brianray

{
    "version": "0.2.0",
    "configurations": [
        {
            "name": "Python: Cloud Function Emulate",
            "type": "python",
            "request": "launch",
            "module": "functions_framework",
            "justMyCode": false, 
            "args": [

brianray

graph LR
  A((Start))--take Survey-->B((Goal Setting))
  B((Goal Setting))--1 on 1 coach-->C((Working On Concentation))
  C((Working On Concentation))--1 on 1 coach weekly-->C((Working On Concentation))

brianray

Scenarios

1. Jailbreaking for Data Leaked from Hacker Actor: the hacker gets data out of the model by pure prompt manipulation,
2. Intrusion from Hacker Actor: The malicious instructions pass through the application and can instruct the extension services to do bad things.
3. Data poisoning for Training data: The source data used to train the LLM has malicious content before it is trained.
4. Prompt Poising: hidden content or injected content unintentional from an innocent bystander.

brianray

[name]		By: [by]
Data Access		...
Runtime and Cost		...
Namespaces		...
Advanced Types		...
Scheduling		...
Streaming		...
Feature Transform		...
Time Sensitivity		...

brianray

Databricks Feature Store		By: Databricks
Data Access		...
Runtime and Cost		...
Namespaces		...
Advanced Types		...
Scheduling		...
Streaming		...
Feature Transform		...
Time Sensitivity		...

brianray

prophet_model = Prophet(
    growth='linear',
    changepoints=None,
    n_changepoints=25,
    changepoint_range=0.8,
    yearly_seasonality=10,  # Fourier
    weekly_seasonality=3,  # Fourier
    daily_seasonality='auto',
    seasonality_mode='additive',
    seasonality_prior_scale=10.0,

brianray

import scipy.signal as sg

def decimate_rolling(df, size=100):
    out = []
    for name in names[:n_samples]:
        inds = np.arange(0, len(df), 8000) ## TODO
        for i, j in zip(inds[:-1], inds[1:]):
            dij = d[i:j]
            dij = sg.decimate(dij, 2, ftype="iir")[::2]
            out.append(dij)

brianray

brianray

function sentiment_analysis(content) {
  var URL = "https://us-central1-mw-automl-first-look.cloudfunctions.net/analyze"   
  var options = {
    'method' : 'post',
    'contentType': 'application/json',
    // Convert the JavaScript object to a JSON string.
    'payload' : JSON.stringify({"content": content})
  };
  return UrlFetchApp.fetch(URL, options).getContentText();
}

brianray

from google.cloud import language
from google.cloud.language import enums
from google.cloud.language import types

def analyze(request):
    request_json = request.get_json()
    client = language.LanguageServiceClient()
    sentance = request_json['content']
    document = types.Document(
        content=sentance,