fix

update

feat: Add return_base64 parameter to generate_speech function, allowing output as Base64 audio alongside file path. Update request and response models for clarity and enhance documentation.

feat: Update generate_speech endpoint to enforce MP3 format, modify request and response models for clarity, and enhance documentation to reflect language code usage and format restrictions.

feat: Enhance TTS functionality to support Base64 audio output alongside file response. Introduce new text_to_speech_base64 function for Base64 conversion and update generate_tts endpoint to handle return_base64 parameter.

feat: Update generate_speech function to use gTTS backend with MP3 format and modify voice parameter to accept language codes. Clean up tts_service.py by removing unused GROQ API key checks and related code.

fix: Resolve merge conflicts in tts_service.py, ensuring proper integration of gTTS for text-to-speech functionality and maintaining MP3 format support.

feat: Update TTS functionality to use gTTS for text-to-speech conversion, supporting only MP3 format. Adjust requirements and model fields for compatibility.

feat: Introduce individual GROQ API keys for Topic, STT, TTS, and Chat services, enhancing configuration flexibility and service initialization checks across the application.

Update README.md

Merge branch 'main' of https://huggingface.co/spaces/NLP-Debater-Project/FastAPI-Backend-Models

similarity

refactor: Update GROQ_TOPIC_MODEL to the latest production version and adjust fallback models in TopicService for improved model selection and stability.

refactor: Update GROQ_TOPIC_MODEL for consistency and adjust fallback models in TopicService to enhance model selection and robustness.

feat: Add GROQ_TOPIC_MODEL configuration and enhance TopicService to utilize it for improved model selection during initialization, including fallback options for robustness.

chore: Update requirements.txt to address urllib3 compatibility issues and add requests-toolbelt for enhanced HTTP request handling.

feat: Integrate Topic Extraction service into API lifecycle, enhancing initialization and health check reporting. Update routes and logging for improved visibility of topic extraction functionality.

feat: Add extract_topic and voice_chat tools to MCP service, enhancing functionality for topic extraction and chatbot responses. Update models and routes to support new features.

refactor: Update file path handling in TopicSimilarityService for improved error reporting and ensure absolute paths for topic and embeddings cache files

test

feat: Add topic similarity service using Google Generative AI embeddings, enabling improved topic matching and similarity analysis. Update topic extraction logic to utilize this service and enhance overall functionality.

refactor: Simplify topic extraction logic in TopicService by removing Pydantic schema, enhancing JSON response handling, and adding fuzzy matching for improved topic validation.

feat: Introduce predefined topics list in TopicService and enhance topic extraction logic to validate against this list, ensuring accurate topic matching and improved error handling.

fix: Update topic extraction instructions in TopicService to specify that the main idea should be captured in simple English.

fix: Clarify topic extraction instructions in the TopicService to specify that the output should be a single sentence capturing the main idea.

feat: Enhance analysis endpoints to support JSON body input and CSV file uploads for argument analysis

fix: Update error logging for route loading failures and enhance route debugging with detailed logging of available routes

refactor: Change analysis endpoint prefixes from "" to "analyse" and update related route methods to use "stance"

feat: Add analysis endpoints and service for processing arguments, extracting topics, and predicting stance

feat: Implement user management service with Supabase integration, including user registration, retrieval, and name update endpoints.

feat: Add `GenerateModelManager` for loading Hugging Face generation models and performing text generation.

feat: Implement generation model manager for Hugging Face Seq2Seq models and add a debug script for testing generation.

chore: Update and manage project dependencies.

chore: Update dependencies in requirements.txt.

chore: Manage project dependency protobuf v 3.20.1

chore: update project dependency protobuf v 3.20.3

build: update project dependencies

Update project dependencies.

Merge branch 'main' of https://huggingface.co/spaces/NLP-Debater-Project/FastAPI-Backend-Models

chore: remove default fallback value for HUGGINGFACE_GENERATE_MODEL_ID.

Merge branch 'main' of https://huggingface.co/spaces/NLP-Debater-Project/FastAPI-Backend-Models

Update config.py

Merge branch 'main' of https://huggingface.co/spaces/NLP-Debater-Project/FastAPI-Backend-Models

feat: Add topic-related schemas and API routes for topic management, along with LangChain dependencies in requirements.

feat: Refactor stance detection, keypoint matching, and argument generation to utilize dedicated model managers for improved reliability and response handling

feat: Implement audio transcription and speech generation endpoints with file upload support and improved response handling

feat: Enhance ToolCallRequest and ToolCallResponse models with detailed examples and descriptions for improved clarity and usability in MCP tool calls.

refactor: Remove GenerateArgumentRequest and GenerateArgumentResponse models; update generate_argument endpoint to accept topic and position parameters.

fix: update default Hugging Face generate model ID to `NLP-Debater-Project/kpa-t5-improved`

feat: Introduce FastAPI endpoints for single and batch text generation with Pydantic models and Hugging Face model management.