v0.6.4 #119
Merged
v0.6.4 #119
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Fixed support for Anthropic's Claude models via the API integration. Also, fixes a bug where default model settings were not being properly loaded.
Enables loading environment variables from a `.env` file if `python-dotenv` is installed, allowing for more flexible configuration. Also, prioritizes explicit root paths and the AGENTFORGE_ROOT environment variable when determining the project root directory.
Update to AgentForge 0.6.2
Adds base infrastructure for Text-to-Speech and Speech-to-Text capabilities, including: - Audio input/output mixins for models - OpenAI Whisper and TTS model wrappers - Agent-level audio handling and routing logic This enables agents to process audio inputs and generate audio outputs.
Adds TTS and STT agents. Refactors audio format handling for OpenAI API compatibility. Adds audio sample and tests.
Enables auto-playing audio files based on settings in `system.yaml`. Removes env vars and uses config for save/play controls.
Relax chromadb version constraint to allow newer versions. This resolves a bug in chromadb on Windows, allowing the use of newer versions that include the fix.
Enables the use of an HTTP client for ChromaDB, offering an alternative connection method. Useful in situations where ChromaDB crashes when running the debugger. This gets ChromaDB off the IDE entirely, making debugging simpler. This is useful for debugging scenarios where the default client might encounter issues. Provides configurable host, port, SSL settings, and headers for the HTTP client.
Updates chromadb dependency to the latest version. chromadb updated to latest version to fix Windows specific bug. (DB entries were 30+mb, when they should have been a few KB) Improves Discord messaging by adding error handling to the send_message function. This allows the program to continue running even if a message fails to send. It also adds message content to the error log, which will assist debugging Discord issues.
Adds a try-except block to the Gemini API's `_process_response` method to catch potential exceptions during response processing. This prevents the application from crashing when the API returns unexpected or malformed responses, especially from the Gemini Vision API. It logs the error and the candidates responses for debugging purposes.
Increments the version number to reflect the latest changes.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implements audio processing features, including Text-to-Speech (TTS) and Speech-to-Text (STT) capabilities, and updates project dependencies.
AudioManagerfor handling audio file persistence and playback.BaseModelsubclasses.chromadbdependency and improves Discord messaging..envfile.