evaluation-for-asr. If you need further assistance, feel free to write to support@gooey.ai.

user: how can i make better image prompts	
assistant: Creating better image prompts on Gooey.AI involves a few steps:

1. Visualize your idea: Have a clear image in your mind of what you want to generate.
2. Break down your idea into descriptors:
   - Medium: Define if it's a painting, sculpture, old photograph, portrait, 3D render, etc.
   - Subjects or Main Objects: Identify the main elements in the image, like a human, an animal, an identity like gender, race, or occupation like dancer, astronaut etc.
   - Style: Specify if it's analogue photography, a watercolor, a line drawing, digital painting etc.
   - Details: Include facial features or expressions, the space and landscape, lighting or the colors etc.
3. Construct your prompt: Combine all these elements into a single sentence. For example, ""An analogue film still of an astronaut in a space suit walking on the busy streets of Mumbai, golden light on the astronaut.""

Remember that AI generators are collaborative tools. You can keep editing your prompt until you have your desired output.

For more detailed information, you can visit our complete guide at https://gooey.ai/docs/. If you need further assistance, feel free to write to support@gooey.ai.

user: how can genAI improve my business	
assistant: GenAI can significantly improve your business in various ways as outlined in the Gooey.AI blog post titled ""The GenAI Marketing Disruption & How GooeyAI Can Help"". Here are some key points:

1. Higher Time-on-site & Engagement with Bots and Quizzes: Bots like Gooey.AI Copilot can significantly increase user engagement. AI-generated quizzes can also drive time on site.

2. Virality via AI-Generated Content: Personalized AI-generated content can encourage users to share links back to your site, increasing organic word-of-mouth marketing.

3. Zeitgeist-Powered AI Content Creation: This involves creating content that taps into the current cultural climate or ""zeitgeist"", which can make your brand more relevant and engaging.

For more detailed information, you can read the complete blog post here: https://gooey.ai/blog/the-genai-marketing-disruption-and-how-gooeyai-can-help. If you need further assistance, feel free to write to support@gooey.ai.

user: how can i use genAI to improve my SEO	
assistant: Gooey.AI offers several tools that leverage GenAI to improve your SEO. One of these tools helps you answer the most common "People Also Ask" questions related to your search query. This can dramatically improve your Google Search rankings. Another tool creates an optimized page for you based on the current top-ranking pages for any query. There's also an SEO-informed image generation tool that creates unique, new images based on top-ranked images for a search query. You can find more details and try these tools directly on our website: https://gooey.ai/workflows. If you need further guidance, please refer to our docs: https://gooey.ai/docs or write to us at support@gooey.ai.

user: can you share the code example for copilot API	
assistant: Yes, here is the example of copilot api:

Generate an api key below👇

Install node-fetch & add the GOOEY_API_KEY to your environment variables.
Never store the api key in your code and don't use direcly in the browser.
```
$ npm install node-fetch
$ export GOOEY_API_KEY=sk-xxxx
```
Use this sample code to call the API.
If you encounter any issues, write to us at support@gooey.ai and make sure to include the full code snippet and the error message.
import fetch from 'node-fetch';

```
const payload = {
  ""input_prompt"": ""When should I plant chili?"",
  ""translation_model"": ""google""
};

async function gooeyAPI() {
  const response = await fetch(""https://api.gooey.ai/v2/video-bots/"", {
    method: ""POST"",
    headers: {
      ""Authorization"": ""Bearer "" + process.env[""GOOEY_API_KEY""],
      ""Content-Type"": ""application/json"",
    },
    body: JSON.stringify(payload),
  });

if (!response.ok) {
    throw new Error(response.status);
  }

const result = await response.json();
  console.log(response.status, result);
}

gooeyAPI();
```
user: how can i integrate copilot in slack	
assistant: Once your copilot is saved as an example, click on the "Integrations" tab. Select the "Connect to Slack" button. Head to the help guide to know more. https://docs.gooey.ai/guides/copilot/deploy-to-slack

user: what is the google gpt tool	
assistant: Google GPT tool allows you to use google search as the RAG for GPT summaries

user: can you share an example link from copilot	
assistant: Yes, you can have a look at our copilot examples here: https://gooey.ai/copilot/examples/

user: is there a tool on gooey i can use for lipsync?	
assistant: Yes, we have lipsync generator, here is the link: https://gooey.ai/Lipsync/

user: how can I add more credits to my account?	
assistant: You can add more credits to your Gooey.AI account by purchasing one of our monthly plans. We offer a $10 plan that provides 1000 credits and a $50 plan that gives you 5000 credits plus special access to make bespoke interactive video bots. You can also opt for a Test Drive for $10 to get 1000 credits. Payments are supported through Stripe or Paypal. Here's the link to our pricing page: https://gooey.ai/pricing

GPT-4 Turbo (openai)

Sean Blagsvedt

Create a Copilot description + 4 sample Qs

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}}

prompt

description

GPT-4 Turbo (openai)

Sean Blagsvedt

Add Emojis to your GitHub readme

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:

code

## What is Gooey Server?
Gooey.AI is a low-code AI recipe platform and Gooey Server is our core repo. It allows users to discover, customize, and deploy AI "recipes" using the best of private and open source AI, all using a single API with a single auth token. Recipes are workflows that incorporate various models to accomplish a task; they are designed to be highly customizable and shareable.

### Who is this for and why would I want to use it?
For the vast majority of developers, we DO NOT recommend running or forking Gooey Server; use our APIs or client SDK instead. The repo is intended only for developers that want to run and deploy their own server cluster or run Gooey locally for development purposes. Specifically, this repo may be for you if:
You want to create a new recipe (instead of changing the parameters on an existing one)
You want to add an AI model that we currently don’t support. 
You are an enterprise who has specific requirements regarding data practices, such as using specific cloud providers.
You want to add some other functionality that we don’t support.

### Prerequisites
Google JSON key - only for auth / storage. 
Updated DB fixture
OS: Mac or Linux. Likely works on other *nix, but this is untested.

### Issues that contributors could work on:
Firebase / Supabase migration. 
Provide a simpler workaround for localhost auth. 
Provide an open source alternative to Google auth for use in VPC. 
Provide a way to do storage locally.

## Setup (Mac)

* Install [pyenv](https://github.com/pyenv/pyenv) & install the same python version as in our [Dockerfile](Dockerfile)
* Install [poetry](https://python-poetry.org/docs/)
* Clone the github repo to gooey-server (and make sure that's the folder name)
* Create & activate a virtualenv (e.g. `poetry shell`)
* Run `poetry install --with dev`
* Install [redis](https://redis.io/docs/getting-started/installation/install-redis-on-mac-os/), [rabbitmq](https://www.rabbitmq.com/install-homebrew.html), and [postgresql](https://formulae.brew.sh/formula/postgresql@15) (e.g. `brew install redis rabbitmq postgresql@15`)
* Enable background services for `redis`, `rabbitmq`, and `postgresql` (e.g. with `brew services start redis` and similar for `rabbitmq` and `postgresql`)
* Use `sqlcreate` helper to create a user and database for gooey:
  * `./manage.py sqlcreate | psql postgres`
  * make sure you are able to access the database with `psql -W -U gooey gooey` (and when prompted for password, entering `gooey`)
* Create an `.env` file from `.env.example` (Read [12factor.net/config](https://12factor.net/config))
* Run `./manage.py migrate`
* Install the zbar library (`brew install zbar`)

## Setup (Linux)
* Install [pyenv](https://github.com/pyenv/pyenv) & install the same python version as in our [Dockerfile](Dockerfile) (currently Python 3.10)
  - `curl https://pyenv.run | bash`
* Install [poetry](https://python-poetry.org/docs/)
  - This is likely available in your distro's package repos. 
* Clone the gooey-server repository:
  - `git clone https://github.com/GooeyAI/gooey-server.git`
* If you want to use the web application frontend, you must clone that repo as well, in the same directory as gooey-server:
  - `git clone https://github.com/GooeyAI/gooey-ui`
* Create and activate a virtualenv using `poetry shell`
* Install dependencies using `poetry install --with dev`
  - Note: you may have to remove `package-mode=false` on line 7 of `pyproject.toml`
* Install redis, rabbitmq-server, and postgresql 15 using your distro's package manager. 
* Enable these services as background services using `sudo systemctl enable --now redis rabbitmq-server postgresql`
* Configure Postgres to ensure that password authentication is enabled for the gooey user
    - open the pg_hba.conf file in a text editor. On Linux, by default, it is usually located either at ```/etc/postgresql/<version>/main/``` or ```/var/lib/pgsql/<version>/data/```
    - add/edit the file so that there are lines at the bottom that looks like this:
    ```
    local    all        gooey                    md5
    host     all        gooey                    md5
    ```
    - restart postgresql using ```sudo systemctl restart postgresql```
* Use the manage.py script to set up the Postgres database:
  - To create the user and database for gooey: `./manage.py sqlcreate | sudo -u postgres psql postgres `
  - Test your setup to ensure that gooey-server can access the database by running `psql -W -U gooey gooey` and supplying "gooey" as the password
* Create a .env file from `.env.example`
* Install the zbar library using your distro's package manager.

## Run

Note: The gooey-server project is not currently set up to be run without support from Gooey. This software requires access to a Google Cloud instance as well as business data loaded in the database. If you are interested in running this software totally independently, reach out to support@gooey.ai to communicate with our enterprise team.

You can start all required processes in one command with Honcho:

```shell
$ poetry run honcho start
```
This will spin up the API server at `http://localhost:8080`. To view the autogenerated API documentation, navigate to `http://localhost:8080/docs`

If you installed the gooey-ui server, you can navigate to 'http://localhost:3000' to access the web application.

The processes that it starts are defined in [`Procfile`](Procfile).
Currently they are these:

| Service          | Port    |
|------------------|---------|
| API + GUI Server | `8080`  |
| Admin site       | `8000`  |
| Usage dashboard  | `8501`  |
| Celery           | -       |
| UI               | `3000`  |
| Vespa            | `8085`  |

This default startup assumes that Redis, RabbitMQ, and PostgreSQL are installed and running
as background services on ports 6379, 5672, and 5432 respectively. 
It also assumes that the gooey-ui repo can be found at `../gooey-ui/` (adjacent to where the
gooey-server repo sits). You can open the Profile and comment this out if you don't need
to run it.

