Package index • elmer

Chatbots

chat_azure(): Chat with a model hosted on Azure OpenAI

chat_bedrock(): Chat with an AWS bedrock model

chat_claude(): Chat with an Anthropic Claude model

chat_cortex() cortex_credentials(): Create a chatbot that speaks to the Snowflake Cortex Analyst

chat_gemini(): Chat with a Google Gemini model

chat_github(): Chat with a model hosted on the GitHub model marketplace

chat_groq(): Chat with a model hosted on Groq

chat_ollama(): Chat with a local ollama model

chat_openai(): Chat with an OpenAI model

chat_perplexity(): Chat with a model hosted on perplexity.ai

token_usage(): Report on token usage in the current session

Chat helpers

create_tool_def(): Create metadata for a tool

content_image_url() content_image_file() content_image_plot(): Encode image content for chat input

live_console() live_browser(): Open a live chat application

interpolate() interpolate_file(): Helpers for interpolating data into prompts

Tools and structured data

tool(): Define a tool

type_boolean() type_integer() type_number() type_string() type_enum() type_array() type_object(): Type specifications

Objects

These classes abstact across behaviour differences in chat providers so that for typical elmer use you don’t need to worry about them. You’ll need to learn more about the objects if you’re doing something that’s only supported by one provider, or if you’re implementing a new provider.

Turn(): A user or assistant turn

Provider(): A chatbot provider

Content() ContentText() ContentImage() ContentImageRemote() ContentImageInline() ContentToolRequest() ContentToolResult(): Content types received from and sent to a chatbot

Chat: A chat