Release 1.1.1 (#2124)

# Changelog

## Improvements:

- **Firecrawl Custom API URL**: Allowed users to set a custom API URL
for Firecrawl.
- **Gemini embedder update:** Updated the `GeminiEmbedder` to use the
new [Google’s genai SDK](https://github.com/googleapis/python-genai). It
means the interface has changed slightly:
    
    ```python
    # Before
embeddings = GeminiEmbedder("models/text-embedding-004").get_embedding(
        "The quick brown fox jumps over the lazy dog."
    )
    
    # After
    embeddings = GeminiEmbedder("text-embedding-004").get_embedding(
        "The quick brown fox jumps over the lazy dog."
    )
    ```
    
- Updated the `ModelsLabTools` toolkit constructor
(`/libs/agno/tools/models_labs.py`) to accommodate audio generation api
call. Its a breaking change since it changes the parameters of the
`ModelsLabTools` class.
`url` and `fetch_url` are removed from the parameters. The API urls are
decided based on the `file_type` the user provides.
    
    ```python
    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:
    
    ```jsx
    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.
- **Gemini Structured Output**: Addressed a bug with Gemini where
structured output would not be generated 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.

libs/agno/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "agno"
-version = "1.1.0"
+version = "1.1.1"
 description = "Agno: a lightweight framework for building multi-modal Agents"
 requires-python = ">=3.7,<4"
 readme = "README.md"