refractor: store history in mongodb

fix: increase buffer size for audio chunk handling in TTS synthesis

refactor: remove unused imports in TTS module

refactor: optimize audio chunk handling in TTS synthesis

fix: add debug output for saved sample path in TTS synthesis

fix: enable queueing for audio additional outputs and add debug sample saving in TTS

fix: remove queqe

fix: Update Dockerfile and application configuration for improved performance and compatibility

fix: Update speaking rate in TTS configuration for improved audio clarity

fix: Add support for .wav files in LFS and update audio handling in app.py

fix: Update startup message and AI persona name for consistency in TTS responses

fix: Update shipping information prompts for clarity and conciseness

fix: Update TTS voice name to 'Despina' and enhance prompt for natural speech; modify startup message and adjust demo launch settings

fix: Update voice selection and language code in TTS client configuration

fix: Restore token counting API request in LLMFinanceAnalyzer and adjust logging

refactor: Comment out token counting API request and streamline logging in LLMFinanceAnalyzer; update shipping information prompts in systemprompt

fix: Increase timeout for token count API request in LLMFinanceAnalyzer

refactor: Update transcription method to use transcribe_typhoon and enhance error handling; streamline token tracking in LLMFinanceAnalyzer

refactor: Comment out debug print statement and streamline tool execution in LLMFinanceAnalyzer

remove google genai

refactor: Remove unused genai import and comment out client initialization in GPT client

Fix summary_order function and update chat history for promotion interactions

refactor: Improve clarity and structure of user interaction stages in order processing

refactor: Update escalation instruction in order processing to improve clarity

refactor: Update display format in tool call and result messages for consistency

refactor: Update chat_history parameter type in call_admin function and adjust usage

feat: Enhance audio processing and transcription features

refactor: load_dotenv only when local

feat: Implement tools calling

Update backend/tts.py

Update backend/tts.py

Update backend/systemprompt.py

Update backend/models.py

Update backend/asr.py

Update backend/systemprompt.py

Update backend/models.py

Update backend/asr.py

Update backend/main.py

Update backend/models.py

Update backend/utils.py

Update backend/utils.py

Update backend/models.py

Update backend/utils.py

Update backend/models.py

Update backend/models.py

Update backend/models.py

Upload 23 files

Delete backend

Upload 32 files