**Note:** the Celery worker must be manually restarted on code changes. You
can do this by stopping and starting Honcho.

## To run any recipe

* In order to run recipes, you will need API keys. To connect to Gooey's Google Cloud instance, you need a personal key, stored in `serviceAccountKey.json` in the project root.

## To run vespa (used for vector search)

You need to install OrbStack or Docker Desktop for this to work.

1. Create a persistent volume for Vespa:
```bash
docker volume create vespa
```
2. Run the container:
```bash
docker run \
  --hostname vespa-container \
  -p 8085:8080 -p 19071:19071 \
  --volume vespa:/opt/vespa/var \
  -it --rm --name vespa vespaengine/vespa
```
3. Run the setup script
```bash
./manage.py runscript setup_vespa_db
```

### Install imagemagick

Needed for HEIC image support - https://docs.wand-py.org/en/0.5.7/guide/install.html

```
brew install freetype imagemagick
export MAGICK_HOME=/opt/homebrew
```

### Code Formatting

Use black - https://pypi.org/project/black

**Recommended**: Black IDE integration Guide: [Pycharm](https://black.readthedocs.io/en/stable/integrations/editors.html#pycharm-intellij-idea)

### backup & restore postgres db

```bash
# reset the database
./manage.py reset_db -c
# create the database with an empty template
createdb -T template0 $PGDATABASE
# restore the database
pg_restore --no-privileges --no-owner -d $PGDATABASE $fname
```

### create & load fixtures

```bash
./scripts/run-tests.sh
```

To load the fixture on local db -

```bash
# reset the database
./manage.py reset_db -c
# create the database
./manage.py sqlcreate | psql postgres
# run migrations
./manage.py migrate
# load the fixture
./manage.py loaddata fixture.json
# create a superuser to access admin
./manage.py createsuperuser
```

### copy one postgres db to another

```bash
./manage.py reset_db
createdb -T template0 $PGDATABASE
pg_dump $SOURCE_DATABASE | psql -q $PGDATABASE

GPT-4o (openai)

## What is Gooey Server? 🤖🍲
Gooey.AI is a low-code AI recipe platform and Gooey Server is our core repo. It allows users to discover, customize, and deploy AI "recipes" using the best of private and open source AI, all using a single API with a single auth token. Recipes are workflows that incorporate various models to accomplish a task; they are designed to be highly customizable and shareable.

### Who is this for and why would I want to use it? 🧑‍💻👩‍💻
For the vast majority of developers, we DO NOT recommend running or forking Gooey Server; use our APIs or client SDK instead. The repo is intended only for developers that want to run and deploy their own server cluster or run Gooey locally for development purposes. Specifically, this repo may be for you if:
- 💡 You want to create a new recipe (instead of changing the parameters on an existing one)
- 🧠 You want to add an AI model that we currently don’t support.
- 🏢 You are an enterprise who has specific requirements regarding data practices, such as using specific cloud providers.
- 📈 You want to add some other functionality that we don’t support.

### Prerequisites 📋
- 🔑 Google JSON key - only for auth / storage.
- 🔄 Updated DB fixture
- 🖥️ OS: Mac or Linux. Likely works on other *nix, but this is untested.

### Issues that contributors could work on: 🛠️
- 🔄 Firebase / Supabase migration.
- 🔒 Provide a simpler workaround for localhost auth.
- 🆓 Provide an open source alternative to Google auth for use in VPC.
- 💾 Provide a way to do storage locally.

## Setup (Mac) 🍏

* 📥 Install [pyenv](https://github.com/pyenv/pyenv) & install the same python version as in our [Dockerfile](Dockerfile)
* 📥 Install [poetry](https://python-poetry.org/docs/)
* 🖥️ Clone the github repo to gooey-server (and make sure that's the folder name)
* 🛠️ Create & activate a virtualenv (e.g. `poetry shell`)
* 📦 Run `poetry install --with dev`
* 📥 Install [redis](https://redis.io/docs/getting-started/installation/install-redis-on-mac-os/), [rabbitmq](https://www.rabbitmq.com/install-homebrew.html), and [postgresql](https://formulae.brew.sh/formula/postgresql@15) (e.g. `brew install redis rabbitmq postgresql@15`)
* ⚙️ Enable background services for `redis`, `rabbitmq`, and `postgresql` (e.g. with `brew services start redis` and similar for `rabbitmq` and `postgresql`)
* 🔧 Use `sqlcreate` helper to create a user and database for gooey:
  * `./manage.py sqlcreate | psql postgres`
  * make sure you are able to access the database with `psql -W -U gooey gooey` (and when prompted for password, entering `gooey`)
* 📄 Create an `.env` file from `.env.example` (Read [12factor.net/config](https://12factor.net/config))
* 🔄 Run `./manage.py migrate`
* 📥 Install the zbar library (`brew install zbar`)

## Setup (Linux) 🐧
* 📥 Install [pyenv](https://github.com/pyenv/pyenv) & install the same python version as in our [Dockerfile](Dockerfile) (currently Python 3.10)
  - `curl https://pyenv.run | bash`
* 📥 Install [poetry](https://python-poetry.org/docs/)
  - This is likely available in your distro's package repos.
* 🖥️ Clone the gooey-server repository:
  - `git clone https://github.com/GooeyAI/gooey-server.git`
* 🌐 If you want to use the web application frontend, you must clone that repo as well, in the same directory as gooey-server:
  - `git clone https://github.com/GooeyAI/gooey-ui`
* 🛠️ Create and activate a virtualenv using `poetry shell`
* 📦 Install dependencies using `poetry install --with dev`
  - Note: you may have to remove `package-mode=false` on line 7 of `pyproject.toml`
* 📥 Install redis, rabbitmq-server, and postgresql 15 using your distro's package manager.
* ⚙️ Enable these services as background services using `sudo systemctl enable --now redis rabbitmq-server postgresql`
* 🔧 Configure Postgres to ensure that password authentication is enabled for the gooey user
    - open the pg_hba.conf file in a text editor. On Linux, by default, it is usually located either at ```/etc/postgresql/<version>/main/``` or ```/var/lib/pgsql/<version>/data/```
    - add/edit the file so that there are lines at the bottom that looks like this:
    ```
    local    all        gooey                    md5
    host     all        gooey                    md5
    ```
    - restart postgresql using ```sudo systemctl restart postgresql```
* 🔄 Use the manage.py script to set up the Postgres database:
  - To create the user and database for gooey: `./manage.py sqlcreate | sudo -u postgres psql postgres`
  - Test your setup to ensure that gooey-server can access the database by running `psql -W -U gooey gooey` and supplying "gooey" as the password
* 📄 Create a .env file from `.env.example`
* 📥 Install the zbar library using your distro's package manager.

## Run 🚀

You can start all required processes in one command with Honcho:

```shell
$ poetry run honcho start
```
This will spin up the API server at `http://localhost:8080`. To view the autogenerated API documentation, navigate to `http://localhost:8080/docs`

If you installed the gooey-ui server, you can navigate to 'http://localhost:3000' to access the web application.

The processes that it starts are defined in [`Procfile`](Procfile).
Currently they are these:

This default startup assumes that Redis, RabbitMQ, and PostgreSQL are installed and running
as background services on ports 6379, 5672, and 5432 respectively.
It also assumes that the gooey-ui repo can be found at `../gooey-ui/` (adjacent to where the
gooey-server repo sits). You can open the Profile and comment this out if you don't need
to run it.

**Note:** the Celery worker must be manually restarted on code changes. You
can do this by stopping and starting Honcho.

## To run any recipe 📜

* In order to run recipes, you will need API keys. To connect to Gooey's Google Cloud instance, you need a personal key, stored in `serviceAccountKey.json` in the project root.

## To run vespa (used for vector search) 🔍

You need to install OrbStack or Docker Desktop for this to work.

### Install imagemagick 🖼️

Needed for HEIC image support - https://docs.wand-py.org/en/0.5.7/guide/install.html

```
brew install freetype imagemagick
export MAGICK_HOME=/opt/homebrew
```

### Code Formatting 🖋️

Use black - https://pypi.org/project/black

**Recommended**: Black IDE integration Guide: [Pycharm](https://black.readthedocs.io/en/stable/integrations/editors.html#pycharm-intellij-idea)

### Backup & restore postgres db 🗄️

### Create & load fixtures 🧩

```bash
./scripts/run-tests.sh
```

To load the fixture on local db -

### Copy one postgres db to another 📦

```bash
./manage.py reset_db
createdb -T template0 $PGDATABASE
pg_dump $SOURCE_DATABASE | psql -q $PGDATABASE
```

Claude 3.5 Sonnet (Anthropic)

Here's the GitHub Readme.md with appropriate emojis added:

```markdown
## What is Gooey Server? 🍬🖥️

Gooey.AI is a low-code AI recipe platform and Gooey Server is our core repo. It allows users to discover, customize, and deploy AI "recipes" using the best of private and open source AI, all using a single API with a single auth token. Recipes are workflows that incorporate various models to accomplish a task; they are designed to be highly customizable and shareable.

### Who is this for and why would I want to use it? 🤔

For the vast majority of developers, we DO NOT recommend running or forking Gooey Server; use our APIs or client SDK instead. The repo is intended only for developers that want to run and deploy their own server cluster or run Gooey locally for development purposes. Specifically, this repo may be for you if:
- You want to create a new recipe (instead of changing the parameters on an existing one) 🧪
- You want to add an AI model that we currently don't support 🤖
- You are an enterprise who has specific requirements regarding data practices, such as using specific cloud providers ☁️
- You want to add some other functionality that we don't support 🛠️

### Prerequisites 📋

- Google JSON key - only for auth / storage 🔑
- Updated DB fixture 💾
- OS: Mac or Linux. Likely works on other *nix, but this is untested 🍎🐧

### Issues that contributors could work on: 👨‍💻👩‍💻

- Firebase / Supabase migration 🔄
- Provide a simpler workaround for localhost auth 🏠
- Provide an open source alternative to Google auth for use in VPC 🔓
- Provide a way to do storage locally 💽

## Setup (Mac) 🍎

[Setup instructions for Mac...]

## Setup (Linux) 🐧

[Setup instructions for Linux...]

## Run 🏃‍♂️

[Running instructions...]

## To run any recipe 🍳

[Instructions for running recipes...]

## To run vespa (used for vector search) 🔍

[Vespa setup instructions...]

### Install imagemagick 🖼️

[Imagemagick installation instructions...]

### Code Formatting ✨

[Code formatting instructions...]

