FEATURES=wiki,search,arxiv,hue,summarize
OPENAI_API_KEY=...
DISCORD_TOKEN=...
GUILD_ID=...
GOOGLE_API_KEY=...
GOOGLE_CSE_ID=...

FEATURES=wiki,search,arxiv,hue,summarize
OPENAI_API_KEY=...
HUE_USERNAME=...
HUE_BRIDGE_IP=...
GOOGLE_API_KEY=...
GOOGLE_CSE_ID=...

❯ ./CLI.sh -t "What are the last 5 papers published on Arxiv in AI about? list with for each title and the url, please. Use feedparser."
... (snip) ...
=============   
The original question was: What are the last 5 papers published on Arxiv in AI about? list with for each title and the url, please. Use feedparser.
And the conclusion is: Here are the latest 5 papers published by Arxiv in AI:
Title: Experts' cognition-driven safe noisy labels learning for precise segmentation of residual tumor in breast cancer. (arXiv:2304.07295v1 [q-bio.QM])
URL: http://arxiv.org/abs/2304.07295
Title: MLOps Spanning Whole Machine Learning Life Cycle: A Survey. (arXiv:2304.07296v1 [cs.LG])
URL: http://arxiv.org/abs/2304.07296
Title: Language Instructed Reinforcement Learning for Human-AI Coordination. (arXiv:2304.07297v1 [cs.AI])
URL: http://arxiv.org/abs/2304.07297
Title: Road Network Representation Learning: A Dual Graph based Approach. (arXiv:2304.07298v1 [cs.LG])
URL: http://arxiv.org/abs/2304.07298
Title: Supervised Machine Learning for Breast Cancer Risk Factors Analysis and Survival Prediction. (arXiv:2304.07299v1 [cs.LG])
URL: http://arxiv.org/abs/2304.07299

❯ ./CLI.sh -t 'Show me an example of how to use Sympy to solve a math problem. '
# Your turn
Original question: Show me an example of how to use Sympy to solve a math problem.
Do you have the answer? Use the Conclude Tool to terminate the task.
Observations, Orientation, Decision, The ONLY Action?
=============
## Observations:
- The user wants an example of how to use Sympy to solve a math problem.
- Sympy is a Python library for symbolic mathematics.
## Orientation:
- I will use the SandboxedPython tool to demonstrate the solution to the problem using the Sympy library.
- I will use the Conclude tool to terminate the task when the solution is presented.
- The solution will be presented in plain text to the Conclude tool.
## Decision:
- I will demonstrate how to solve the equation "x^2 - 5x + 6 = 0" using Sympy and present the solution to the Conclude tool.
## The ONLY Action:
```yaml
tool_name: SandboxedPython
parameters:
  code: |
    from sympy import symbols, solve
    x = symbols('x')
    equation = x**2 - 5*x + 6
    solution = solve(equation)
    print(f"The solution to x^2 - 5x + 6 = 0 is {solution}")
```

=============
# Action SandboxedPython result:
```yaml
stdout: |
  The solution to x^2 - 5x + 6 = 0 is [2, 3]
stderr: ''
```
# Your turn
Original question: Show me an example of how to use Sympy to solve a math problem.
Do you have the answer? Use the Conclude Tool to terminate the task.
Observations, Orientation, Decision, The ONLY Action?
=============
## Observations:
- The user wants an example of how to use Sympy to solve a math problem.
- The previous agent has already demonstrated an example of how to use Sympy to solve a quadratic equation.
- The equation is 'x^2 - 5x + 6 = 0'.
- The solution is the roots of the equation, which are [2, 3].
## Orientation:
- I know the answer to the question.
## Decision:
- Use the Conclude Tool to terminate the task when I have presented the solution in plain text.
## The ONLY Action:
```yaml
tool_name: Conclude
parameters:
  original_question: Show me an example of how to use Sympy to solve a math problem.
  conclusion: |
    An example of how to use Sympy to solve the equation "x^2 - 5x + 6 = 0" is:

    from sympy import symbols, solve
    x = symbols('x')
    equation = x**2 - 5*x + 6
    solution = solve(equation)

    The solution is the roots of the equation: [2, 3].
```

=============
The original question was: Show me an example of how to use Sympy to solve a math problem.
And the conclusion is: An example of how to use Sympy to solve the equation "x^2 - 5x + 6 = 0" is:

from sympy import symbols, solve
x = symbols('x')
equation = x**2 - 5*x + 6
solution = solve(equation)

The solution is the roots of the equation: [2, 3].

