Skip to content

ellmer 0.1.1

CRAN release: 2025-02-06

Lifecycle changes

New features

Bug fixes and minor improvements

  • Chat$get_model() returns the model name (#299).

  • chat_azure() has greatly improved support for Azure Entra ID. API keys are now optional and we can pick up on ambient credentials from Azure service principals or attempt to use interactive Entra ID authentication when possible. The broken-by-design token argument has been deprecated (it could not handle refreshing tokens properly), but a new credentials argument can be used for custom Entra ID support when needed instead (for instance, if you’re trying to use tokens generated by the AzureAuth package) (#248, #263, #273, #257, @atheriel).

  • chat_azure() now reports better error messages when the underlying HTTP requests fail (#269, @atheriel). It now also defaults to api_version = "2024-10-21" which includes data for structured data extraction (#271).

  • chat_bedrock() now handles temporary IAM credentials better (#261, @atheriel) and chat_bedrock() gains api_args argument (@billsanto, #295).

  • chat_databricks() now handles the DATABRICKS_HOST environment variable correctly whether it includes an HTTPS prefix or not (#252, @atheriel). It also respects the SPARK_CONNECT_USER_AGENT environment variable when making requests (#254, @atheriel).

  • chat_gemini() now defaults to using the gemini-2.0-flash model.

  • print(Chat) no longer wraps long lines, making it easier to read code and bulleted lists (#246).

ellmer 0.1.0

CRAN release: 2025-01-09

  • New chat_vllm() to chat with models served by vLLM (#140).

  • The default chat_openai() model is now GPT-4o.

  • New Chat$set_turns() to set turns. Chat$turns() is now Chat$get_turns(). Chat$system_prompt() is replaced with Chat$set_system_prompt() and Chat$get_system_prompt().

  • Async and streaming async chat are now event-driven and use later::later_fd() to wait efficiently on curl socket activity (#157).

  • New chat_bedrock() to chat with AWS bedrock models (#50).

  • New chat$extract_data() uses the structured data API where available (and tool calling otherwise) to extract data structured according to a known type specification. You can create specs with functions type_boolean(), type_integer(), type_number(), type_string(), type_enum(), type_array(), and type_object() (#31).

  • The general ToolArg() has been replaced by the more specific type_*() functions. ToolDef() has been renamed to tool.

  • content_image_url() will now create inline images when given a data url (#110).

  • Streaming ollama results works once again (#117).

  • Streaming OpenAI results now capture more results, including logprops (#115).

  • New interpolate() and prompt_file() make it easier to create prompts that are a mix of static text and dynamic values.

  • You can find how many tokens you’ve used in the current session by calling token_usage().

  • chat_browser() and chat_console() are now live_browser() and live_console().

  • The echo can now be one of three values: “none”, “text”, or “all”. If “all”, you’ll now see both user and assistant turns, and all content types will be printed, not just text. When running in the global environment, echo defaults to “text”, and when running inside a function it defaults to “none”.

  • You can now log low-level JSON request/response info by setting options(ellmer_verbosity = 2).

  • chat$register_tool() now takes an object created by Tool(). This makes it a little easier to reuse tool definitions (#32).

  • new_chat_openai() is now chat_openai().

  • Claude and Gemini are now supported via chat_claude() and chat_gemini().

  • The Snowflake Cortex Analyst is now supported via chat_cortex() (#56).

  • Databricks is now supported via chat_databricks() (#152).