File size: 3,109 Bytes
8a0f3d7 6b138a7 8a0f3d7 a90de82 8a0f3d7 a90de82 8a0f3d7 a90de82 8a0f3d7 a90de82 8a0f3d7 6b138a7 8a0f3d7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 |
# Exercise : HuggingFace LLM Playground
# Application flow:
# 1. User selects the LLM
# 2. User adjusts the model parameters (optional)
# 3. User provide a query
# 4. Selected model is invoked
# 5. Result is shown to the user
import streamlit as st
from dotenv import load_dotenv
import os
# from langchain_community.llms import HuggingFaceHub
from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
from langchain_core.messages import HumanMessage
# Load the API keys, if running locally
# CHANGE the path to the env file
# If HF space is used then set the env var HUGGINGFACEHUB_API_TOKEN in the settings
try:
load_dotenv('C:\\Users\\raj\\.jupyter\\.env')
except:
print("Environment file not found !! MUST find the env var HUGGINGFACEHUB_API_TOKEN to work.")
# Title
st.title('HuggingFace LLM playground')
# Models that can be used
# Add/remove models from this list as needed
models = [
'mistralai/Mistral-7B-Instruct-v0.2',
'google/flan-t5-xxl',
# 'meta-llama/Meta-Llama-3-8B',
'tiiuae/falcon-40b-instruct',
]
# Selected model in model_id
model_id = st.sidebar.selectbox(
'Select model',
options=tuple(models)
)
# Read the API key from environment - switch key for different providers
# api_token = os.environ.get('HUGGINGFACEHUB_API_TOKEN')
if 'model-response' not in st.session_state:
st.session_state['model-response'] = '<provide query & click on invoke>'
# draw the box for model response
st.text_area('Response', value = st.session_state['model-response'], height=400)
# draw the box for query
query = st.text_area('Query', placeholder='provide query & invoke', value='who was the president of the USA in 2023?')
# Model parameter controls
# https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html
# Temperature
temperature = st.sidebar.slider(
label='Temperature',
min_value=0.01,
max_value=1.0
)
# Top p
top_p = st.sidebar.slider(
label='Top p',
min_value=0.01,
max_value=1.0,
value=0.01
)
# Top k
top_k = st.sidebar.slider(
label='Top k',
min_value=1,
max_value=50,
value=10
)
repetition_penalty = st.sidebar.slider(
label='Repeatition penalty',
min_value=0.0,
max_value=5.0,
value=1.0
)
# Maximum token
max_tokens = st.sidebar.number_input(
label='Max tokens',
value=50
)
# Function to create the LLM
def get_llm(model_id):
return HuggingFaceEndpoint(
repo_id=model_id,
temperature=temperature,
top_k = top_k,
top_p = top_p,
repetition_penalty = repetition_penalty,
max_new_tokens=max_tokens,
task="conversational"
)
# Function for invoking the LLM
def invoke():
llm_hf = get_llm(model_id)
# 2. Wrap it in ChatHuggingFace
chat_model = ChatHuggingFace(llm=llm_hf)
# Show spinner, while we are waiting for the response
with st.spinner('Invoking LLM ... '):
st.session_state['model-response'] = chat_model.invoke([HumanMessage(content=query)]).content
st.button("Invoke", on_click=invoke) |