❯ ./CLI.sh -t "How is the weather today in San Jose, CA, USA? I have no API KEY but BS4 is available."
## Observations:
- We want to know the weather of San Jose, California, USA.
- We don't have an API KEY to fetch the data.
- BeautifulSoup4 is available as a tool.
## Orientation:
- We will scrape the weather data from a website using BeautifulSoup4.
- We will parse the HTML data to extract the required information.
## Decision:
- We will use the SandboxedPython tool to extract the temperature and other relevant info of San Jose from the HTML data.
## The ONLY Action:
```yaml
tool_name: SandboxedPython
parameters:
  code: |
    import requests
    from bs4 import BeautifulSoup

    url = "https://www.google.com/search?q=weather+san+jose"

    res = requests.get(url)

    # Parsing the HTML output from requests
    html = res.content
    soup = BeautifulSoup(html, 'html.parser')

    # Getting the temperature and other info
    temp = soup.find('div', attrs={'class': 'BNeawe iBp4i AP7Wnd'}).text
    str = soup.find('div', attrs={'class': 'BNeawe s3v9rd AP7Wnd'}).text

    # Converting temperature into Celsius
    tempC = (int(temp.split('°')[0]) - 32) * 5/9

    conclusion = f"The temperature in San Jose, California, USA is {tempC:.2f}°C and {str}"
    print(conclusion)
```

=============   2 messages in the chat history =============
# Action result:
```yaml
stdout: |
  The temperature in San Jose, California, USA is 12.78°C and 10 Day Weather-San Jose, CA ; Mon 17 · 59°. 1%. NW 13 mph. Cloudy. High 59F. Winds NW at 10 to 15 mph. ; Tue 18 · 61°. 7%. NW 14 mph. Partly cloudy. High 61F. Winds ...
stderr: ''
```
# Your turn
Original question: How is the weather today in San Jose, CA, USA? I have no API KEY but BS4 is available.
Do you have the answer? Use the Conclude Tool to terminate the task.
Observations, Orientation, Decision, The ONLY Action?
=============   3 messages in the chat history =============
## Observations:
- The original question is to know the weather in San Jose, California, USA.
- We don't have an API Key but we the BeautifulSoup4 tool is available for web scraping.
- We got the temperature and other relevant info from the web page.
## Orientation:
- We already have the temperature and other relevant information from the webpage.
## Decision:
- We will use the Conclude Tool to terminate the task with the information extracted.
## The ONLY Action:
```yaml
tool_name: Conclude
parameters:
  original_question: "How is the weather today in San Jose, CA, USA? I have no API KEY but BS4 is available."
  conclusion: "The temperature in San Jose, California, USA is 12.78°C and 10 Day Weather-San Jose, CA ; Mon 17 · 59°. 1%. NW 13 mph. Cloudy. High 59F. Winds NW at 10 to 15 mph. ; Tue 18 · 61°. 7%. NW 14 mph. Partly cloudy. High 61F. Winds ..."
```

=============   4 messages in the chat history =============
The original question was: How is the weather today in San Jose, CA, USA? I have no API KEY but BS4 is available.
And the conclusion is: The temperature in San Jose, California, USA is 12.78°C and 10 Day Weather-San Jose, CA ; Mon 17 · 59°. 1%. NW 13 mph. Cloudy. High 59F. Winds NW at 10 to 15 mph. ; Tue 18 · 61°. 7%. NW 14 mph. Partly cloudy. High 61F. Winds ...

$ cargo run

You are an automated agent named Sapiens interacting with the WORLD

; output = <...> ; print(output)`. MANDATORY' - name: LightStatusTool description: A tool to use that the source of truth for the Light statuses. description_context: Use this to fetch the Light statuses input_format: light_filter: 'The list of Lights IDs () to get the status for, e.g. `light_filter: ["1", "2"]`. Use `[]` to get all Lights.' ">

You are Sapiens, large language model assisting the WORLD. Use available tools to answer the question as best as you can.
You will proceed in a OODA loop made of the following steps:
- Observations: What do you know? What is your source? What don't you know? You might want to note down important information for later like relevant past Action results. 
- Orientation: Plan the intermediate objectives along the path to answer the original question. Make a list of current objectives. 
- Decision: Choose what to do first to answer the question. Why? What are the pros and cons of this decision?
- Action: Take a single Action consisting of exactly one tool invocation. The available Tools listed below. Use ConcludeTool when you have the final answer to the original question.

# Notes: 
- Template expansion is not supported in Action. If you need to pass information from on action to another, you have to pass them manually.
- Use ConcludeTool with your conclusion (as text) once you have the final answer to the original question.
- There are no APIs available to you. You have to use the Tools.

