GeorgePearse

import pandas as pd
from umap import UMAP
from sentence_transformers import SentenceTransformer

# Load the universal sentence encoder
# Stay well clear of the direct Hugging Face API which is grim
sample_size = 30000
model = SentenceTransformer('all-mpnet-base-v2')

embeddings = model.encode(sentences[:sample_size])

GeorgePearse

from datasets import load_dataset
from sentence_transformers import SentenceTransformer
import numpy as np
import pandas as pd

selected_dataset = 'ag_news'
sample_size = 6000
dataset = load_dataset(selected_dataset)
dataset_df = pd.DataFrame(dataset['train'])

GeorgePearse

from fastapi import FastAPI, Path
from utils import create_connection, sql_to_df
import pandas as pd

app = FastAPI()

@app.get("/query/{query_name}")
async def root(
    query_name: str = Path(
        title="Query name of the query to run", 

GeorgePearse

import sqlite3
import streamlit as st
import pandas as pd
import os
import plotly.express as px


def create_connection(db_file):
    """ create a database connection to the SQLite database
        specified by the db_file

GeorgePearse

import sqlite3
import streamlit as st
import pandas as pd
import os


def create_connection(db_file):
    """ create a database connection to the SQLite database
        specified by the db_file
    :param db_file: database file

GeorgePearse

import streamlit as st
import os
import requests

vector_db_host = os.environ.get('VECTOR_DB_HOST')

# queries the DB to get the options
collections = [
    record["name"]
    for record in requests.get(f"{vector_db_host}/collections").json()["result"][

GeorgePearse

import streamlit as st
import requests
import os

vector_db_host = os.environ.get('VECTOR_DB_HOST')
request = st.text_input("request")
response = requests.get(f"{vector_db_host}/{request}").json()
st.json(response)

GeorgePearse

import sys
import numpy as np
import torch
import torch.nn as nn


def enable_dropout(model):
    """ Function to enable the dropout layers during test-time 
    From https://stackoverflow.com/questions/63285197/measuring-uncertainty-using-mc-dropout-on-pytorch
    """

GeorgePearse

def return_dropout_model(model, with_dropout=True):

  model = model.to(device)
  if with_dropout:
    print('Dropout still on.')
    feats_list = list(model.features)
    new_feats_list = []
    for feat in feats_list:
        new_feats_list.append(feat)
        # Add a drop out layer after every