Release 0.2.0

.gitignore

@@ -175,3 +175,7 @@ cython_debug/
 
 # PyPI configuration file
 .pypirc
+
+# Others
+.trash
+docs

Makefile

@@ -0,0 +1,10 @@
+lint:
+	black .
+	isort .
+	flake8 .
+	mypy . --check-untyped-defs
+
+test:
+	pytest
+
+check: lint test

README.md

@@ -1,3 +1,88 @@
-# speech-to-speech
+# HuRI
 
-1. python3.12
+## Presentation
+
+HuRI is an open-source research project focused on conversational AI for humanoid robots and virtual avatars.
+HuRI provides a modular architecture that allows developers to design, implement, and run AI modules within customizable conversational pipelines defined by the user.
+HuRI is launched as a multi-client server, to handle multiple client (robots) conversational requests.
+The framework supports the implementation and integration of multiple AI modules, including:
+Speech-to-Text (STT) and Text-to-Speech (TTS), Retrieval-Augmented Generation (RAG), Emotional analysis (EMO), Motion and gesture generation (MOV)
+
+## Getting Started
+
+### Prerequisites
+
+- python 3.11.14
+  ```sh
+  sudo apt install python3.11
+  ```
+- pip
+  ```sh
+  sudo apt install python3-pip
+  ```
+
+### Installation
+
+1. Clone the repo
+   ```sh
+   git clone https://github.com/Sentience-Robotics/HuRI.git
+   ```
+2. Install pip packages
+   ```sh
+   pip install -r requirements.txt
+   ```
+
+## Usage
+
+#### Launch HuRI server:
+
+```sh
+serve run [config_file_path]
+```
+
+We use ray serve config file, doc [here](https://docs.ray.io/en/latest/serve/configure-serve-deployment.html).
+
+You can also launch HuRI without config file:
+
+```sh
+python -m src.launch_huri
+```
+
+#### Launch Client:
+
+```sh
+python -m src.client --config [client_config_file_path]
+```
+
+We have custom yaml file to define modules to use and how they are initialized, template [here](config/client_template.yaml).
+
+### Folder/Module structure
+
+- #### root
+
+Entrypoints:
+
+HuRI: app.py & launch_huri.py \
+Client: client.py
+
+- #### Core
+
+HuRI's Core classes:
+
+client & client_senders \
+events \
+huri \
+module \
+session
+
+- #### Modules
+
+Modules implementation:
+
+rag: rag's implementation \
+speech_to_text: speech to text implementation, including MIC (vad), STT (speech to text) and TAG (text aggregator) \
+utils: utility modules, like Sender (send event to Clients)
+
+## Developper Documentation
+
+HuRI's complete documentation is available [here](https://docs.sentience-robotics.fr/share/p1x9ikjkhf/p/hu-ri-documentation-f4amcndYQg).

config/client_aux.yaml

@@ -0,0 +1,28 @@
+huri_url: ws://localhost:8000/session
+
+topic_list: [question]
+
+senders:
+  audio:
+    name: audio
+    args:
+      sample_rate: 16000
+      frame_duration: 0.030
+
+modules:
+  mic:
+    name: mic
+    args:
+      vad_agressiveness: 3
+      silence_duration: 1.5
+      block_duration: ${inputs.audio.args.frame_duration}
+    logging: INFO
+  stt:
+    name: stt
+    args:
+      language: "en"
+      block_duration: ${inputs.audio.args.frame_duration}
+    logging: INFO
+  tag:
+    name: tag
+    logging: INFO

config/client_aux2.yaml

@@ -0,0 +1,32 @@
+huri_url: ws://localhost:8000/session
+
+topic_list: [transcript, question, rag_response]
+
+senders:
+  audio:
+    name: audio
+    args:
+      sample_rate: 16000
+      frame_duration: 0.030
+
+modules:
+  mic:
+    name: mic
+    args:
+      vad_agressiveness: 3
+      silence_duration: 1.5
+      block_duration: ${senders.audio.args.frame_duration}
+  stt:
+    name: stt
+    args:
+      language: en
+      block_duration: ${senders.audio.args.frame_duration}
+    logging: INFO
+  tag:
+    name: tag
+    logging: INFO
+  rag:
+    name: rag
+    args:
+      language: en
+      tone: formal