# Format of your response

Please use the following format for your response - no need to be verbose:
====================
## Observations:
- ...
## Orientation:
- ...
## Decision:
- ...
## The ONLY Action: 
```yaml
tool_name: 
parameters:
  <... using the `input_format` for the Tool ...>
```
====================

# The following are the ONLY Tools you can use for your Actions:
- name: RoomTool
  description: A tool to use that the source of truth for the Lights of a Room.
  description_context: Use this to fetch the Lights of Rooms.
  input_format:
    room_filter: 'The list of Room names () to get the lights for, e.g. `room_filter: ["Bedroom"]`. If unsure, use `[]` to get all Rooms.'
- name: ConcludeTool
  description: A tool to terminate a task with a conclusion.
  description_context: Use this to terminate a task when it is complete.
  input_format:
    conclusion: The final textual answer for this task. No string interpolation supported, only plain text. MANDATORY.
- name: SandboxedPythonTool
  description: 'A tool that executes sandboxed Python code. Only stdout and stderr are captured and made available. '
  description_context: Use this to transform data. This is not a tool to retrieve information. Except `print()`, no interactions with the world. No input. No `import`. No library. No API access. Just plain Python. import|open|exec|eval|__import__ are forbidden.
  input_format:
    code: 'The Python code to execute. For example: `data = [...]; <...>; output = <...> ; print(output)`. MANDATORY'
- name: LightStatusTool
  description: A tool to use that the source of truth for the Light statuses.
  description_context: Use this to fetch the Light statuses
  input_format:
    light_filter: 'The list of Lights IDs () to get the status for, e.g. `light_filter: ["1", "2"]`. Use `[]` to get all Lights.'

Understood.

## Original question: Sort in ascending order: [2, 3, 1, 4, 5].

## Observations:
- The given list to sort is [2, 3, 1, 4, 5].
- I need to sort this list in ascending order.
## Orientation:
- SandboxedPythonTool can be used to sort the list.
## Decision:
- We can use the sorted() function of Python to sort the list.
## The ONLY Action:
```yaml
tool_name: SandboxedPythonTool
parameters:
  code: |
    lst = [2, 3, 1, 4, 5]
    sorted_list = sorted(lst)
    print(f"The sorted list is {sorted_list}")
```

# Action result:
```yaml
status: 0
stdout: |
  The sorted list is [1, 2, 3, 4, 5]
stderr: ''
```
# Your turn
Original question: Sort [2, 3, 1, 4, 5]
Observations, Orientation, Decision, The ONLY Action?

# Observations:
- We needed to sort the list in ascending order.
- We have the result of the Action.
- We have the sorted list: [1, 2, 3, 4, 5].
# Orientation:
- I know the answer to the original question.
# Decision:
- Use the ConcludeTool to terminate the task with the sorted list.
# The ONLY Action:
```yaml
tool_name: ConcludeTool
parameters:
  conclusion: |
    The ascending sorted list is [1, 2, 3, 4, 5].
```

# Your turn
Original question: What is the status of the lights where I most likely work?
Observations, Orientation, Decision, The ONLY Action?

# Observations:
- We need to find the status of the lights where the user most likely works.
- We need information about the room where the user works to query the LightStatusTool.
# Orientation:
- We can use the RoomTool to find the name of the room where the user works.
- Then use this room name as a filter with the LightStatusTool to get the status of the lights.
# Decision:
- Use the RoomTool to find the name of the room where the user works.
- Use the LightStatusTool to find the status of the lights in the room.
# The ONLY Action:
```yaml
tool_name: RoomTool
parameters:
  room_filter: ["office"]
```

 
# Action result: 
```yaml
rooms: []
```
# Your turn
Original question: What is the status of the lights where I most likely work?
Observations, Orientation, Decision, The ONLY Action?

 
# Observations:
- We need to find the status of the lights where the user most likely works.
- The RoomTool with the room_filter of "office" returned an empty list of rooms.
- We don't know which room we should look at now.
# Orientation:
- We can use the RoomTool to fetch the list of rooms and their details.
- We can then decide which room to consider.
# Decision:
- Use the RoomTool to fetch the list of all rooms and their details.
# The ONLY Action:
```yaml
tool_name: RoomTool
parameters:
  room_filter: []
```

 
# Action result: 
```yaml
rooms:
- name: Living
  lights:
  - '4'
  - '5'
  - '6'
  - '21'
- name: Office
  lights:
  - '13'
  - '27'
  - '2'
  - '16'
  - '26'
  - '25'
  - '24'
  - '15'
  - '17'
  - '18'
  - '20'
- name: Hallway
  lights:
  - '33'
  - '28'
- name: Room
  lights:
  - '32'
  - '3'
  - '1'
  - '9'
  - '10'
  - '11'
  - '19'
- name: Kitchen
  lights:
  - '31'
  - '30'
  - '22'
  - '23'
```
# Your turn
Original question: What is the status of the lights where I most likely work?
Observations, Orientation, Decision, The ONLY Action?

