Skip to content

Instantly share code, notes, and snippets.

from datasets import load_dataset, concatenate_datasets
import json
# Load the XSum dataset
raw_datasets = load_dataset("EdinburghNLP/xsum")
# Rename and remove columns as necessary
processed_datasets = {}
for split, dataset in raw_datasets.items():
# Rename 'document' column to 'text' and remove 'id' column
@klei22
klei22 / embed.py
Created April 24, 2023 15:04 — forked from peterw/embed.py
embedding the pdf
import openai
import streamlit as st
from streamlit_chat import message
from dotenv import load_dotenv
import os
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
import openai
from langchain.document_loaders import UnstructuredMarkdownLoader
from langchain.chains.question_answering import load_qa_chain
@klei22
klei22 / index.html
Last active March 15, 2018 03:15
Lithium Energy Graph - Google Charts
<div id="chart_div" style="width: 900px; height: 500px;">
</div>