Snowflake(SiS)のStreamlitを使ったトークン数チェックアプリを作ってみた

import streamlit as st from snowflake.snowpark.context import get_active_session import snowflake.snowpark.functions as F # Get current session session = get_active_session() # Application title st.title("Cortex AI Token Count Checker") # AI settings st.sidebar.title("AI Settings") lang_model = st.sidebar.radio("Select the language model you want to use", ("snowflake-arctic", "reka-core", "reka-flash", "mistral-large2", "mistral-large", "mixtral-8x7b", "mistral-7b", "llama3.1-405b", "llama3.1-70b", "llama3.1-8b", "llama3-70b", "llama3-8b", "llama2-70b-chat", "jamba-instruct", "gemma-7b") ) # Function to count tokens (using Cortex's token counting function) def count_tokens(model, text): result = session.sql(f"SELECT SNOWFLAKE.CORTEX.COUNT_TOKENS('{model}', '{text}') as token_count").collect() return result[0]['TOKEN_COUNT'] # Token count check and cost calculation st.header("Token Count Check and Cost Calculation") input_text = st.text_area("Select a language model from the left pane and enter the text you want to check for token count:", height=200) # Let user input the price per credit credit_price = st.number_input("Enter the price per Snowflake credit (in dollars):", min_value=0.0, value=2.0, step=0.01) # Credits per 1M tokens for each model (as of 2024/8/30, mistral-large2 is not supported) model_credits = { "snowflake-arctic": 0.84, "reka-core": 5.5, "reka-flash": 0.45, "mistral-large2": 1.95, "mistral-large": 5.1, "mixtral-8x7b": 0.22, "mistral-7b": 0.12, "llama3.1-405b": 3, "llama3.1-70b": 1.21, "llama3.1-8b": 0.19, "llama3-70b": 1.21, "llama3-8b": 0.19, "llama2-70b-chat": 0.45, "jamba-instruct": 0.83, "gemma-7b": 0.12 } if st.button("Calculate Token Count"): if input_text: # Calculate character count char_count = len(input_text) st.write(f"Character count of input text: {char_count}") if lang_model in model_credits: # Calculate token count token_count = count_tokens(lang_model, input_text) st.write(f"Token count of input text: {token_count}") # Ratio of tokens to characters ratio = token_count / char_count if char_count > 0 else 0 st.write(f"Token count / Character count ratio: {ratio:.2f}") # Cost calculation credits_used = (token_count / 1000000) * model_credits[lang_model] cost = credits_used * credit_price st.write(f"Credits used: {credits_used:.6f}") st.write(f"Estimated cost: ${cost:.6f}") else: st.warning("The selected model is not supported by Snowflake's token counting feature.") else: st.warning("Please enter some text.")