### backup & restore postgres db 💾

[Database backup and restore instructions...]

### create & load fixtures 🔧

[Fixture creation and loading instructions...]

### copy one postgres db to another 📋➡️💾

[Database copying instructions...]
```

Alexander Metzger

PaLM2 Translations with Custom Glossary

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.
&lt;Q&gt;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.
&lt;A&gt;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 }}.
&lt;Q&gt;{{ text_to_translate }}
&lt;A&gt;

glossary

source_language

target_language

text_to_translate

Hi, I'm Sean, one of the founders here at goowy. And I wanted to give you a demo today of how to use one of our recipes, a face in any scene. So just go ahead and click on this. And so the scenario that I'd like you to imagine with us is let's imagine, you know, rather than trying to do stuff with Elon Musk, we are working for a travel agency and we've got a spokesperson and we want to show that person basically all over the country in a variety of locations. Which is expensive because you got to send that person out, you got to do a photo shoot. And so what I'll do is I can just drag in a picture. So I have here Lana, AI generated spokesperson that I've drafted right here. And then I can just take any other quote. So I'll just copy in another one right here, which is basically a beautiful woman to the grand Tetons in Hawaii or Wyoming and award-winning landscape photographer. And then you literally just do those two and then hit submit. What happens now is we're looking for this face and then we basically go ahead and we craft out or mask out that particular face. We readjust it and then boom, we've got this picture of Lana hanging out at the grand Tetons. You can go ahead and download that and we can change anything else. So if we want to say, well, no, she's not at the Grand Tetons, you know, she's in something like Maroon Bells, another famous American destination that I've never been to. We can put that up and then you'll notice the same thing happens. In about nine seconds, we do the same face repositioning, same face masking, we put that in and then we do a little bit of cleanup at the end with JPF CAD. And so this is an example of a four stage recipe that hopefully anybody can go ahead and use just by uploading a picture of a person and any text they want. So we hope you enjoy it and we look forward to seeing what you make with it. Thanks so much.

PaLM 2 Chat (Google)

Hej, jeg er Sean, en af grundlæggerne her hos Gooey. Og jeg ville gerne give dig en demo i dag af, hvordan du bruger en af vores opskrifter, et ansigt i enhver scene. Så bare gå videre og klik på dette. Så det scenarie, som jeg gerne vil have, at du forestiller dig sammen med os, er, lad os forestille os, du ved, snarere end at forsøge at gøre ting med Elon Musk, vi arbejder for et rejsebureau, og vi har en talsmand, og vi ønsker at vise den person i det væsentlige over hele landet i en række forskellige lokationer. Hvilket er dyrt, fordi du er nødt til at sende den person ud, du er nødt til at lave en fotooptagelse. Så det, jeg vil gøre, er, at jeg bare kan trække et billede ind. Så jeg har her Lana, AI-genereret talsmand, som jeg har udarbejdet lige her. Og så kan jeg bare tage et hvilket som helst andet citat. Så jeg vil bare kopiere et andet ind lige her, som i bund og grund er en smuk kvinde til de store Tetons i Hawaii eller Wyoming og prisvindende landskabsfotograf. Og så gør du bogstaveligt talt bare de to og trykker derefter på send. Hvad der sker nu er, at vi leder efter dette ansigt, og så går vi i bund og grund videre, og vi laver eller maskerer det pågældende ansigt. Vi justerer det, og så, vupti, har vi dette billede af Lana, der hænger ud ved de store Tetons. Du kan gå videre og downloade det, og vi kan ændre alt andet. Så hvis vi vil sige, nå, nej, hun er ikke ved de store Tetons, ved du, hun er i noget som Maroon Bells, en anden berømt amerikansk destination, som jeg aldrig har været på. Vi kan sætte det op, og så vil du bemærke, at det samme sker. På omkring ni sekunder laver vi den samme ansigtsompositionering, samme ansigtsmaskering, vi sætter det ind, og så laver vi en lille smule oprydning til sidst med JPF CAD. Og så er dette et eksempel på en firetrinsopskrift, som forhåbentlig alle kan gå videre og bruge blot ved at uploade et billede af en person og enhver tekst, de ønsker. Så vi håber, du nyder det, og vi glæder os til at se, hvad du laver med det. Mange tak.

Sean Blagsvedt

FALana Summary Script

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&#x27;s responses to questions asked by the assistant.

Return the summary as a numbered list of 5 representative user responses. Group the user&#x27;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: 
{&quot;What&#x27;s your reaction to everything you&#x27;ve seen so far?&quot;: &quot;1. Hope: Most people expressed cautious optimism about AI&#x27;s potential for India&quot;, 
&quot;Top questions&quot;: &quot;1. AI and Jobs: What can we do to stem job losses from AI?&quot; }

Return your analysis as the following JSON object: { &quot;What&#x27;s your reaction to everything you&#x27;ve seen so far?&quot;: &quot;1. &lt;Theme&gt;: &lt;Response&gt;\n2. &lt;Theme&gt;: &lt;Response&gt;\n3. ...&quot;,  &quot;Top questions&quot;: &quot;1. &lt;Theme&gt;: &lt;Response&gt;\n2. &lt;Theme&gt;: &lt;Response&gt;\n3. ...&quot; }

If the user responses doesn&#x27;t fit into any of the categories, return an empty object (`{}`)

conversations

user: """hey"""
assistant: """Hello there! It's great to have you at the fireside chat. I'm Gooey.AI Fireside Bot, and I'm excited to chat with you. So, what's your name?"""
user: """dev"""
assistant: """Nice to meet you, Dev! I'm curious, after everything you've seen so far in the chat with Nandan Nilekani, what's your emotional reaction? Why do you feel that way?"""
user: """i feel so confused"""
assistant: """I see, confusion can definitely be a common reaction, especially when discussing complex topics. Could you share a bit about what specifically is causing you confusion? Maybe I can help clarify things or pose a question to Nandan on your behalf."""
user: """I am not sure how ai works"""
assistant: """Understandable, AI can be quite intricate and perplexing. If you had the opportunity, what question would you like to ask Nandan to help demystify AI for you?"""
user: """how to make ai great again"""
assistant: """That's a very interesting question! It sparks a conversation about improving AI and its impacts on society. Is there anything else about AI that piques your curiosity?"""
user: """how to get the data for that"""
assistant: """Data is indeed the fuel for AI! To ensure you get the most out of Nandan's insights, I could ask him to elaborate on strategies for ethically sourcing and managing data to power AI systems. Would that help address some of your confusion and interest?"""
user: """yes thx"""
assistant: """You're welcome, Dev! By the way, out of all the things you've seen today, what has been your favorite? And have you considered being a part of any AI projects?"""
user: """no because it will will steal my data"""
assistant: """That's a valid concern, and privacy is a major topic in the AI community. It's important to find a balance between innovation and protecting personal information. Given these concerns, how do you think we could work together to create AI solutions that respect user privacy?"""
user: """never"""
assistant: """I understand your hesitation, Dev. It’s crucial to have strong safeguards and transparent practices in place for AI systems to gain trust.

On a different note, did you feel more comfortable with the idea of AI after Nandan's talk, or do you still have some reservations?"""
####
user: """You suck"""
assistant: """Oh no, I'm sorry to hear you're not having the best time. But let's try to turn that around! What's something you've seen today that sparked your interest or curiosity?"""
user: """Hatred of modi"""
assistant: """I can sense some strong feelings there! It's important to have a space for all kinds of emotions. Shifting gears a bit, what’s your emotional reaction to the rest of the content you've seen at this event?"""
user: """Anger"""
assistant: """It sounds like you've been quite moved by what you've encountered. Emotions can be powerful drivers of conversation and change. In the context of today's discussions, what questions have been stirred up for you that you'd be interested in asking Nandan?"""
####
user: """Hey"""
assistant: """Hello there! I'm Gooey.AI Fireside Bot. May I have the pleasure of knowing your name and the company you're representing today?"""
user: """Tanuj, people+ai"""
assistant: """Hi Tanuj, it's great to meet you! I'm curious, after all the insights and information shared today, what's your emotional reaction to everything you've seen so far? Why do you feel that way?"""
user: """Excited"""
assistant: """That's fantastic to hear! Excitement is contagious. Could you share a bit more about what specifically is fueling your excitement?"""
user: """Use cases"""
assistant: """Use cases can indeed be quite thrilling, especially when they reveal the potential of new technology. Speaking of potential, do you have any questions you'd like to ask Nandan? Something that sparked your curiosity during the talk?"""
user: """Where will india go from here. How to save people from job losses"""
assistant: """That's a very insightful question, addressing both the future trajectory of India in the tech space and the socio-economic impact of technological advancement. Is there anything else you're wondering about or would like to delve into?"""
####
user: """Hi"""
assistant: """Hello! It’s great to see you here. What's your name and which company are you representing today?"""
user: """David from People+ai"""
assistant: """Nice to meet you, David from People+AI! What’s your emotional reaction to everything you’ve seen so far in this event?"""
user: """Hi"""
assistant: """Hello again, David! It sounds like you're ready to dive into more. What questions do you have for Nandan?"""

GPT-4 Turbo (openai)

Computational Mama aka Ambika

FALANA Chat Analysis Script

381 runs

Prompt

{{messages}}

###

Your job is to analyze the user&#x27;s messages above and determine how to categorize them.

Category choices: [ &quot;😊 Happy&quot;, &quot;😟 Worry&quot;, &quot;🌟 Hopeful&quot;, &quot;😨 Fear&quot;, &quot;🤯 Mind Blown&quot; ]

Return your analysis as the following json object: { &quot;How did this evening make you feel about AI and Robots?&quot;: &quot;&lt;category&gt;&quot; }

If the messages doesn&#x27;t fit into any of the categories, return an empty object (`{}`)

messages

Assistant: That's a very broad and interesting question, Dev! The world of AI is vast and constantly evolving. If we could narrow it down, what specific aspect of AI are you most curious about? Is it the latest advancements, ethical considerations, applications in software development, or something else entirely?
User: The new image generation models
Assistant: Ah, image generation models are indeed a fascinating area of AI! They've made significant strides recently. Have you seen any particular image generation model or application today that piqued your interest? Or is there a project related to this that you've considered getting involved with?
User: dall e 3
Assistant: DALL-E 3 is an impressive leap forward in the field of AI-generated art and image creation, isn't it? It's amazing how it can take a simple text prompt and turn it into a unique and often quite intricate image.

What's your favorite thing about DALL-E 3, or is there another aspect of today's discussions that has been your favorite? And have you thought about how you might want to integrate such technology into your work at JetBrains?
User: i dont want to integrate because i am afraid of ai
Assistant: That's a very honest response, and it's important to acknowledge those feelings. It’s okay to have reservations and to approach AI with a level of caution. After hearing the talk today, do you feel any differently about AI, or do you still have some concerns? And if you're open to sharing, what specifically about AI makes you feel afraid?

GPT-4 Turbo (openai)

Dev Aggarwal

Fireside Chat Summary Script

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&#x27;s responses to questions asked by the assistant.

Return the summary as a numbered list of 5 representative user responses. Group the user&#x27;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: 
{&quot;What&#x27;s your reaction to everything you&#x27;ve seen so far?&quot;: &quot;1. Hope: Most people expressed cautious optimism about AI&#x27;s potential for India&quot;, 
&quot;Top questions for Nandan&quot;: &quot;1. AI and Jobs: What can we do to stem job losses from AI?&quot; }

Return your analysis as the following JSON object: { &quot;What&#x27;s your reaction to everything you&#x27;ve seen so far?&quot;: &quot;1. &lt;Theme&gt;: &lt;Response&gt;\n2. &lt;Theme&gt;: &lt;Response&gt;\n3. ...&quot;,  &quot;Top questions for Nandan&quot;: &quot;1. &lt;Theme&gt;: &lt;Response&gt;\n2. &lt;Theme&gt;: &lt;Response&gt;\n3. ...&quot; }