 
# Observations:
- We need to find the status of the lights where the user most likely works.
- We got a list of rooms and their light IDs from the RoomTool.
- We need to identify which room the user most likely works in before we can look up the status of the lights.
# Orientation:
- To identify the room where the user works, we need more information about the user.
- If room name is not available, we can use the LightStatusTool to query for the status of lights in all rooms.
# Decision:
- Use the LightStatusTool to get the status of lights in all rooms.
# The ONLY Action:
```yaml
tool_name: LightStatusTool
parameters:
  light_filter: []
```

 
# Action result: 
```yaml
lights:
- id: '23'
  name: Bloom L
  state:
    on: false
    brightness: 254
    hue: 0
    saturation: 143
- id: '27'
  name: Desk lamp
  state:
    on: false
    brightness: 254
    hue: 43690
    saturation: 200
    color_temperature: 500
- id: '28'
  name: Couloir south
  state:
    on: false
    brightness: 56
    hue: 21845
    saturation: 199
    color_temperature: 153
- id: '31'
  name: Kitchen
  state:
    on: false
    brightness: 254
    hue: 21845
    saturation: 199
    color_temperature: 153
- id: '19'
  name: Sapin 4
  state:
    on: false
    brightness: 254
    hue: 0
    saturation: 199
    color_temperature: 500
- id: '22'
  name: Bloom R
  state:
    on: false
    brightness: 254
    hue: 65535
    saturation: 143
- id: '26'
  name: Work R
  state:
    on: false
    brightness: 254
    hue: 21845
    saturation: 199
    color_temperature: 153
- id: '16'
  name: Under desk lightstrip
  state:
    on: false
    brightness: 254
    hue: 0
    saturation: 199
    color_temperature: 500
- id: '1'
  name: Iris
  state:
    on: false
    brightness: 254
    hue: 0
    saturation: 143
- id: '10'
  name: Sapin 3
  state:
    on: false
    brightness: 254
    hue: 43690
    saturation: 200
    color_temperature: 500
- id: '13'
  name: Walk-in closet
  state:
    on: false
    brightness: 254
    hue: 21845
    saturation: 200
    color_temperature: 328
- id: '18'
  name: Bureau C
  state:
    on: false
    brightness: 254
    hue: 43690
    saturation: 199
    color_temperature: 500
- id: '2'
  name: Spot bureau
  state:
    on: false
    brightness: 254
    hue: 65535
    saturation: 200
    color_temperature: 500
- id: '25'
  name: Work L
  state:
    on: false
    brightness: 254
    hue: 43690
    saturation: 199
    color_temperature: 500
- id: '5'
  name: Salon 3
  state:
    on: false
    brightness: 254
    hue: 21845
    saturation: 200
    color_temperature: 328
- id: '24'
  name: Bureau D
  state:
    on: false
    brightness: 254
    hue: 65535
    saturation: 199
    color_temperature: 500
- id: '15'
  name: Desk bloom
  state:
    on: false
    brightness: 254
    hue: 0
    saturation: 143
- id: '6'
  name: Salon 2
  state:
    on: false
    brightness: 254
    hue: 43690
    saturation: 200
    color_temperature: 500
- id: '21'
  name: Counter
  state:
    on: false
    brightness: 254
    hue: 65535
    saturation: 199
    color_temperature: 500
- id: '17'
  name: Bureau A
  state:
    on: false
    brightness: 254
    hue: 21845
    saturation: 199
    color_temperature: 153
- id: '30'
  name: Sink
  state:
    on: false
    brightness: 254
    hue: 43690
    saturation: 199
    color_temperature: 500
- id: '9'
  name: Sapin 2
  state:
    on: false
    brightness: 254
    hue: 21845
    saturation: 200
    color_temperature: 328
- id: '20'
  name: Bureau B
  state:
    on: false
    brightness: 254
    hue: 65535
    saturation: 199
    color_temperature: 500
- id: '3'
  name: Bed lightstrip
  state:
    on: false
    brightness: 254
    hue: 21845
    saturation: 143
- id: '11'
  name: Table
  state:
    on: false
    brightness: 254
    hue: 65535
    saturation: 200
    color_temperature: 500
- id: '32'
  name: Sapin 1
  state:
    on: false
    brightness: 254
    hue: 43690
    saturation: 254
    color_temperature: 447
- id: '33'
  name: Couloir Nord
  state:
    on: false
    brightness: 56
    hue: 0
    saturation: 199
    color_temperature: 500
- id: '4'
  name: Salon 1
  state:
    on: false
    brightness: 254
    hue: 0
    saturation: 200
    color_temperature: 500
```
# Your turn
Original question: What is the status of the lights where I most likely work?
Observations, Orientation, Decision, The ONLY Action?

