Package index • tidyllm

LLM Message Handling

Functions for creating, managing, and retrieving messages and metadata.

llm_message(): Create or Update Large Language Model Message Object
df_llm_message(): Convert a Data Frame to an LLMMessage Object
get_reply() last_reply(): Retrieve Assistant Reply as Text
get_reply_data() last_reply_data(): Retrieve Assistant Reply as Structured Data
get_user_message() last_user_message(): Retrieve a User Message by Index
get_metadata() last_metadata(): Retrieve Metadata from Assistant Replies
get_logprobs(): Retrieve Log Probabilities from Assistant Replies
rate_limit_info(): Get the current rate limit information for all or a specific API

Tidyllm Main Verbs

Core verbs for interacting with LLMs: sending messages, generating embeddings, deep research, and managing batch requests.

chat(): Chat with a Language Model
embed(): Generate text embeddings
deep_research(): Run Deep Research via a Provider
check_job(): Check the Status of a Batch or Research Job
fetch_job(): Fetch Results from a Batch or Research Job
send_batch(): Send a batch of messages to a batch API
check_batch(): Check Batch Processing Status
fetch_batch(): Fetch Results from a Batch API
list_batches(): List all Batch Requests on a Batch API
list_models(): List Available Models for a Provider

Schemata, Tools, and Media

Functions for JSON schemas, tool definitions, and media attachments.

tidyllm_schema(): Create a JSON Schema for Structured Outputs
field_chr() field_fct() field_dbl() field_lgl(): Define Field Descriptors for JSON Schema
field_object(): Define a nested object field
tidyllm_tool(): Create a Tool Definition for tidyllm
ellmer_tool(): Convert an ellmer Tool to a tidyllm TOOL
img(): Create an Image Object

API Provider Functions

Provider functions called from main verbs. Each provider exposes a consistent interface — pass to chat(), embed(), send_batch(), etc.

openai(): OpenAI Provider Function
claude(): Provider Function for Claude models on the Anthropic API
gemini(): Google Gemini Provider Function
groq(): Groq API Provider Function
mistral(): Mistral Provider Function
ollama(): Ollama API Provider Function
perplexity(): Perplexity Provider Function
deepseek(): Deepseek Provider Function
voyage(): Voyage Provider Function
openrouter(): OpenRouter Provider Function
llamacpp(): llama.cpp Provider Function
azure_openai(): Azure OpenAI Endpoint Provider Function

OpenAI-Specific Functions

Functions for OpenAI chat, batch processing, embeddings, and model listing.

openai_chat(): Send LLM Messages to the OpenAI Chat Completions API
openai_embedding(): Generate Embeddings Using OpenAI API
openai_list_models(): List Available Models from the OpenAI API
send_openai_batch(): Send a Batch of Messages to OpenAI Batch API
check_openai_batch(): Check Batch Processing Status for OpenAI Batch API
fetch_openai_batch(): Fetch Results for an OpenAI Batch
list_openai_batches(): List OpenAI Batch Requests
cancel_openai_batch(): Cancel an In-Progress OpenAI Batch

Claude-Specific Functions

Functions for Anthropic Claude chat, batch processing, and file management.

claude_chat(): Interact with Claude AI models via the Anthropic API
claude_list_models(): List Available Models from the Anthropic Claude API
send_claude_batch(): Send a Batch of Messages to Claude API
check_claude_batch(): Check Batch Processing Status for Claude API
fetch_claude_batch(): Fetch Results for a Claude Batch
list_claude_batches(): List Claude Batch Requests
claude_upload_file(): Upload a File to Claude API
claude_delete_file(): Delete a File from Claude API
claude_file_metadata(): Retrieve Metadata for a File from Claude API
claude_list_files(): List Files in Claude API
claude_websearch(): Builtin Claude Web Search Tool

Gemini-Specific Functions

Functions for Google Gemini chat, embeddings, file management, and batch processing.

gemini_chat(): Send LLMMessage to Gemini API
gemini_embedding(): Generate Embeddings Using the Google Gemini API
gemini_list_models(): List Available Models from the Google Gemini API
gemini_upload_file(): Upload a File to Gemini API
gemini_list_files(): List Files in Gemini API
gemini_file_metadata(): Retrieve Metadata for a File from Gemini API
gemini_delete_file(): Delete a File from Gemini API
send_gemini_batch(): Submit a list of LLMMessage objects to Gemini's batch API
check_gemini_batch(): Check the Status of a Gemini Batch Operation
fetch_gemini_batch(): Fetch Results for a Gemini Batch
list_gemini_batches(): List Recent Gemini Batch Operations