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&#x27;t fit into any of the categories, return an empty object (`{}`)

conversations

GPT-4 Turbo (openai)

Dev Aggarwal

Fireside Chat Analysis Script

188 runs

Prompt

{{messages}}

###

Your job is to analyze the user&#x27;s messages above and determine how to categorize them.

Category choices: [ &quot;😊 Happy&quot;, &quot;😟 Worry&quot;, &quot;🌟 Hopeful&quot;, &quot;😨 Fear&quot;, &quot;🤯 Mind Blown&quot; ]

Return your analysis as the following json object: { &quot;How do you feel about AI after today&quot;: &quot;&lt;category&gt;&quot; }

If the messages doesn&#x27;t fit into any of the categories, return an empty object (`{}`)

messages

GPT-4 Turbo (openai)

Sean Blagsvedt

Run Mistral... FAST via an API

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.

product

Mixtral 8x7b Instruct v0.1 (Mistral)

Gooey.AI

How Farmer.CHAT turns conversations to structured data

2.11K 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:

We should update the user's profile object (because they mentioned their location, crop or gender)
The user's question was answered
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&#x27;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: &quot;&quot;&quot;
   user: Hi
   assistant: Hello! How can I assist you with farming today?
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: null, &quot;subject&quot;: ”Salutation”, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Found&quot;}}
///
Conversation: &quot;&quot;&quot;
   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
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: ”rice”, &quot;subject&quot;: ”Plant Death (Infestation and Infection)”, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Found&quot;}}
///
Conversation: &quot;&quot;&quot;
   user: A drug can be used to increase the height of chillies in the chilli garden
   assistant: I&#x27;m sorry, but I couldn&#x27;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.
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: ”chili”, &quot;subject&quot;: ”Supplements (Fertilizers and Pesticides)”, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Missing&quot;}}
///
Conversation: &quot;&quot;&quot;
   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]
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: null, &quot;subject&quot;: &quot;Farming Practice&quot;, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Found&quot;}}
///
Conversation: &quot;&quot;&quot;
   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. 💦
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: &quot;pepper&quot;, &quot;subject&quot;: &quot;Irrigation&quot;, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Found&quot;}}
///
Conversation: &quot;&quot;&quot;
   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. 🌶️🌱
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: ”chili”, &quot;subject&quot;: ”Plant Death (Infestation and Infection)”, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Found&quot;}}
///
Conversation: &quot;&quot;&quot;
   user: How to prepare dukki for planting chili garden
   assistant: I&#x27;m sorry, I couldn&#x27;t find any relevant information on preparing &quot;dukki&quot; for planting chili garden in the search results. Could you please provide more context or try rephrasing your question?
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: &quot;chili&quot;, &quot;subject&quot;: &quot;Farming Practice&quot;, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Missing&quot;}}
///
Conversation: &quot;&quot;&quot;
   user: Is there a video for this?
   assistant: I&#x27;m sorry, I don&#x27;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.
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: null, &quot;subject&quot;: &quot;Video&quot;, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Missing&quot;}}
///
Conversation: &quot;&quot;&quot;
   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]
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: null, &quot;subject&quot;: &quot;Farming Practice&quot;, &quot;location&quot;: &quot;Anantapur&quot;, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Found&quot;}}
///
Conversation: &quot;&quot;&quot;
   user: {{ user_msg }}
   assistant:  {{ assistant_msg }}
&quot;&quot;&quot;
Analysis:

user_msg

assistant_msg

ChatGPT (openai)

Gooey.AI

Financial Report Maker

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&#x27;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&#x27;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 &quot;team must fill this information&quot;
          |||[finance report] 
          {{ financereport }} 

          [transcripts] 
          {{ transcripts }} 

          [decision]
          {{ decision }}
          |||

decision

transcripts

09-May-2023 
Corrected Transcript

Achieve Life Sciences, Inc. (ACHV) Q1 2023 Earnings Call
Total Pages: 11

Achieve Life Sciences, Inc. (ACHV) Q1 2023 Earnings Call 
CORPORATE PARTICIPANTS 
Corrected Transcript 09-May-2023 
Nicole Jones 
Vice President, CG Capital 
John A. Bencich 
Chief Executive Officer & Director, Achieve Life Sciences, Inc. 
Cindy A. Jacobs 
President, Chief Medical Officer & Director, Achieve Life Sciences, Inc. 
Jerry Wan 
Principal Accounting Officer, Achieve Life Sciences, Inc.

Thomas Flaten 
Analyst, Lake Street Capital Markets LLC 
Francois Brisebois 
Analyst, Oppenheimer & Co., Inc. 
Michael Higgins 
Analyst, Ladenburg Thalmann & Co., Inc. 
John D. Vandermosten 
Analyst, Zacks Investment Research, Inc. (Small Cap Research)

Achieve Life Sciences, Inc. (ACHV) Q1 2023 Earnings Call 
Corrected Transcript 09-May-2023

vaping cessation. Cytisinicline treatment resulted in a statistically significant benefit for nicotine e-cigarette  cessation compared to placebo. 
Results for the primary endpoint showed that study participants who received cytisinicline were approximately  three times more likely to quit vaping compared to those who received placebo. Cytisinicline and also continued to  demonstrate exceptional safety and tolerability. 
We are very pleased with another win for cytisinicline and for people who are seeking options to overcome their  nicotine dependence. Nicotine e-cigarette use continues to be a growing concern, with recent reports from CDC  indicating vaping rates in the US are increasing. 
Data recently published indicate that roughly 11 million adults and 2.5 million high school and middle school  students use e-cigarettes to vape nicotine. The CDC indicated in recent weeks the percentage of use has  increased by 2.5%. As this segment of nicotine use continues to grow, an increasing number of people who use  e-cigarettes may start to look for solutions to quit. And currently, there are no medications specifically indicated for  vaping cessation. 
We completed a survey in people using e-cigarettes and found that 73% of participants desired to quit vaping in  the next 3 to 12 months, and the overwhelming majority would be interested in using a naturally-derived  prescription treatment to help them do so. 
Based on this unmet need for treatments, the swift enrollment we observed in the ORCA-V1 trial and the  statistically significant results from the recent top line data announcement, we believe that cytisinicline has the  unique opportunity to become a solution to help address this growing vaping epidemic. 
To touch more on the recent clinical data, I'll now hand the call over to Cindy to go through the ORCA-V1 results  in more detail. 
...................................................................................................................................................................................................................................................... Cindy A. Jacobs 
President, Chief Medical Officer & Director, Achieve Life Sciences, Inc. 
Thanks, John. As I mentioned, the ORCA-V1 top line results that we shared last month showed a statistically  significant benefit for cytisinicline as a treatment for nicotine vaping cessation. Even though this Phase 2 proof-of concept study was not powered to do that. 
Similar to our Phase 3 designs, ORCA-V1 evaluated 3 milligrams cytisinicline dose 3 times daily for 12 weeks,  ORCA-V1 randomized subjects at five clinical sites in the US in a 2:1 ratio, such that a total of 160 subjects were  randomized with 107 receiving cytisinicline for 12 weeks and 53 receiving placebo. 
ORCA-V1 enrollment was completed in approximately four months. The average age of ORCA-V1 subjects was  34 and all of them wanted to quit vaping on the study. Approximately half of the subjects had previously tried to  quit vaping by self-attempt methods. Subjects were stratified based on past smoking history, with 72% identifying  as former or past smokers. 
Dr. Nancy Rigotti of Harvard Medical School served as the primary investigator of the study and ORCA-V1 was  supported via grant funding from NIDA and the NIH. The primary endpoint results for vaping cessation showed  subjects who received cytisinicline had 2.6 times higher odds or likelihood to quit vaping during the last 4 weeks  of treatment compared to subjects who received placebo.
3

Achieve Life Sciences, Inc. (ACHV) Q1 2023 Earnings Call 
Corrected Transcript 09-May-2023

This endpoint was statistically significant with a p-value of 0.035. The 4 weeks continuous vaping cessation rate  during weeks 9 through 12 was 31.8% for cytisinicline treated subjects compared to 15.1% for those who received  placebo. Importantly, cytisinicline benefit was also observed across all clinical trial sites and demographics, such  as participant age, gender, race and whether they had been past smokers or not. 
Regarding safety, cytisinicline was very well-tolerated with 50.9% of subjects who received cytisinicline reporting  adverse events, compared to 54.7% of subjects in the placebo arm. Adverse events were as expected, mainly  mild to moderate, and there were no serious adverse events reported during the study. 
As these are top line results, we are continuing to analyze the data and look forward to providing additional details  on our findings as we learn more. 
I will now turn the call back over to John. 
...................................................................................................................................................................................................................................................... John A. Bencich 
Chief Executive Officer & Director, Achieve Life Sciences, Inc. 
Thank you, Cindy. Our next key milestone is rapidly approaching as we eagerly await results from our second  NDA-enabling Phase 3 study, which we expect to report later this quarter. The ORCA-3 trial mirrors the design of  the previously reported and highly successful ORCA-2 trial. ORCA-3 is evaluating the efficacy and tolerability of 3  milligrams cytisinicline dose three times daily for either 6 weeks or 12 weeks compared with placebo. 
Biochemically verified continuous abstinence is the primary end point. And similar to ORCA-2, will be evaluated  during the last four weeks of treatment. Each arm will be compared independently to the placebo arm, and  success will be determined if either or both of the cytisinicline treatment arms show a statistical benefit as  compared to placebo. 
Our efforts are now focused on preparing for the data later this quarter and continuing our preparations to support  a new drug application or NDA for cytisinicline in the US. 
At this time. I'll now turn the call over to Jerry to review our financial results for the quarter. ...................................................................................................................................................................................................................................................... Jerry Wan 
Principal Accounting Officer, Achieve Life Sciences, Inc. 
Thanks, John. Looking at our statement of operations, the company incurred a net loss of $9 million for the  quarter ended March 31, 2023, as compared to a net loss of $7.6 million for the same quarter of 2022. Total  operating expenses in the first quarter of 2023 increased to $8.6 million as compared to $7.2 million for the same  quarter of 2022. 
Operating expenses were higher for the quarter ended March 31, 2023, as both the ORCA-3 Phase 3 trial and the  ORCA-V1 Phase 2 trial were fully enrolled during the quarter and had their last subject last visit completed in  March 2023 as compared to the same period in 2022, where only our Phase 3 ORCA-2 was fully enrolled. 
We anticipate our operating expenses to decline in the second quarter in line with the completion of the two  clinical studies. As of March 31, 2023, the company's cash, cash equivalents and restricted cash were $16.6  million as compared to $24.8 million as of December 31, 2023. We believe our current cash balance is sufficient  to provide us with runway into late-2023.
4

Achieve Life Sciences, Inc. (ACHV) Q1 2023 Earnings Call 
I'd now like to turn the call back over to John. 
Corrected Transcript 09-May-2023