config/client_auxio.yaml

@@ -0,0 +1,25 @@
+huri_url: ws://localhost:8000/session
+
+topic_list: [question]
+
+senders:
+  text:
+    name: text
+
+modules:
+  mic:
+    name: mic
+    args:
+      vad_agressiveness: 3
+      silence_duration: 1.5
+      block_duration: ${senders.audio.args.frame_duration}
+    logging: INFO
+  stt:
+    name: stt
+    args:
+      language: en
+      block_duration: ${senders.audio.args.frame_duration}
+    logging: INFO
+  tag:
+    name: tag
+    logging: INFO

config/client_template.yaml

@@ -0,0 +1,25 @@
+# HuRI websocket server url
+huri_url: ws://localhost:8000/session
+
+# List of event topic the client will receive
+topic_list: [topic1, topic2]
+
+# Define senders to be used and their custom args
+senders:
+  # sender tag can be anything
+  example:
+    # sender name must be in the list of available ClientSender in Client instance (src.client_sender:get_senders)
+    name: my_sender
+    # if my_sender init with "model", "sample_rate" and "refresh_rate" params, they can be customized here
+    args:
+      refresh_rate: infinite
+
+# Define module to be used and their custom args
+modules:
+  # module tag can be anything
+  example:
+    # module name must be in the list of available module in HuRI's instance (src.modules.modules:get_modules)
+    name: my_module
+    # if my_module init with "model", "sample_rate" and "hello" params, they can be customized here
+    args:
+      hello: world

config/client_text.yaml

@@ -0,0 +1,15 @@
+huri_url: ws://localhost:8000/session
+
+topic_list: [question, rag_response]
+
+senders:
+  text:
+    name: text
+
+modules:
+  rag:
+    name: rag
+    args:
+      language: en
+      tone: formal
+    logging: INFO

config/huri.yaml

@@ -1,11 +1,35 @@
-hostname: localhost
+proxy_location: EveryNode
 
-router:
-  port: 3000
+http_options:
+  host: 0.0.0.0
+  port: 8000
 
-event-proxy:
-  xsub: 5555
-  xpub: 5556
+logging_config:
+  encoding: TEXT
+  log_level: INFO
+  logs_dir: null
+  enable_access_log: true
+  additional_log_standard_attrs: []
 
-log-puller:
-  port: 8008
+services:
+  qdrant:
+    port: 6333
+    image: "qdrant/qdrant:latest"
+    storage_volume: "qdrant_data"
+  ollama:
+    model: "mistral:7b"
+    image: "ollama/ollama:rocm"
+    gpu_devices: true
+    num_replicas: 1
+
+applications:
+  - name: huri-app
+    route_prefix: /
+    import_path: src.app:app
+    runtime_env: { RAY_COLOR_PREFIX=1 }
+    deployments:
+      - name: HuRI
+      - name: RAGHandle
+        num_replicas: 2
+      - name: OllamaService
+      - name: QdrantService

pyproject.toml

@@ -0,0 +1,31 @@
+[tool.black]
+line-length = 88
+target-version = ["py310"]
+
+[tool.isort]
+profile = "black"
+line_length = 88
+multi_line_output = 3
+include_trailing_comma = true
+skip_gitignore = true
+
+[tool.flake8]
+max-line-length = 88
+extend-ignore = ["E203"]
+exclude = """
+  __pycache__
+  venv
+  .venv
+"""
+
+[tool.mypy]
+python_version = "3.10"
+ignore_missing_imports = true
+strict_optional = true
+warn_unused_ignores = true
+warn_return_any = true
+warn_unused_configs = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py"]