 
# Observations:
- We need to find the status of the lights where the user most likely works.
- We got the status of all lights from LightStatusTool.
- We need to identify which room the user most likely works in before we can look up the status of the lights.
# Orientation:
- We can use the RoomTool to fetch the list of all rooms and check which room has a light that the user uses most often.
- We can then use the LightStatusTool to query the status of lights in that room.
# Decision:
- Use the RoomTool to fetch the list of all rooms.
- Check which room has a light that the user uses most often.
- Use the LightStatusTool to query the status of lights in that room.
# The ONLY Action:
```yaml
tool_name: RoomTool
parameters:
  room_filter: []
```

 
# Action result: 
```yaml
rooms:
- name: Kitchen
  lights:
  - '31'
  - '30'
  - '22'
  - '23'
- name: Office
  lights:
  - '13'
  - '27'
  - '2'
  - '16'
  - '26'
  - '25'
  - '24'
  - '15'
  - '17'
  - '18'
  - '20'
- name: Room
  lights:
  - '32'
  - '3'
  - '1'
  - '9'
  - '10'
  - '11'
  - '19'
- name: Living
  lights:
  - '4'
  - '5'
  - '6'
  - '21'
- name: Hallway
  lights:
  - '33'
  - '28'
```
# Your turn
Original question: What is the status of the lights where I most likely work?
Observations, Orientation, Decision, The ONLY Action?

 
# Observations:
- We need to find the status of the lights where the user most likely works.
- We got the list of rooms where the user most likely works from the RoomTool.
# Orientation:
- We can see that the Office room in the fetched list contains lights, so we can use the LightStatusTool to look for the status of the lights in the Office room.
# Decision:
- Use the LightStatusTool to find the status of the lights in the Office room.
# The ONLY Action:
```yaml
tool_name: LightStatusTool
input:
  light_filter: ["13", "27", "2", "16", "26", "25", "24", "15", "17", "18", "20"]
```

 
# Action result: 
```yaml
lights:
- id: '26'
  name: Work R
  state:
    on: false
    brightness: 254
    hue: 21845
    saturation: 199
    color_temperature: 153
- id: '16'
  name: Under desk lightstrip
  state:
    on: false
    brightness: 254
    hue: 0
    saturation: 199
    color_temperature: 500
- id: '25'
  name: Work L
  state:
    on: false
    brightness: 254
    hue: 43690
    saturation: 199
    color_temperature: 500
- id: '27'
  name: Desk lamp
  state:
    on: false
    brightness: 254
    hue: 43690
    saturation: 200
    color_temperature: 500
- id: '2'
  name: Spot bureau
  state:
    on: false
    brightness: 254
    hue: 65535
    saturation: 200
    color_temperature: 500
- id: '24'
  name: Bureau D
  state:
    on: false
    brightness: 254
    hue: 65535
    saturation: 199
    color_temperature: 500
- id: '15'
  name: Desk bloom
  state:
    on: false
    brightness: 254
    hue: 0
    saturation: 143
- id: '20'
  name: Bureau B
  state:
    on: false
    brightness: 254
    hue: 65535
    saturation: 199
    color_temperature: 500
- id: '17'
  name: Bureau A
  state:
    on: false
    brightness: 254
    hue: 21845
    saturation: 199
    color_temperature: 153
- id: '18'
  name: Bureau C
  state:
    on: false
    brightness: 254
    hue: 43690
    saturation: 199
    color_temperature: 500
- id: '13'
  name: Walk-in closet
  state:
    on: false
    brightness: 254
    hue: 21845
    saturation: 200
    color_temperature: 328
```
# Your turn
Original question: What is the status of the lights where I most likely work?
Observations, Orientation, Decision, The ONLY Action?

 
# Observations:
- We used the LightStatusTool to fetch the status of lights in the Office room.
# Orientation:
- We can see from the retrieved data that all lights in the Office room are off, so we can inform the user that no lights are on in the Office room.
# Decision:
- Inform the user.
# The ONLY Action:
```yaml
tool_name: ConcludeTool
input:
  conclusion: |
    All the lights in the user's most likely work place are currently off.
```

 
And the conclusion is: All the lights in the user's most likely work place are currently off.