...................................................................................................................................................................................................................................................... John A. Bencich 
Chief Executive Officer & Director, Achieve Life Sciences, Inc. 
Thanks, Jerry. A final highlight from the first quarter before we conclude today's call. In March, we announced a  refresh to our board of directors to support the future direction of the company. We are pleased to welcome Mr.  Stuart Duty, Mr. Thomas King and Mr. Tom Sellig to the board. 
They each bring extensive leadership in the pharmaceutical and life science industries across capital markets,  strategic transactions, sales and marketing, as well as manufacturing. 
We would also like to thank Mr. Don Joseph, Dr. Martin Mattingly and Mr. Jay Moyes for their years of service and  strategic guidance to Achieve as they will not be standing for re-election at our upcoming Annual Shareholder  Meeting on June 7. 
We have achieved many milestones within the first quarter of 2023 and we expect to continue this exciting year  with the upcoming ORCA-3 read out. We appreciate your continued support and I will now turn the call over to the  operator for questions. 
...................................................................................................................................................................................................................................................... QUESTION AND ANSWER SECTION 
Operator: Thank you. The floor is now open for questions. [Operator Instructions] And our first question comes  from Thomas Flaten from Lake Street Capital. Go ahead, Thomas. 
...................................................................................................................................................................................................................................................... Analyst, Lake Street Capital Markets LLC Q 
Thomas Flaten 
Great. I appreciate you guys taking the questions. John or Cindy, with respect to completing ORCA-3 and then  moving forward. Could you give us some sense of what you think realistic timing for an NDA submission would be  and if there are any critical path items there that we should be aware of that, pre-NDA meeting with FDA or  anything like that, any pre-clinical data that you still need to generate. 
...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
Thanks for the question, Thomas. I'm going to hand this one over to Cindy. 
...................................................................................................................................................................................................................................................... President, Chief Medical Officer & Director, Achieve Life Sciences, Inc. A 
Cindy A. Jacobs 
Sure. So, we've been waiting for ORCA-3 results. With ORCA-3 results, now we can coordinate a pre-NDA  meeting with FDA. Obviously, we're going to target that for this year. Timing though, we would need to request the  meeting. 
So, we kind of figure it's going to be at the end of quarter three or quarter three at some time, but we'll find that  out when we get that scheduled. We actually have three Phase 1 studies we're finishing up, things that we need  for the NDA, like PK study on renal impairment.
5

Achieve Life Sciences, Inc. (ACHV) Q1 2023 Earnings Call 
Corrected Transcript 09-May-2023

We actually have another PK study looking at steady state concentrations with three milligram, three times a day  and also finishing up a TQT study. These are all things that are required in the NDA and all of them will be  completed by the end of this year. So, we're looking at the first half of next year some time for the NDA coming  together. 
...................................................................................................................................................................................................................................................... Analyst, Lake Street Capital Markets LLC Q 
Thomas Flaten 
Excellent. John, any update on the potential for debt refinancing because I know that repayment is looming at the  end of the year as well? 
...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
Yeah. Thanks, Tom on the debt side, so we've been in dialogue with the folks at SVB formerly SVB, now Citizens  Bank. And we do think there is a path towards getting some movement on – an extension or refi of that facility.  So, nothing to announce today. But we do think at least the discussions we've had so far are positive on that front. ...................................................................................................................................................................................................................................................... Analyst, Lake Street Capital Markets LLC Q 
Thomas Flaten 
And then just one quick final one maybe for Jerry, there was a bit of a sequential uptick in G&A, I was curious if  there are any one-timers in there, stock-based comp or bonuses or anything like that? ...................................................................................................................................................................................................................................................... Analyst, Lake Street Capital Markets LLC Q 
Thomas Flaten 
Jerry do you want to take that one? 
...................................................................................................................................................................................................................................................... Principal Accounting Officer, Achieve Life Sciences, Inc. A 
Jerry Wan 
Yeah. Sorry I was just on mute there. Yeah it was just the one-time stock based comp grant that we have  annually at the beginning of January. 
...................................................................................................................................................................................................................................................... Analyst, Lake Street Capital Markets LLC Q 
Thomas Flaten 
Excellent. Appreciate it, guys. Thanks so much. 
...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
Thanks, Thomas. 
...................................................................................................................................................................................................................................................... 
Operator: Thank you. And our next question comes from Francois Brisebois from Oppenheimer. Go ahead. 
...................................................................................................................................................................................................................................................... Analyst, Oppenheimer & Co., Inc. Q 
Francois Brisebois 
Thank you for taking the question. The first one here in terms of the ORCA-3 that's you're expecting to read out  this quarter. I just wondering any thoughts on what you would expect maybe odds ratio wise, is this something  where we should compare it to the data that you had shown in the previous Phase 3 ORCA trial?
6

Achieve Life Sciences, Inc. (ACHV) Q1 2023 Earnings Call 
Corrected Transcript 09-May-2023

Chief Executive Officer & Director, Achieve Life Sciences, Inc. A John A. Bencich 
Yeah. Thanks for the question, Franc. I think in terms of odds ratios, I don't think we have a firm expectation in  terms of what those might look like. I think when we look at the market today and where odds ratios fit for the  existing products that are in the range of 2 to 3, when you go kind of at the low end of NRT to varenicline is at the  higher end. 
So, I think anything in that range or above, we see as being a win. In the ORCA program, so far, at least for  smoking cessation, we've seen odds ratios between 5 and 8. So, we've exceeded kind of those benchmark  requirements. But from the discussions we've had with the key opinion leaders in the space, anything over an  odds ratio of 2 is going to be a meaningful clinical benefit in this setting. 
...................................................................................................................................................................................................................................................... Analyst, Oppenheimer & Co., Inc. Q 
Francois Brisebois 
Okay. That's helpful. And then in terms of manufacturing, as we're getting to that stage here, can you give any  color on what's going on, on the manufacturing side? Any obstacles to overcome or just the process where you  stand right now? Thank you. 
...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
On the CMC side, so we've been working hand in hand with our colleagues over at Sopharma who will be the  manufacturers of record on that front. So, the focus has been, I would say, in two parallel tracks, one is just FDA  inspection readiness. 
So, that's something we'll continue to focus on as we march forward to an NDA filing. And then the other track  would be preparations on supply chain, getting registration batches up and on stability, and then making sure kind  of all the way through the supply chain through final packaging is sorted and those activities are all in process as  well. 
...................................................................................................................................................................................................................................................... Analyst, Oppenheimer & Co., Inc. Q 
Francois Brisebois 
Okay. Great. Then lastly, maybe if I can ask you about vaping, sorry if you mentioned it, but steps going forward,  is this kind of a label expansion? How many trials will we need to potentially get to approval here on the vaping  side? Thank you. 
...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
Yeah, thanks, Franc. On the vaping side, as we indicated a couple of weeks back when we released the ORCA V1 results, our belief currently is that a single-Phase 3 trial is likely what the FDA would expect for approval in this  indication. 
That would be under the guise of already being on the market or having an approval for smoking cessation. So,  we're effectively just expanding the indication and I think by having a statistical significant result from ORCA-V1  that reinforces our belief. 
......................................................................................................................................................................................................................................................7

Achieve Life Sciences, Inc. (ACHV) Q1 2023 Earnings Call 
Corrected Transcript 09-May-2023

Analyst, Oppenheimer & Co., Inc. Q Francois Brisebois 
Thank you. 
...................................................................................................................................................................................................................................................... 
Operator: Our next question comes from Michael Higgins from Ladenburg Thalmann. Go ahead, Michael. 
...................................................................................................................................................................................................................................................... Analyst, Ladenburg Thalmann & Co., Inc. Q 
Michael Higgins 
Thanks, operator. Good evening guys. Congrats on the progress with cytisinicline including ORCA-V1, we're  certainly eager here to see the second Phase 3 ORCA-3 here in Q2. Question on ORCA-3. Can you give us any  sense for the timing here in Q2 as investors start to look out and look at the calendars, when might we see that  data come through? 
...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
The timing for ORCA-3. We've guided to the second quarter and I think the closest we can get to firming that up  would be second half of this quarter. So, any time after kind of the middle of May, that trial result would be in play. 
...................................................................................................................................................................................................................................................... Analyst, Ladenburg Thalmann & Co., Inc. Q 
Michael Higgins 
Okay. That's helpful. Also on the Phase 3, Cindy, a question for you on the 24-week data that was presented  [indiscernible] (00:17:15) you noted, 82% compliance at 24 weeks. Curious how that compares to cytisinicline or  your expectations for cytisinicline in both ORCA pivotal. Thanks. 
...................................................................................................................................................................................................................................................... President, Chief Medical Officer & Director, Achieve Life Sciences, Inc. A 
Cindy A. Jacobs 
