v2.7.4

This release enhances multimodal capabilities with audio support, improves session page performance, and fixes various bugs for better stability and usability.

New Features

• Audio Response Support: Added support for audio responses, enhancing multimodal interaction capabilities.
• Audio Generation Tools: Integrated Eleven Labs for Audio Generation.
• Cohere Embedder: Introduced a new Cohere Embedder class with a corresponding cookbook example to demonstrate its usage.
• JSON and YAML Agent Storage: Now you can persist your data locally in JSON and YAML extension files

Improvements

• Version Checker for OpenAI: Added a warning for users with OpenAI versions below 1.52.0 to ensure compatibility with features like audio in ChatCompletionMessage.
• Agent Response Handling: Enhanced processing of agent responses to support lists, improving handling of multi-item outputs.

Bug Fixes

• AWS Bedrock Tool Descriptions: Fixed an issue where the transfer tool description was missing, causing incompatibility with AWS Bedrock Claude.
• Response Content Handling: Resolved crashes on the session page caused by non-string response content.
• Deep Copy Agent Memory: Addressed deep copy errors when using agent memory on the playground.
• Session Page Enhancements: Fixed the refresh button
• Fix Tool Parsing for Ollama: Fixed JSON schema tool parsing by transforming ['string', 'null'] parameters to 'string' for compatibility.
• Response Parsing for Gemini Tool: Improved response parsing to handle unserializable objects in tool_calls for Gemini on the playground.
• Memory Handling for Google Provider: Fixed an issue in monitoring_data where memory was removed for all providers, causing blank titles on Phidata.app; now only modifies memory for Google provider.
• RecursiveChunking ID Conflict: Resolved an issue in RecursiveChunking where processing large files with multiple chunks caused duplicate chunk record IDs, leading to psycopg.errors.UniqueViolation.

What's Changed

• created a weekend planner agent by @monali7-d in #1576
• added a book recommendation agent by @monali7-d in #1573
• Added Shopping Partner Agent by @monali7-d in #1571
• Fix: function tools description by @manthanguptaa in #1582
• Add version checker for openai by @dirkbrnd in #1590
• Fix: deep copy agent memory by @manthanguptaa in #1583
• cohere-embedder-phi-2214 by @ysolanky in #1586
• Fix tool parsing for ollama by @dirkbrnd in #1597
• Feat: File Agent Storage by @manthanguptaa in #1596
• Fix response parsing to make gemini tool use work by @dirkbrnd in #1591
• fix: docs has same id with recursive chucking by @cpunion in #1589
• fix-memory-bug-phi-2229 by @ysolanky in #1599
• Multimodal add audio gen tools, eleven labs by @anuragts in #1551
• Fix: path param to dir_path by @manthanguptaa in #1601
• Release 2.7.4 by @dirkbrnd in #1600

New Contributors

• @monali7-d made their first contribution in #1576
• @cpunion made their first contribution in #1589

Full Changelog: v2.7.3...v2.7.4