v1.1.1

Changelog

Improvements:

• File / Image Uploads on Agent UI: Agent UI now supports file and image uploads with prompts.

  • Supported file formats: .pdf .csv .txt .docx .json
  • Supported image formats: .png .jpeg .jpg .webp

• Firecrawl Custom API URL: Allowed users to set a custom API URL for Firecrawl.

• Updated ModelsLabTools Toolkit Constructor: The constructor in /libs/agno/tools/models_labs.py has been updated to accommodate audio generation API calls. This is a breaking change, as the parameters for the ModelsLabTools class have changed. The url and fetch_url parameters have been removed, and API URLs are now decided based on the file_type provided by the user.

  MODELS_LAB_URLS = {
      "MP4": "https://modelslab.com/api/v6/video/text2video",
      "MP3": "https://modelslab.com/api/v6/voice/music_gen",
      "GIF": "https://modelslab.com/api/v6/video/text2video",
  }
  
  MODELS_LAB_FETCH_URLS = {
      "MP4": "https://modelslab.com/api/v6/video/fetch",
      "MP3": "https://modelslab.com/api/v6/voice/fetch",
      "GIF": "https://modelslab.com/api/v6/video/fetch",
  }

  The FileType enum now includes MP3 type:

  class FileType(str, Enum):
      MP4 = "mp4"
      GIF = "gif"
      MP3 = "mp3"

Bug Fixes:

• Gemini functions with no parameters: Addressed an issue where Gemini would reject function declarations with empty properties.
• Fix exponential memory growth: Fixed certain cases where the agent memory would grow exponentially.
• Chroma DB: Fixed various issues related to metadata on insertion and search.
• Gemini Structured Output: Fixed a bug where Gemini would not generate structured output correctly.
• MistralEmbedder: Fixed issue with instantiation of MistralEmbedder.
• Reasoning: Fixed an issue with setting reasoning models.
• Audio Response: Fixed an issue with streaming audio artefacts to the playground.

What's Changed

• Fix audio on responses by @dirkbrnd in #2091
• reasoning-fix-ag-2692 by @ysolanky in #2096
• Add optional parameter to pass custom api url in firecrawl by @anuragts in #2097
• Make Gemini return structured outputs by @dirkbrnd in #2098
• Blog to audio podcast generator by @anuragts in #2090
• added audio to text example by @Ansub in #2089
• added audio sentimental analysis example by @Ansub in #2086
• Fix Chroma DB by @manthanguptaa in #2104
• fix: mistral initialization by @pritipsingh in #2106
• Remove image_to_image_agent from multimodal agents playground by @Ansub in #2110
• Music generator by @mishramonalisha76 in #2103
• fix case where memory is None when you get the system message by @dirkbrnd in #2111
• Fix history growing exponentially by @dirkbrnd in #2101
• Fix issue with Gemini and functions with no params by @dirkbrnd in #2123
• Release 1.1.1 by @dirkbrnd in #2124

Full Changelog: v1.1.0...v1.1.1