From 1688f6dfc5aadd909f3237091208b9a62172c516 Mon Sep 17 00:00:00 2001
From: Dirk Brand <51947788+dirkbrnd@users.noreply.github.com>
Date: Wed, 18 Dec 2024 17:18:54 +0200
Subject: [PATCH] Release 2.7.4 (#1600)

## Description
This releases 2.7.4.

** Changelog **
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.

---------

Co-authored-by: Anurag <anuragsharma011011@gmail.com>
---
 phi/model/openai/chat.py | 1 -
 pyproject.toml           | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/phi/model/openai/chat.py b/phi/model/openai/chat.py
index 041ab5fc9..7b6256cb9 100644
--- a/phi/model/openai/chat.py
+++ b/phi/model/openai/chat.py
@@ -925,7 +925,6 @@ async def aresponse_stream(self, messages: List[Message]) -> Any:
         # -*- Generate response
         metrics.response_timer.start()
         async for response in self.ainvoke_stream(messages=messages):
-
             if response.choices and len(response.choices) > 0:
                 metrics.completion_tokens += 1
                 if metrics.completion_tokens == 1:
diff --git a/pyproject.toml b/pyproject.toml
index e6000c9e8..dbefd4499 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "phidata"
-version = "2.7.3"
+version = "2.7.4"
 description = "Build multi-modal Agents with memory, knowledge and tools."
 requires-python = ">=3.7"
 readme = "README.md"