mneedham

import streamlit as st
import json
from sseclient import SSEClient

print("Listening for updates...")
if "messages" in st.session_state:
    print("Closing old connection")
    st.session_state["messages"].resp.close()

url = "http://127.0.0.1:8000/livetext"

mneedham

import { ClickHouseStore } from "@langchain/community/vectorstores/clickhouse";
import { createRetrievalChain } from "langchain/chains/retrieval";
import { OpenAI, OpenAIEmbeddings } from "@langchain/openai";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { createStuffDocumentsChain } from "langchain/chains/combine_documents";
import { RecursiveCharacterTextSplitter } from "langchain/text_splitter";

import { Document } from '@langchain/core/documents'

const openAIApiKey = "sk-xxx"

mneedham

{"url": "https://www.bbc.com/news/uk-politics-67296825", "title": "AI summit: Education will blunt AI risk to jobs, says Rishi Sunak - BBC News", "body": ["People should not be worried about the impact of AI on jobs because education reforms will boost skills, Rishi Sunak has said.", "Speaking after the UK's first AI safety summit, the prime minister said the technology would improve the economy in the long term.", "He added that new tools should be seen as a \"co-pilot\" to help people at work, rather than replacing them.", "The government's job should be to improve training, he told reporters.", "Mr Sunak said he recognised there was \"anxiety\" about the impact new AI tools could have on the workplace, but said it would enhance productivity over time. ", "\"We should look at AI much more as a co-pilot than something which is necessary going to replace someone's job. AI is a tool that can help almost anybody do their jobs better, faster, quicker.", "\"My job, the government's job, is to make sure we have a 

mneedham

git clone git@github.com:huggingface/text-embeddings-inference.git
cd text-embeddings-inference

cargo install --path router -F candle -F accelerate

model=BAAI/bge-large-en-v1.5
revision=refs/pr/5
text-embeddings-router --model-id $model --revision $revision --port 8080

mneedham

import quixstreams as qx
from quixstreams import StreamConsumer, EventData, CancellationTokenSource, CommitMode
import time
import json
import sys
import threading
import click

def on_event_data_received_handler(stream: StreamConsumer, data: EventData):
    global events_consumed

mneedham

pip install confluent-kafka avro urllib3 requests fastavro

mneedham

# Dataset: https://www.kaggle.com/datasets/wilmerarltstrmberg/recipe-dataset-over-2m

import duckdb

db1 = duckdb.connect('db1.duck.db')
db2 = duckdb.connect('db2.duck.db')

db1.sql("""
CREATE OR REPLACE TABLE recipes AS 
FROM read_csv_auto('recipes_data.csv', header=True)

mneedham

Intro to Window Functions

Queries based on the Citi bikes dataset using DuckDB.

Associated YouTube video: https://youtu.be/u9AtW5P0m5c

Import data

CREATE OR REPLACE TABLE bikeStations AS
FROM read_csv_auto('data/*.csv', types={"station_id": "VARCHAR"}) 

mneedham

SQL Aggregate vs Aggregate Window Functions

Queries based on the Citi bikes dataset using DuckDB.

Associated YouTube video: https://www.youtube.com/watch?v=KTIBhsIoCvk

Load the data

CREATE OR REPLACE TABLE bikeStations AS

mneedham

import streamlit as st
import duckdb
from streamlit_searchbox import st_searchbox

atp_duck = duckdb.connect('atp.duck.db', read_only=True)

def search_players(search_term):
    query = '''
    SELECT DISTINCT winner_name AS player
    FROM matches