ws-bom-robot-app 0.0.79

A FastAPI application serving ws bom/robot/llm platform ai.

🤖 ws-bom-robot-app

A FastAPI application serving ws bom/robot/llm platform ai

🌵 Minimal app structure

app/
|-- .env
|-- main.py

Fill main.py with the following code:

from ws_bom_robot_app import main
app = main.app

FIll .env with the following code:

#robot_env=local/development/production
robot_env=local
robot_user='[user]'
robot_password='[pwd]'
robot_data_folder='./.data'
robot_cms_auth='[auth]'
robot_cms_host='https://[DOMAIN]'
robot_cms_db_folder=llmVectorDb
robot_cms_files_folder=llmKbFile

🚀 Run the app

• development

  fastapi dev --port 6001
  #uvicorn main:app --app-dir ./ws_bom_robot_app --reload --host 0.0.0.0 --port 6001 
  

• production

  uvicorn main:app --host 0.0.0.0 --port 6001  
  

• production with multipler workers

  fastapi run --port 6001 --workers 4
  #uvicorn main:app --host 0.0.0.0 --port 6001 --workers 4
  #gunicorn -w 4 -k uvicorn.workers.UvicornWorker main:app --bind
  

📖 API documentation

• swagger
• redoc

💬 multimodal chat

The multimodal message allows users to interact with the application using both text and media files. robot accept multimodal input in a uniform way, regarding the llm provider used. Can also be used the llm/model specific input format.

• simple message

{
  "role": "user",
  "content": "What is the capital of France?"
}

• multimodal message

{
  "role": "user",
  "content": [
    {"type": "text", "text": "Read carefully all the attachments, analize the content and provide a summary for each one:"},        
    {"type": "image", "url": "https://www.example.com/image/foo.jpg"},        
    {"type": "file", "url": "https://www.example.com/pdf/bar.pdf"},   
    {"type": "file", "url": "data:plain/text;base64,CiAgICAgIF9fX19fCiAgICAgLyAgIC..."}, # base64 encoded file     
    {"type": "media", "mime_type": "plain/text", "data": "CiAgICAgIF9fX19fCiAgICAgLyAgIC..."} # google/gemini specific input format    
  ]          
}

---

🔖 Windows requirements

libmagic (mandatory)

py -m pip install --upgrade python-magic-bin

tesseract-ocr (mandatory)

Install tesseract Last win-64 release

Add tesseract executable (C:\Program Files\Tesseract-OCR) to system PATH

$pathToAdd = "C:\Program Files\Tesseract-OCR"; `
$currentPath = [System.Environment]::GetEnvironmentVariable("Path", [System.EnvironmentVariableTarget]::Machine); `
if ($currentPath -split ';' -notcontains $pathToAdd) { `
  [System.Environment]::SetEnvironmentVariable("Path", "$currentPath;$pathToAdd", [System.EnvironmentVariableTarget]::Machine) `
}

docling

Set the following environment variables

KMP_DUPLICATE_LIB_OK=TRUE

libreoffice (optional: for robot_env set to development/production)

Install libreoffice Last win-64 release

Add libreoffice executable (C:\Program Files\LibreOffice\program) to system PATH

$pathToAdd = "C:\Program Files\LibreOffice\program"; `
$currentPath = [System.Environment]::GetEnvironmentVariable("Path", [System.EnvironmentVariableTarget]::Machine); `
if ($currentPath -split ';' -notcontains $pathToAdd) { `
  [System.Environment]::SetEnvironmentVariable("Path", "$currentPath;$pathToAdd", [System.EnvironmentVariableTarget]::Machine) `
}

poppler (optional: for robot_env set to development/production)

Download win poppler release Extract the zip, copy the nested folder "poppler-x.x.x." to a program folder (e.g. C:\Program Files\poppler-24.08.0) Add poppler executable (C:\Program Files\poppler-24.08.0\Library\bin) to system PATH

$pathToAdd = "C:\Program Files\poppler-24.08.0\Library\bin"; `
$currentPath = [System.Environment]::GetEnvironmentVariable("Path", [System.EnvironmentVariableTarget]::Machine); `
if ($currentPath -split ';' -notcontains $pathToAdd) { `
  [System.Environment]::SetEnvironmentVariable("Path", "$currentPath;$pathToAdd", [System.EnvironmentVariableTarget]::Machine) `
}

---

👷 Contributors

Build/distribute pkg from websolutespa bom [Github]

dir in robot project folder

  cd ./src/robot

🔖 requirements

py -m pip install --upgrade setuptools build twine streamlit 

🪛 build

if (Test-Path ./dist) {rm ./dist -r -force}; `
py -m build && twine check dist/*

📦 test / 🧪 debugger

Install the package in editable project location

py -m pip install -U -e .
py -m pip show ws-bom-robot-app

code quality tools

# .\src\robot
!py -m pip install -U scanreq prospector[with_everything]
## unused requirements
scanreq -r requirements.txt -p ./ws_bom_robot_app
## style/linting
prospector ./ws_bom_robot_app -t pylint -t pydocstyle
## code quality/complexity
prospector ./ws_bom_robot_app -t vulture -t mccabe -t mypy 
## security
prospector ./ws_bom_robot_app -t dodgy -t bandit
## package
prospector ./ws_bom_robot_app -t pyroma

lauch pytest

!py -m pip install -U pytest pytest-asyncio pytest-mock pytest-cov pyclean
# clean cache if needed
# pyclean --verbose .
pytest --cov=ws_bom_robot_app --log-cli-level=info
# directory
# pytest --cov=ws_bom_robot_app --log-cli-level=info ./tests/app/llm/vector_store/db

launch debugger

streamlit run debugger.py --server.port 8051

dockerize base image

<# cpu #>
docker build -f Dockerfile-robot-base-cpu -t ghcr.io/websolutespa/ws-bom-robot-base:cpu .
docker push ghcr.io/websolutespa/ws-bom-robot-base:cpu
<# gpu #>
docker build -f Dockerfile-robot-base-gpu -t ghcr.io/websolutespa/ws-bom-robot-base:gpu .
docker push ghcr.io/websolutespa/ws-bom-robot-base:gpu

dockerize app

docker build -f Dockerfile -t ws-bom-robot-app .
docker run --rm --name ws-bom-robot-app -d -p 6001:6001 ws-bom-robot-app

docker run mounted to src

docker run --rm --name ws-bom-robot-app-src -d -v "$(pwd)/ws_bom_robot_app:/app/ws_bom_robot_app" -v "$(pwd)/.data:/app/.data" -v "$(pwd)/tmp:/tmp"  -p 6001:6001 ws-bom-robot-app

✈️ publish

• testpypi

  twine upload --verbose -r testpypi dist/*
  #pip install -i https://test.pypi.org/simple/ -U ws-bom-robot-app 
  

• pypi

  twine upload --verbose dist/*