Yeah, I think compliance is actually quite good. I think it may be a little higher than what varenicline reported. It  obviously is probably a component of being in a clinical trial as well as you have the behavioral support  component that continues actually throughout the follow-up period. 
...................................................................................................................................................................................................................................................... Analyst, Ladenburg Thalmann & Co., Inc. Q 
Michael Higgins 
That's helpful. And then one on vaping, obviously, this is an area of increased interest across [ph] society  (00:18:02). Curious in your conversations with investors, how they're seeing vaping relative to their interest in  cigarette smoking. 
...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
Yeah. Interesting question, I think. The bread and butter of what we've been doing has been on the smoking  cessation side. And I think people are beginning to appreciate what we just validated here with ORCA-V1 which  has the potential to expand into a segment that currently has no available treatment options and is growing. 
We just saw the latest update of e-cigarette users here in the US increase from about 9 million up to 11 million.  So, this is a growing segment with no available options. And we think this is the right course [indiscernible] 
8

Achieve Life Sciences, Inc. (ACHV) Q1 2023 Earnings Call 
Corrected Transcript 09-May-2023

(00:18:49) as we move ahead. And I think that's resonated quite strongly as we've been able to socialize the  results. 
...................................................................................................................................................................................................................................................... Analyst, Ladenburg Thalmann & Co., Inc. Q 
Michael Higgins 
Look forward to seeing ORCA-3. Appreciate the questions. Thanks guys. 
...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
Thanks, Michael. 
...................................................................................................................................................................................................................................................... 
Operator: [Operator Instructions] And our next question comes from John Vandermosten from Zacks. Go ahead. 
...................................................................................................................................................................................................................................................... Analyst, Zacks Investment Research, Inc. (Small Cap Research) Q 
John D. Vandermosten 
Thank you and good afternoon, John, Cindy and Jerry. As you guys are going into the final stages, are there any  preparations that you're making for commercialization? Our belief is that you're going to work with a partner to do  that. 
But I know sometimes that it makes sense to reach out and work on some – perhaps labeling, packaging, pricing  or outreach to key stakeholders in order to kind of prep to work with the partner, also help your negotiating  position. Is that something that you're planning to do or makes sense to do? 
...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
Yeah. Thanks for the question, John. On the commercialization prep, one of the key areas is supply chain,  making sure that we've got all the blocking and tackling together all the way through final packaging and into  potential distribution. 
So again, we're in the early phases of a lot of that planning to make sure that's on track. I would say, the other  piece that we're looking at to make sure is moving ahead beyond the market access side. 
Now we know that this is a very favorable category given the Affordable Care Act mandates that all FDA  approved smoking cessation products be covered. But there's still a fair amount of work that's required to make  sure that we can get all the pieces in place. So we're ready to move ahead with those contracting discussions. So,  I'd say those are the two primary areas of focus. 
...................................................................................................................................................................................................................................................... Analyst, Zacks Investment Research, Inc. (Small Cap Research) Q 
John D. Vandermosten 
Okay. And regarding labeling. What's the timeline left for that, discussions with the FDA and preparation there? 
...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
On the labeling front. So, we've already began working with some outside advisors on what the label would look  like. So, that's early days ORCA-3, we'll feed into that. So, we'll need that in hand. But that's an important piece  that we will submit with the NDA. So, the bulk of that work will be done over the course of 2023.
9

Achieve Life Sciences, Inc. (ACHV) Q1 2023 Earnings Call 
Corrected Transcript 09-May-2023

Analyst, Zacks Investment Research, Inc. (Small Cap Research) Q John D. Vandermosten 
Got it. And final one for me, any work done on a brand name yet or directions in terms of how are you going to  eventually market that? 
...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
Sorry, was the question around a brand name? 
...................................................................................................................................................................................................................................................... Analyst, Zacks Investment Research, Inc. (Small Cap Research) Q 
John D. Vandermosten 
Yeah, exactly. Is that anything you've worked on yet? I mean, I know it's probably a challenging thing to do with all  the other names out there, but any work down there yet, any indications of where that might go? ...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
Yes, we have been through an exercise to hone in on a brand name and we did get preliminary clearance from  FDA on that. We wouldn't get final approval until it's submitted with NDA. But we have gone through that process,  so that is another piece, at least on the commercialization front that we're ready for. 
...................................................................................................................................................................................................................................................... Analyst, Zacks Investment Research, Inc. (Small Cap Research) Q 
John D. Vandermosten 
Great. Thank you, gentlemen. 
...................................................................................................................................................................................................................................................... Chief Executive Officer & Director, Achieve Life Sciences, Inc. A 
John A. Bencich 
Thanks, John. 
...................................................................................................................................................................................................................................................... 
Operator: And that appears to be the last question at this time. I would now like to turn it back to management  for any closing remarks. 
...................................................................................................................................................................................................................................................... John A. Bencich 
Chief Executive Officer & Director, Achieve Life Sciences, Inc. 
Thanks, operator, and thanks, everyone, for joining us today. It's been an exciting first portion of 2023, and we  look forward to rejoining you soon with results from the ORCA-3 trial later this quarter. So, appreciate the  continued support and we'll talk to you soon. Thanks. 
...................................................................................................................................................................................................................................................... 
Operator: Thank you. This does conclude today's conference. We thank you for your participation. You may  disconnect your lines at this time and have a wonderful day.
10

examplereport

UpHealth, Inc. Hold
(UPH – $0.81 – intraday) Price Target: $1
Righting The Ship, Not Out Of The Storm Yet But We Like
The Progress; Maintain Hold Rating
Quarter and Outlook – Q1 revenue of $36M was ahead of consensus at $35M, and
AEBITDA of ($1.3M) was ahead of the street at ($3.2M). Revenue guidance of
$205M-$233M and AEBITDA guidance $14M-$19M were reiterated. UpHealth
expects to be CF+ in Q3’22. Total cash at Q1 end was $71M. Subsequent Q1 end,
UpHealth repaid its forward share purchase agreement in full (~$19M). We
estimate PF cash to $52M. PF total debt of $124M includes $22M short-term debt
and ~$102M in LT debt. In a separate 8-K, UpHealth announced the appointment
of Sam Meckey to CEO effective July 2022. Current CEO, Ramesh Balakrishnan will
move to Chief Strategy Officer.
Our Take – UpHealth made solid progress in Q1 turning the ship. While we expect
this to be a multi-quarter process, we think initial changes made are positive and
should build a better foundation for predictable revenue growth and profitability.
While we are waiting for the final 10-Q filing (expected Monday, May 16th), results
were ahead of expectations on the top and bottom-line. UpHealth also cleaned up
the balance sheet some when settling the ~$19M forward share purchase
agreement. PF cash and debt stand at $52M and $124M, respectively, which
sufficiently bridges UpHealth to CF+ operations expected Q3’22. Company-wide
operational changes have been implemented including consolidated support
functions, internal controls, and management changes with the appointment of
new CEO Meckey expected in July. Previous collection challenges in the Integrated
Care Management business in Q4 are being addressed, and we expect to see some
collections in mid-2022 positively impacting the financials. While shares are cheap,
we remain at a Hold rating while we track execution. We are optimistic UpHealth
made the right changes and will emerge a stronger organization.
HIGHLIGHTS
• Q1’22 Results – Q1 revenue of $36M was ahead of us and the street at $35M.
AEBITDA is expected to be ($1.3M) vs. consensus at ($3.2M). Integrated Care
Management generated $2.6M in revenue vs. $6.3M in Q1’21 and had a 63%
GM. Virtual Care Infrastructure generated $15.6M in revenue vs. $10.8M in
Q1’21 (pro forma basis) and had a GM of 47%. Services, a combination of Digital
Pharmacy and Behavioral Health, generated revenue of $17.7M vs. $13.5M in
Q1’21 and had a GM of 35%. Aggregate gross margin was 43% vs. 54% in Q1’21.
Q1 AEBITDA loss is expected at ($1.3M) vs. our ($4.8M) and the street at
($3.2M).

• Guidance, Model Adjustments – UpHealth reiterated its 2022 revenue guidance
of $205M-$233M. Management also reiterated its AEBITDA guidance of $14M
to $19M. Management expects 2022 gross margin between 42% and 43%. Our
$205M revenue estimate and $14.6M AEBITDA estimate for 2022 remain

unchanged. We also left our 2023 revenue estimate of $245M (+20% Y/Y) and
AEBITDA of $25.8M (11% margin) unchanged.
• Balance Sheet – Cash at Q1 end is expected at $70.7M. April 9, 2022, UpHealth
repaid its forward share purchase agreement. PF cash stands at $52M. We

estimate debt of $124M which is comprised of $22M short-term and $102M long-
term (convertible note). UpHealth expects to be CF+ by Q3’22 and cash on the

balance sheet sufficiently bridges the Company to this point.
• Longer Term Expectations – UpHealth outlined its expectations of continued
growth over the next five years over 35% Y/Y with 45%-50% gross margins and
15%-20% AEBITDA margins. We think the products and markets merit this growth;
however, we are remaining cautious while the ship is turned and new management
arrives in July. Our 2023 estimates call for 20% growth, 44% GMs, and 11%
AEBITDA margins.
• Potential Collections – Similar to last quarter, in the Integrated Care Management
business, UpHealth provided services to a West Central African customer but did
not recognize revenue due to uncertain creditworthiness. UpHealth is awaiting this
customer to have better clarity into its government funding before recognizing
revenue as funds flow from the government to this customer and then to
UpHealth. The value of this customer is $8.3M/year. In addition, UpHealth is
making significant strides toward collections of accounts receivables from a
European customer and remains optimistic. Collection would be a net positive to
net income and cash but not revenue. The total amount here is ~$15.8M but
UpHealth does not expect to collect this in its entirety.
• Fitting The Pieces Together – There are three primary pieces to UpHealth’s
business: 1) a platform to integrate health care known as Integrated Care
Management (ICM), 2) technological infrastructure to enable care known as Virtual
Care Infrastructure (VCI), and 3) in-house services like behavioral health
