Hey Everyone,
Recently, Databricks announced a new standard for efficient open source LLMs – DBRX. This LLM can be used together with Dash to create remarkable AI data apps.
Starting today, we challenge the LLM builder community to develop large language models with DBRX and create front-end app interfaces for them with Dash.
The winning apps will be judged according to the following categories:
- App must integrate DBRX
- Impact the app could have (great business idea, societal impact, etc.)
- Integration of AI agents (LangChain, CrewAI, etc.)
- App UI/UX Design
Please submit your app as a new post in this thread. Please include a link to the app (not mandatory, but encouraged), link to code on GitHub, and a short description of the app.
Submission deadline is the end of the day Sunday, June 30, 2024.
The winners will be announced in July and will receive a reward of:
$125
$75
$50
The lucky app challenge participants will be featured in the next edition of Dash Club and have a chance to showcase their app at a community event.
For any questions, please email Adam at adam@plot.ly.
DBRX Pricing Note:
You can open your first Databricks account with a 14-day free trial. All Databricks usage is free during this time, but Databricks uses compute and S3 storage resources in your AWS account, so please be aware of usage and expenses.
Create Free Trial Databricks Account:
- To work with the DBRX LLM, you will need to create a Databricks account and a Databricks workspace. We’ve recorded a video tutorial to support you through the process.
App Ideas:
- Question-Answering app
- RAG app that can summarize and answer questions from links, PDFs, videos, etc.
- App that summarizes risks and opportunities in a financial report
- App that incorporates a chatbot - customer support
Minimal App Examples:
Question-Answering Dash app with DBRX:
from dash import Dash, html, dcc, callback, Output, Input, no_update
from openai import OpenAI
from dotenv import find_dotenv, load_dotenv
import os
dotenv_path = find_dotenv()
load_dotenv(dotenv_path)
# Once you have your workspace, create your token by going to your databricks avatar -> settings -> developer -> Access tokens
DATABRICKS_TOKEN = os.getenv("DATABRICKS_TOKEN") # Create a .env file and write: DATABRICKS_TOKEN="insert-your-token"
client = OpenAI(
api_key=DATABRICKS_TOKEN,
base_url="https://***your-workspace***.cloud.databricks.com/serving-endpoints"
# the base_url will be sent to your email once your workspace is created. It's also in the 1st part of the url when you're in your workspace
)
app = Dash()
app.layout = [
dcc.Markdown("# Minimal example of a no-memory Chat Dash app"),
html.Label("Type your question to activate the DBRX LLM"),
html.P(),
dcc.Input(id='user-input', type='text', debounce=True), # debounce will delay the Input Processing until after you hit Enter
html.Div(id='response-space', children='')
]
@callback(
Output('response-space', 'children'),
Input('user-input', 'value'),
prevent_initial_call=True
)
def activate_chat(input_value):
if not input_value: # don't update the Output if the input value is empty (no text)
return no_update
else:
chat_completion = client.chat.completions.create(
messages=[
{
"role": "system",
"content": "You are an AI assistant"
},
{
"role": "user",
"content": input_value
}
],
model="databricks-dbrx-instruct", # this is the DBRX model
max_tokens=256
)
print(chat_completion)
response = chat_completion.choices[0].message.content
return response
if __name__ == '__main__':
app.run_server(debug=True)
RAG App with DBRX:
from dash import Dash, dcc, html, callback, Output, Input, State
import dash_mantine_components as dmc # pip install dash-mantine-components==0.12.0
from langchain_community.document_loaders import WebBaseLoader, PyPDFLoader
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_core.prompts import ChatPromptTemplate
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain.chains import create_retrieval_chain
from dotenv import find_dotenv, load_dotenv
import re
import os
dotenv_path = find_dotenv()
load_dotenv(dotenv_path)
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") # Create a .env file and write: OPENAI_API_KEY="insert-your-openai-token"
# Once you have your workspace, create your token by going to your databricks avatar -> settings -> developer -> Access tokens
DATABRICKS_TOKEN = os.getenv("DATABRICKS_TOKEN") # Add to your .env file: DATABRICKS_TOKEN="insert-your-token"
llm = ChatOpenAI(model_name="databricks-dbrx-instruct", # this is the DBRX model
