Package index • tidyllm

LLM Message Handling

llm_message(): Create or Update Large Language Model Message Object

df_llm_message(): Convert a Data Frame to an LLMMessage Object

last_reply(): Retrieve the Last Assistant Reply

last_user_message(): Retrieve the Last User Message

get_reply(): Retrieve an Assistant Reply by Index

get_user_message(): Retrieve a User Message by Index

Core API Functions

chatgpt(): Call the OpenAI API to interact with ChatGPT or o-reasoning models

claude(): Call the Anthropic API to interact with Claude models

groq(): Call the Groq API to interact with fast opensource models on Groq

mistral(): Send LLMMessage to Mistral API

ollama(): Send LLMMessage to ollama API

Ollama Functions

ollama_download_model(): Download a model from the Ollama API

ollama_embedding(): Generate Embeddings Using Ollama API

ollama_list_models(): Retrieve and return model information from the Ollama API

Internals and Utility Functions

LLMMessage: Large Language Model Message Class

perform_api_request(): Perform an API request to interact with language models

generate_callback_function(): Generate API-Specific Callback Function for Streaming Responses

initialize_api_env(): Initialize or Retrieve API-specific Environment

rate_limit_info(): Get the current rate limit information for all or a specific API

update_rate_limit(): Update the standard API rate limit info in the hidden .tidyllm_rate_limit_env environment

wait_rate_limit(): Wait for ratelimit restore times to ellapse if necessary

parse_duration_to_seconds(): An internal function to parse the duration strings that OpenAI APIs return for ratelimit resets

PDF Processing

pdf_page_batch(): Batch Process PDF into LLM Messages