management and pharmacy. The ICM platform coordinates local and virtual care
teams to formulate a patient’s (or a population of patients) care regimen
(aggregate, risk stratify, treat, review). VCI enables care to be delivered in an
efficient matter when compared to traditional means as it allows coordination
between virtual and physical care teams. The last piece of UpHealth’s business is
Services, which consists of the digital pharmacy and behavioral health services.

INVESTMENT THESIS AND VALUATION

UpHealth is a healthcare technology company focused on integrating and enabling
efficient patient care with complementary provider services. We think UpHealth is
positioned to drive significant growth through the addition of new customers,
expansion at existing customers and partners, and cross-selling opportunities as it
leverages its six acquisitions with an aggregate market opportunity over $500B. The
three primary pieces to the offering make UpHealth a one-stop-shop for 1) Integrated
Care Management (ICM), 2) Virtual Care Infrastructure (VCI), and 3) Services
(behavioral management, pharmacy). While we think UpHealth has unique offerings

satisfying unmet needs, we think shares will be range-bound in the near-to-
intermediate term. We think execution and balance sheet relief are most important to rating evaluation going forward.
Valuation – Our PT uses a 1.2x revenue multiply applied to our 2022 revenue
estimate of $205M. We subtract net debt of $72M and divide by 180M shares
outstanding (common + RSUs + Warrants + 2021 EIP). We believe a 1.2x revenue
multiple is a trough multiple and see execution and balance sheet relief making the
case for multiple expansion.

financereport

Achieve Life Sciences Reports Financial Results for First Quarter 2023 and Provides Corporate Update Tuesday, May 09, 2023 08:05:00 PM (GMT) 
Company to host conference call at 4:30 PM EDT today, May 9, 2023 
SEATTLE and VANCOUVER, British Columbia, May 09, 2023 (GLOBE NEWSWIRE) -- Achieve Life Sciences, Inc. (Nasdaq: ACHV), a late-stage pharmaceutical company committed to the global development and commercialization of cytisinicline for smoking cessation and nicotine dependence, today announced first quarter 2023 financial results and provided an update on the cytisinicline development program. 
Recent Business Highlights 
Released positive Phase 2 ORCA-V1 clinical trial results showing statistically significant vaping cessation benefit for cytisinicline 
Announced accomplishment of key milestones, including last subject dosing and last subject visit, in the Phase 3 ORCA-3 trial evaluating cytisinicline for smoking cessation 
Presented additional analyses from the Phase 3 ORCA-2 trial at the Society for Research on Nicotine and Tobacco (SRNT) Annual Meeting 
Appointed three new members to Achieve’s Board of Directors 
“We are excited about our start to 2023, announcing statistically significant trial results from ORCA-V1 in April, and on-track to report topline results from the Phase 3 ORCA-3 trial in the second quarter,” stated John Bencich, Chief Executive Officer of Achieve. “We continue to believe in the tremendous potential of cytisinicline to become the first new FDA-approved treatment for smoking cessation in nearly twenty years, and now with the results of ORCA-V1, the possibility of becoming the first treatment specifically indicated for e-cigarette cessation.” 
ORCA-V1 E-Cigarette Cessation Benefit for Cytisinicline 
Achieve announced successful results from the Phase 2 ORCA-V1 trial in April 2023. Trial participants who received 12 weeks of cytisinicline treatment had 2.6 times higher odds, or likelihood, to have quit vaping during the last 4 weeks of treatment compared to subjects who received placebo (p=0.035). The vaping cessation rate during weeks 9 through 12 was 31.8% for those who received cytisinicline treatment compared to 15.1% for those who received placebo. A benefit in favor of cytisinicline was consistently observed across the secondary endpoints and was observed across clinical trial sites and demographics such as age, gender, race, or whether they had smoked cigarettes in the past. Cytisinicline was well tolerated and no serious adverse events were reported. 
Phase 3 ORCA-3 Last Subject Dosed/Last Subject Visit Completed 
In January 2023 and March 2023, the final subject was dosed, and the last subject last visit was completed, respectively, in the ongoing Phase 3 ORCA-3 trial. ORCA-3 enrolled 792 adults who smoke cigarettes across 20 clinical trial locations in the United States. Study participants were randomized to receive either 6 or 12 weeks of cytisinicline treatment or placebo, and all participants received standard behavioral support for the duration of the study. The primary endpoint is biochemically verified continuous abstinence during the last four weeks of treatment and the trial will be determined successful if either cytisinicline treatment arm shows a statistical benefit compared to placebo. Topline results are on track to be reported in the second quarter of 2023. 
Cytisinicline Data Presentation at SRNT Annual Meeting 
In April 2023, additional analyses from the Phase-3 ORCA-2 trial were reported at the SRNT Annual Meeting confirming that successful smoking cessation was observed in subgroups of people who smoke that received cytisinicline, regardless of age, gender, smoking history, or previous quit attempts. Subjects who received either 6 or 12 weeks of cytisinicline treatment experienced consistently higher rates of smoking cessation. The improvement was observed by the second week of treatment and maintained weekly throughout study treatment and during the 24-week follow-up period; such improvement was not observed in those who received placebo. Study compliance was high with 82% of subjects completing the 12 weeks of treatment. No treatment-related serious adverse events were reported and the majority of adverse events were mild in all subjects. 
Three New Members Appointed to Board of Directors 
In March 2023, the Company announced a refresh to the Board of Directors with the appointment of three new directors, Mr. Stuart Duty, Mr. Thomas King, and Mr. Tom Sellig. The new directors bring extensive capital markets, strategic transaction, sales, marketing, and manufacturing expertise in the pharmaceutical and life sciences industries. 
Financial Results 
As of March 31, 2023, the Company’s cash, cash equivalents, and restricted cash was $16.6 million. Total operating
expenses for the first quarter ended March 31, 2023 were $8.6 million. Total net loss for the first quarter ended March 31, 2023 was $9.0 million. As of May 9, 2023, Achieve had 18,040,760 shares outstanding. 
Conference Call Details 
Achieve will host a conference call at 4:30 PM EDT today, Tuesday, May 9, 2023. To access the webcast, log on to the investor relations page of the Achieve website at http://ir.achievelifesciences.com/events-and-webcasts. Alternatively, access to the live conference call is available by dialing (866) 682-6100 (U.S. & Canada) or (862) 298-0702 (International) and referencing conference ID 13738142. A webcast replay will be available approximately two hours after the call and will be archived on the website for 90 days. 
About Achieve and Cytisinicline 
Achieve’s focus is to address the global smoking health and nicotine addiction epidemic through the development and commercialization of cytisinicline. Tobacco use is currently the leading cause of preventable death that is responsible for more than eight million deaths worldwide and nearly half a million deaths in the United States annually.1,2 More than 87% of lung cancer deaths, 61% of all pulmonary disease deaths, and 32% of all deaths from coronary heart disease are attributable to smoking and exposure to secondhand smoke.2 
In addition, there are over 11 million adults in the United States who use e-cigarettes, also known as vaping.3In 2022, approximately 2.5 million middle and high school students in the United States reported using e-cigarettes.4 Currently, there are no FDA-approved treatments indicated specifically as an aid to nicotine e-cigarette cessation. 
Cytisinicline is a plant-based alkaloid with a high binding affinity to the nicotinic acetylcholine receptor. It is believed to aid in treating nicotine addiction for smoking and e-cigarette cessation by interacting with nicotine receptors in the brain, reducing the severity of withdrawal symptoms, and reducing the reward and satisfaction associated with nicotine products. Cytisinicline is an investigational product candidate being developed for the treatment of nicotine addiction and has not been approved by the Food and Drug Administration for any indication in the United States. 
Forward Looking Statements 
This press release contains forward-looking statements within the meaning of the “safe harbor” provisions of the Private Securities Litigation Reform Act of 1995, including, but not limited to, statements regarding the timing and nature of cytisinicline clinical development, data results and commercialization activities, the potential market size for cytisinicline, the potential benefits, safety and tolerability of cytisinicline, the ability to discover and develop new uses for cytisinicline, including but not limited to as an e-cigarette cessation product, and the development and effectiveness of new treatments. All statements other than statements of historical fact are statements that could be deemed forward-looking statements. Achieve may not actually achieve its plans or product development goals in a timely manner, if at all, or otherwise carry out its intentions or meet its expectations or projections disclosed in these forward-looking statements. These statements are based on management’s current expectations and beliefs and are subject to a number of risks, uncertainties and assumptions that could cause actual results to differ materially from those described in the forward-looking statements, including, among others, the risk that cytisinicline may not demonstrate the hypothesized or expected benefits; the risk that Achieve may not be able to obtain additional financing to fund the development of cytisinicline; the risk that cytisinicline will not receive regulatory approval or be successfully commercialized; the risk that new developments in the smoking cessation landscape require changes in business strategy or clinical development plans; the risk that Achieve’s intellectual property may not be adequately protected; general business and economic conditions; risks related to the impact on our business of macroeconomic conditions, including inflation, rising interest rates, instability in the global banking sector, and public health crises, such as the COVID-19 pandemic and the other factors described in the risk factors set forth in Achieve’s filings with the Securities and Exchange Commission from time to time, including Achieve’s Annual Reports on Form 10-K and Quarterly Reports on Form 10-Q. Achieve undertakes no obligation to update the forward-looking statements contained herein or to reflect events or circumstances occurring after the date hereof, other than as may be required by applicable. 
Investor Relations Contact 
Nicole Jones 
achv@cg.capital 
(404) 736-3838 
Media Contact 
Glenn Silver 
Glenn.Silver@Finnpartners.com 
(646) 871-8485 
References 
1 World Health Organization. WHO Report on the Global Tobacco Epidemic, 2019. Geneva: World Health Organization, 2017. 
2 U.S. Department of Health and Human Services. The Health Consequences of Smoking – 50 Years of Progress. A Report of the Surgeon General, 2014.
3 Cornelius ME, Loretan CG, Jamal A, et al. Tobacco Product Use Among Adults – United States, 2021. MMWR Morb Mortal Wkly Rep 2023;72:475–483. 
4 Park Lee E, Ren C, Cooper M, Cornelius M, Jamal A, Cullen KA. Tobacco Product Use Among Middle and High School Students – United States, 2022. Morbidity and Mortality Weekly Report, 2022; 71:45. 
Consolidated Statements of Loss 
(In thousands, except per share and share data) 
Three months ended March 31, 
2023 2022 
Operating expenses: 
Research and development 5,534 4,388 General and administrative 3,044 2,838 Total operating expenses 8,578 7,226 
Loss from operations (8,578) (7,226) Other income (expense) (414) (347) Net loss $ (8,992) $ (7,573) 
Basic and diluted net loss per share $ (0.50) $ (0.80) Weighted average number of basic and diluted common shares 17,917,769 9,458,745 
Consolidated Balance Sheets 
(In thousands) 
March 31, December 31, 
2023 2022 
Assets: 
Cash and cash equivalents $ 16,514 $ 24,771 Prepaid expenses and other current assets 1,710 2,559 Other assets and restricted cash 68 123 Right-of-use assets 109 66 License agreement 1,363 1,418 Goodwill 1,034 1,034 Total assets $ 20,798 $ 29,971 
Liabilities and stockholders' equity: 
Accounts payable and accrued liabilities $ 3,872 $ 5,470 Current portion of long-term obligations 58 58 Convertible debt 16,371 16,071 Long-term obligations 54 69 Stockholders' equity 443 8,303 Total liabilities and stockholders' equity $ 20,798 $ 29,971 
Primary Identifiers: ACHV-US 
Related Identifiers: ACHV-US 
Subjects: Earnings Releases and Operating Results

GPT-4 Turbo (openai)