openai_api_key=DATABRICKS_TOKEN,
openai_api_base="***your-workspace***.cloud.databricks.com/serving-endpoints")
# the base_url will be sent to your email once your workspace is created. It's also in the 1st part of the url when you're in your workspace
prompt = ChatPromptTemplate.from_template("""Answer the following question based only on the provided context:
<context>
{context}
</context>
Question: {input}""")
document_chain = create_stuff_documents_chain(llm, prompt) # chain the LLM to the prompt
# Initialize the Dash app and define the layout
app = Dash()
app.layout = html.Div(
[
dmc.Container( # dash-mantine-components==0.12.0
children=[
dmc.Title(order=1, children="Online Document Summarizer"),
dmc.TextInput(label="Summarize Doc", placeholder="Enter the webpage or pdf...", id="input-1"),
dmc.TextInput(label="Ask your question", placeholder="Ask away...", id="input-2"),
dcc.Loading(html.Div(id='answer-space')),
dmc.Button(children="Submit", id="submit-btn", mt="md")
],
style={"maxWidth": "500px", "margin": "0 auto"},
)
]
)
@callback(
Output('answer-space', 'children'),
Input('submit-btn', 'n_clicks'),
State('input-1', 'value'),
State('input-2', 'value'),
prevent_initial_call=True
)
def update_output(n_clicks, input1, input2):
if bool(re.search(r'\.pdf$', input1, re.IGNORECASE)): # checks if link refers to a pdf
# https://image-us.samsung.com/SamsungUS/tv-ci-resources/2018-user-manuals/2018_UserManual_Q9FNSeries.pdf
# https://arxiv.org/pdf/2304.03271.pdf
loader = PyPDFLoader(input1)
docs = loader.load_and_split()
else:
# load HTML pages and parse them
# https://en.wikipedia.org/wiki/Paris
loader = WebBaseLoader(input1)
docs = loader.load()
embeddings = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)
text_splitter = RecursiveCharacterTextSplitter()
documents = text_splitter.split_documents(docs)
vector = FAISS.from_documents(documents, embeddings)
retriever = vector.as_retriever()
retrieval_chain = create_retrieval_chain(retriever, document_chain)
# Sample questions for testing app:
# What was Paris architecture like in the 19th century
# How can I fix my remote control?
# How many litters of water did google consume in 2022?
response = retrieval_chain.invoke(
{"input": input2})
return response["answer"]
if __name__ == '__main__':
app.run_server(debug=True)
Pandas Agent Dash App with DBRX and Langchain:
from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent
from langchain_openai import ChatOpenAI
from dash import Dash, html, dcc, callback, Input, Output
import plotly.express as px
import pandas as pd
from dotenv import find_dotenv, load_dotenv
import os
dotenv_path = find_dotenv()
load_dotenv(dotenv_path)
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") # Create a .env file and write: OPENAI_API_KEY="insert-your-openai-token"
df = px.data.stocks()
df['date'] = pd.to_datetime(df['date'])
dropdown_options = list(df.columns)
dropdown_options.remove('date')
DATABRICKS_TOKEN = os.getenv("DATABRICKS_TOKEN") # Add to your .env file: DATABRICKS_TOKEN="insert-your-token"
llm = ChatOpenAI(model_name="databricks-dbrx-instruct",
openai_api_key=DATABRICKS_TOKEN,
openai_api_base="https://***your-workspace***.cloud.databricks.com/serving-endpoints")
# agent = create_pandas_dataframe_agent(llm, df, verbose=True)
# response = agent.invoke("what is the data telling us about APPL stock performance?")
# print(response)
# exit()
app = Dash()
app.layout = [
dcc.Markdown("# Demo App using a Langchain Pandas Agent"),
dcc.Dropdown(id='stock-picker', options=dropdown_options, value=['AAPL','FB'], multi=True),
dcc.Graph(id='line-chart', figure={}),
dcc.Loading(html.Div(id='answer-space'))
]
@callback(
Output('line-chart', 'figure'),
Output('answer-space', 'children'),
Input('stock-picker', 'value')
)
def activate_agent(stocks_chosen):
# Create the figure
stocks_chosen.append('date') # append date column to other columns chosen by user
df_filtered = df.loc[:, stocks_chosen]
print(df_filtered)
fig = px.line(df_filtered, x='date', y=stocks_chosen)
# Use pandas agent to analyze the dataset
agent = create_pandas_dataframe_agent(llm, df_filtered, verbose=True, handle_parsing_errors=True)
response = agent.invoke("The dataset includes data for 2018 and for 2019. what is the dataset telling us about the performance of the stocks in both years")
print(response)
return fig, response["output"]
if __name__ == '__main__':
app.run_server(debug=True)
Good luck with the challenge. If you have any question while working on the challenge, please use the forum and support each other.