Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://github.com/dylanpieper/batchLLM below:

dylanpieper/batchLLM: Batch Process LLM Text Completions Using a Data Frame

Batch process large language model (LLM) text completions by looping across the rows of a data frame column. This package is designed to optimize text processing tasks by utilizing data frames and column rows as the input and a new column with the text completions as the output.

This package is now deprecated.

I have stopped the development of batchLLM. This was my first attempt at creating an R package for LLM integration, and while it served its purpose, there are now better alternatives to work on:

• For general LLM operations, check out the ellmer package
• For batch processing with ellmer, check out the hellmer package
• For batch processing with local LLMs, check out the mall package

I appreciate everyone who used and supported this package. All existing functions will remain available but no new features will be added or issues resolved.

• Supports multiple LLMs: OpenAI's GPT, Anthropic's Claude, and Google's Gemini
• Automatic logging of batches and metadata
• Side-by-side comparison of outputs from different LLMs
• User-friendly Shiny App Addin
• Resumable batch processing
• Flexible configuration options

Production (CRAN):

install.packages("batchLLM")

Development (GitHub):

install.packages("devtools")
devtools::install_github("dylanpieper/batchLLM")

library(batchLLM)

# Set up your API keys
Sys.setenv(OPENAI_API_KEY = "your_openai_api_key")
Sys.setenv(ANTHROPIC_API_KEY = "your_anthropic_api_key")
Sys.setenv(GEMINI_API_KEY = "your_gemini_api_key")

# Configure LLMs
llm_configs <- list(
  list(LLM = "openai", model = "gpt-4o-mini"),
  list(LLM = "anthropic", model = "claude-3-haiku-20240307"),
  list(LLM = "google", model = "1.5-flash")
)

# Process data
beliefs <- lapply(llm_configs, function(config) {
  batchLLM(
    df = beliefs,
    col = statement,
    prompt = "classify as a fact or misinformation in one word",
    LLM = config$LLM,
    model = config$model,
    max_tokens = 100,
    batch_size = 10,
    batch_delay = "1min",
    case_convert = "lower",
    sanitize = TRUE
  )
})[[length(llm_configs)]]

print(beliefs)

• scrape_metadata(): Retrieve metadata from processed batches
• get_batches(): Subset generated output from processed batches
• batchLLM_shiny(): Shiny Addin for interactive use within RStudio IDE

• Sentiment analysis
• Thematic analysis
• Classification
• Labeling or tagging
• Language translation
• Refactoring variables

• Be aware of your API rate limits
• Check model accessibility with your API key

Contributions are welcome! Here are some features ideas:

• Function to analyze agreement between models

This project is licensed under the MIT License.

My work on a complex classification problem inspired me to create this tool. I was challenged with categorizing thousands of unique offense descriptions in court data, and later, I tested the functionality to classify drug metabolites to their drug categories in toxicology data. The original function evolved significantly, and today, it powers this Shiny app designed to streamline and scale the use of LLMs across various datasets. I hope this tool proves as valuable to you as it has in my own projects.

• Demo on ShinyApps.io
• Report an Issue

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4