mneedham

docker run --rm clickhouse/clickhouse-server:24.3 clickhouse-local --query "SELECT * FROM system.contributors ORDER BY name" > contributors_24.3.txt

docker run --rm clickhouse/clickhouse-server:24.4 clickhouse-local --query "SELECT * FROM system.contributors ORDER BY name" > contributors_24.4.txt

./clickhouse --query "

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

from flask import Flask
from flask import render_template
import csv
import json

app = Flask(__name__)

@app.route('/')
def my_runs():
    runs = []

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

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

-- Fails because of weird date
CREATE TABLE players AS 
select *
from 'atp_players.csv';

-- all varchar
CREATE TABLE players1 AS 
select *
from read_csv_auto('atp_players.csv', ALL_VARCHAR=TRUE);

mneedham

SELECT count(*)
FROM 'data/*.parquet';

SELECT * 
FROM 'data/*.parquet' 
LIMIT 10;

DESCRIBE
SELECT * 
FROM 'data/yellow_tripdata_2011-07.parquet';

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

# The NYC Taxis Dataset - https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page

pip install parquet-cli

parq data/yellow_tripdata_2022-01.parquet

parq data/yellow_tripdata_2022-01.parquet --schema

parq data/yellow_tripdata_2022-01.parquet --head 10