v1.4.4
May 3, 2025
1.4.4
New Features:
- OpenAI File Support: Added support for
File
attached to prompts for agents withOpenAIChat
models.
Improvements:
- Llama API: Various improvements for Llama and LlamaOpenAI model classes including structured output and image input support
- Async Custom Retriever: The
retriever
parameter can now be anasync
function to be used withagent.arun
andagent.aprint_response
. - Gemini Video URL Input: Added support for
Video(url=...)
for Gemini.
Bug Fixes:
- OpenAI Responses o3 / o4 Tools: Fixed broken tool use for advanced reasoning models on
OpenAIResponses
. - MCP on CLI Support: Fixed support for
MCPTools
usage while callingagent.acli_app
.