```
Achieve Life Sciences, Inc. Buy
(ACHV – $X.XX – intraday) Price Target: $Y
Cytisinicline's Potential in Smoking and Vaping Cessation; Initiating with Buy Rating

Quarter and Outlook – Achieve Life Sciences reported a net loss of $9.0 million for Q1 2023, compared to a net loss of $7.6 million for the same period in 2022. The increase in net loss was primarily due to higher operating expenses related to the fully enrolled ORCA-3 Phase 3 trial and the ORCA-V1 Phase 2 trial. As of March 31, 2023, the company had cash, cash equivalents, and restricted cash of $16.6 million, which is expected to provide a runway into late-2023. The company is on track to report topline results from the Phase 3 ORCA-3 trial in Q2 2023.

Our Take – Achieve Life Sciences has shown promising developments with its lead candidate, cytisinicline, for smoking cessation and nicotine dependence. The positive Phase 2 ORCA-V1 clinical trial results demonstrating statistically significant vaping cessation benefits and the completion of the last subject visit in the Phase 3 ORCA-3 trial are key milestones that reinforce our confidence in the drug's potential. With the upcoming ORCA-3 results and preparations for a New Drug Application (NDA), we see a clear path forward for cytisinicline. Additionally, the appointment of three new board members with extensive industry expertise bodes well for strategic direction.

HIGHLIGHTS
• Q1’23 Results – The company reported a net loss of $9.0 million for Q1 2023 due to increased operating expenses associated with ongoing clinical trials. Cash reserves are sufficient to fund operations into late-2023.
• Clinical Progress – Positive results from the ORCA-V1 trial for vaping cessation and completion of the last subject visit in the ORCA-3 trial position cytisinicline favorably for upcoming regulatory milestones.
• Board Refresh – The addition of three new board members with significant pharmaceutical and life sciences experience is expected to provide valuable insights as Achieve Life Sciences advances towards commercialization.

• Guidance, Model Adjustments – We anticipate a decrease in operating expenses in Q2 following the completion of clinical studies. Topline results from the ORCA-3 trial are expected in Q2 2023, which will be a critical catalyst for the stock.

INVESTMENT THESIS AND VALUATION

Achieve Life Sciences is at a pivotal juncture with its lead candidate cytisinicline showing significant promise in both smoking and vaping cessation. The company's focus on addressing the global smoking health and nicotine addiction epidemic is timely given the lack of FDA-approved treatments for e-cigarette cessation and the growing number of e-cigarette users. The recent clinical trial successes bolster our belief in cytisinicline's potential to become a key player in this space.

Valuation – Our PT will be determined post-analysis of the upcoming ORCA-3 trial results. We expect these results to be a major inflection point for the company and will provide further clarity on cytisinicline's market potential.

team must fill this information
```

Gooey.AI

Ulangizi AI Analysis Script

6.5K 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:

We should update the user's profile object (because they mentioned their location, crop or gender)
The user's question was answered
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&#x27;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: &quot;&quot;&quot;
   user: Hi
   assistant: Hello! How can I assist you with farming today?
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: null, &quot;subject&quot;: ”Salutation”, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Found&quot;}}
///
Conversation: &quot;&quot;&quot;
   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
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: ”rice”, &quot;subject&quot;: ”Plant Death (Infestation and Infection)”, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Found&quot;}}
///
Conversation: &quot;&quot;&quot;
   user: A drug can be used to increase the height of chillies in the chilli garden
   assistant: I&#x27;m sorry, but I couldn&#x27;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.
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: ”chili”, &quot;subject&quot;: ”Supplements (Fertilizers and Pesticides)”, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Missing&quot;}}
///
Conversation: &quot;&quot;&quot;
   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]
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: null, &quot;subject&quot;: &quot;Farming Practice&quot;, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Found&quot;}}
///
Conversation: &quot;&quot;&quot;
   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. 💦
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: &quot;pepper&quot;, &quot;subject&quot;: &quot;Irrigation&quot;, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Found&quot;}}
///
Conversation: &quot;&quot;&quot;
   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. 🌶️🌱
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: ”chili”, &quot;subject&quot;: ”Plant Death (Infestation and Infection)”, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Found&quot;}}
///
Conversation: &quot;&quot;&quot;
   user: How to prepare dukki for planting chili garden
   assistant: I&#x27;m sorry, I couldn&#x27;t find any relevant information on preparing &quot;dukki&quot; for planting chili garden in the search results. Could you please provide more context or try rephrasing your question?
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: &quot;chili&quot;, &quot;subject&quot;: &quot;Farming Practice&quot;, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Missing&quot;}}
///
Conversation: &quot;&quot;&quot;
   user: Is there a video for this?
   assistant: I&#x27;m sorry, I don&#x27;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.
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: null, &quot;subject&quot;: &quot;Video&quot;, &quot;location&quot;: null, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Missing&quot;}}
///
Conversation: &quot;&quot;&quot;
   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]
&quot;&quot;&quot;
Analysis: {&quot;user&quot;: {&quot;crop&quot;: null, &quot;subject&quot;: &quot;Farming Practice&quot;, &quot;location&quot;: &quot;Anantapur&quot;, &quot;gender&quot;: &quot;unspecified&quot;}, &quot;assistant&quot;: {&quot;answer&quot;: &quot;Found&quot;}}
///
Conversation: &quot;&quot;&quot;
   user: {{ user_msg }}
   assistant:  {{ assistant_msg }}
&quot;&quot;&quot;
Analysis:

user_msg

assistant_msg

ChatGPT (openai)

Gooey.AI

Natural language to Stripe API via an LLM

14 runs

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

Prompt

&quot;&quot;&quot;
Util exposes the following:

util.stripe() -&gt; authenticates &amp; returns the stripe module; usable as stripe.Charge.create etc
&quot;&quot;&quot;
import util
&quot;&quot;&quot;
Create a Stripe token using the users credit card: 5555-4444-3333-2222, expiration date 12 / 28, cvc 521
&quot;&quot;&quot;

PaLM 2 Text (Google)

Llama 2 70B Chat [Deprecated] (Meta AI)

GPT-4 (openai)

Gooey.AI

A simple Quiz about Cassian Andor

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.

ChatGPT (openai)

{
  "title": "The Daring Adventures of Cassian Andor Quiz",
  "questions": [
    {
      "question": "What is Cassian Andor's primary role in the Rebel Alliance?",
      "options": [
        "Pilot",
        "Spy",
        "Medic",
        "Engineer"
      ],
      "answer": "Spy"
    },
    {
      "question": "Which planet is Cassian Andor from?",
      "options": [
        "Tatooine",
        "Alderaan",
        "Yavin 4",
        "Eadu"
      ],
      "answer": "Yavin 4"
    },
    {
      "question": "What type of droid is Cassian Andor's loyal companion, K-2SO?",
      "options": [
        "Protocol droid",
        "Astromech droid",
        "Assassin droid",
        "Security droid"
      ],
      "answer": "Security droid"
    },
    {
      "question": "Who is Cassian Andor's contact within the Rebellion?",
      "options": [
        "Mon Mothma",
        "Saw Gerrera",
        "Bail Organa",
        "Leia Organa"
      ],
      "answer": "Leia Organa"
    },
    {
      "question": "What is the name of the mission in which Cassian Andor and Jyn Erso are involved in Rogue One?",
      "options": [
        "Operation Endor",
        "Operation Scarif",
        "Operation Hoth",
        "Operation Mustafar"
      ],
      "answer": "Operation Scarif"
    },
    {
      "question": "What is the name of the actor who portrays Cassian Andor in the Star Wars films?",
      "options": [
        "Diego Luna",
        "Pedro Pascal",
        "Oscar Isaac",
        "Gael García Bernal"
      ],
      "answer": "Diego Luna"
    }
  ]
}

Gooey.AI

Golden answer comparison algo for ASR

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: {
&quot;rationale&quot;: &quot;The ai_answer is missing key elements such as chili farm and white flies.&quot; ,
&quot;score&quot;: &quot;.2&quot;
}

Golden: {{ golden }}
AI_text: {{ai_answer}}
JSON:

golden

ai_answer

ChatGPT (openai)

Gooey.AI

Create an Icon from a Gooey.AI Workflow Prompt

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&#x27;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 &quot;Hi&quot; or &quot;Hello&quot;, introduce yourself before answering the user&#x27;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

prompt

workflow

GPT-4 Turbo (openai)

Examples: LLM

FUNCTIONS: Make a Haiku with ISS Coordinates

Improve AI Image Prompt

Compare Indic LLMs

Compare AfroLlama vs LLaLM3: Yoruba

Compare LLMs: SEA-LION vs SOTA

Default Copilot Analysis Script

Create a Copilot description + 4 sample Qs

Add Emojis to your GitHub readme

PaLM2 Translations with Custom Glossary

FALana Summary Script

FALANA Chat Analysis Script

Fireside Chat Summary Script

Fireside Chat Analysis Script

Run Mistral... FAST via an API

How Farmer.CHAT turns conversations to structured data

Financial Report Maker

Ulangizi AI Analysis Script

Natural language to Stripe API via an LLM

A simple Quiz about Cassian Andor

Golden answer comparison algo for ASR

Create an Icon from a Gooey.AI Workflow Prompt

GET STARTED

LEARN

DEVELOPERS

SOCIAL

CONNECT

EXTRAS