Groq-Specific Functions

Functions for Groq chat, audio transcription, and batch processing.

groq_chat(): Send LLM Messages to the Groq Chat API
groq_transcribe(): Transcribe an Audio File Using Groq transcription API
groq_list_models(): List Available Models from the Groq API
send_groq_batch(): Send a Batch of Messages to the Groq API
check_groq_batch(): Check Batch Processing Status for Groq API
fetch_groq_batch(): Fetch Results for a Groq Batch
list_groq_batches(): List Groq Batch Requests

Mistral-Specific Functions

Functions for Mistral chat, embeddings, and batch processing.

mistral_chat(): Send LLMMessage to Mistral API
mistral_embedding(): Generate Embeddings Using Mistral API
mistral_list_models(): List Available Models from the Mistral API
send_mistral_batch(): Send a Batch of Requests to the Mistral API
check_mistral_batch(): Check Batch Processing Status for Mistral Batch API
fetch_mistral_batch(): Fetch Results for an Mistral Batch
list_mistral_batches(): List Mistral Batch Requests

Ollama-Specific Functions

Functions for local Ollama models: chat, embeddings, and model management.

ollama_chat(): Interact with local AI models via the Ollama API
ollama_embedding(): Generate Embeddings Using Ollama API
ollama_list_models(): Retrieve and return model information from the Ollama API
ollama_download_model(): Download a model from the Ollama API
ollama_delete_model(): Delete a model from the Ollama API
send_ollama_batch(): Send a Batch of Messages to Ollama API

Perplexity-Specific Functions

Functions for Perplexity AI chat and asynchronous deep research.

perplexity_chat(): Send LLM Messages to the Perplexity Chat API
perplexity_deep_research(): Submit a Deep Research Request to Perplexity
perplexity_check_research(): Check the Status of a Perplexity Deep Research Job
perplexity_fetch_research(): Fetch Results from a Completed Perplexity Deep Research Job

DeepSeek-Specific Functions

Functions for DeepSeek chat and reasoning models.

deepseek_chat(): Send LLM Messages to the DeepSeek Chat API

VoyageAI-Specific Functions

Functions for Voyage AI embeddings and reranking.

voyage_embedding(): Generate Embeddings Using Voyage AI API
voyage_rerank(): Rerank Documents Using Voyage AI API

OpenRouter-Specific Functions

Functions for OpenRouter — access to 300+ models via a single API key.

openrouter_chat(): Send LLM Messages to the OpenRouter Chat API
openrouter_embedding(): Generate Embeddings Using the OpenRouter API
openrouter_list_models(): List Available Models on OpenRouter
openrouter_credits(): Get OpenRouter Credit Balance
openrouter_generation(): Get Details for an OpenRouter Generation

llama.cpp-Specific Functions

Functions for local llama.cpp servers: chat, embeddings, reranking, model management, and server utilities.

llamacpp_chat(): Send LLM Messages to a llama.cpp Server
llamacpp_embedding(): Generate Embeddings Using a llama.cpp Server
llamacpp_rerank(): Rerank Documents Using a llama.cpp Server
llamacpp_list_models(): List Models Loaded in the llama.cpp Server
llamacpp_health(): Check Health of the llama.cpp Server
llamacpp_list_local_models(): List Local GGUF Model Files
llamacpp_download_model(): Download a GGUF Model from Hugging Face
llamacpp_delete_model(): Delete a Local GGUF Model File
list_hf_gguf_files(): List GGUF Files Available in a Hugging Face Repository

Azure OpenAI-Specific Functions

Functions for Azure-hosted OpenAI deployments.

azure_openai_chat(): Send LLM Messages to an Azure OpenAI Chat Completions endpoint
azure_openai_embedding(): Generate Embeddings Using OpenAI API on Azure
send_azure_openai_batch(): Send a Batch of Messages to Azure OpenAI Batch API
check_azure_openai_batch(): Check Batch Processing Status for Azure OpenAI Batch API
fetch_azure_openai_batch(): Fetch Results for an Azure OpenAI Batch
list_azure_openai_batches(): List Azure OpenAI Batch Requests

Ellmer Compatibility

Functions for using tidyllm together with ellmer tools and chat objects.

ellmer_tool(): Convert an ellmer Tool to a tidyllm TOOL
chat_ellmer(): Send LLM Messages to Ellmer Chat Object
ellmer(): Alias for the Ellmer Provider Function

PDF Processing

Helpers for batch processing multi-page PDF documents.

pdf_page_batch(): Batch Process PDF into LLM Messages

Internals

Core S7 class definitions at the heart of tidyllm.

LLMMessage(): Large Language Model Message Class