Adding additional node in the node-hub

.github/workflows/node-hub-ci-cd.yml

@@ -37,23 +37,8 @@ jobs:
 
       - name: Run Linting and Tests
         run: |
-          for dir in node-hub/*/ ; do
-            if [ -d "$dir" ]; then
-              if [ -f "$dir/pyproject.toml" ]; then
-                echo "Running linting and tests for Python project in $dir..."
-                (cd "$dir" && pip install .)
-                (cd "$dir" && poetry run black --check .)
-                (cd "$dir" && poetry run pylint --disable=C,R  --ignored-modules=cv2 **/*.py)
-                (cd "$dir" && poetry run pytest)
-              fi
-
-              if [ -f "$dir/Cargo.toml" ]; then
-                echo "Running build and tests for Rust project in $dir..."
-                (cd "$dir" && cargo build)
-                (cd "$dir" && cargo test)
-              fi
-            fi
-          done
+          chmod +x .github/workflows/node_hub_test.sh
+          .github/workflows/node_hub_test.sh
 
   publish:
     needs: [ci]

.github/workflows/node_hub_test.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+set -euo
+
+for dir in node-hub/*/ ; do
+if [ -d "$dir" ]; then
+    if [ -f "$dir/pyproject.toml" ]; then
+    echo "Running linting and tests for Python project in $dir..."
+    (cd "$dir" && pip install .)
+    (cd "$dir" && poetry run black --check .)
+    (cd "$dir" && poetry run pylint --disable=C,R  --ignored-modules=cv2 **/*.py)
+    (cd "$dir" && poetry run pytest)
+    fi
+
+    if [ -f "$dir/Cargo.toml" ]; then
+    echo "Running build and tests for Rust project in $dir..."
+    (cd "$dir" && cargo build)
+    (cd "$dir" && cargo test)
+    fi
+fi
+done

.gitignore

@@ -11,6 +11,8 @@ examples/**/*.txt
 
 # Removing images.
 *.jpg
+*.mp3
+*.wav
 *.png
 !docs/src/latency.png
 

Cargo.toml

@@ -32,6 +32,7 @@ members = [
     "libraries/extensions/telemetry/*",
     "node-hub/dora-record",
     "node-hub/dora-rerun",
+    "node-hub/terminal-print",
     "libraries/extensions/ros2-bridge",
     "libraries/extensions/ros2-bridge/msg-gen",
     "libraries/extensions/ros2-bridge/python",

examples/echo/.gitignore

@@ -0,0 +1 @@
+*.pt

examples/echo/README.md

@@ -0,0 +1,12 @@
+# Dora echo example
+
+Make sure to have, dora, pip and cargo installed.
+
+```bash
+dora up
+dora build dataflow.yml
+dora start dataflow.yml
+
+# In another terminal
+terminal-input
+```

examples/echo/dataflow.yml

@@ -0,0 +1,22 @@
+nodes:
+  - id: terminal-input
+    build: pip install -e ../../node-hub/terminal-input
+    path: dynamic
+    outputs:
+      - data
+    inputs:
+      echo: dora-echo/echo
+
+  - id: dora-echo
+    build: pip install -e ../../node-hub/dora-echo
+    path: dora-echo
+    inputs:
+      input: terminal-input/data
+    outputs:
+      - echo
+
+  - id: terminal-print
+    build: cargo build -p terminal-print
+    path: dynamic
+    inputs:
+      echo: dora-echo/echo

examples/pyarrow-test/.gitignore

@@ -0,0 +1 @@
+*.pt

examples/pyarrow-test/README.md

@@ -0,0 +1,9 @@
+# Dora echo example
+
+Make sure to have, dora, pip and cargo installed.
+
+```bash
+dora up
+dora build dataflow.yml
+dora start dataflow.yml
+```

examples/pyarrow-test/dataflow.yml

@@ -0,0 +1,16 @@
+nodes:
+  - id: pyarrow-sender
+    build: pip install -e ../../node-hub/pyarrow-sender
+    path: dynamic
+    outputs:
+      - data
+    env:
+      DATA: "[1, 2, 3, 4, 5]"
+
+  - id: pyarrow-assert
+    build: pip install -e ../../node-hub/pyarrow-assert
+    path: pyarrow-assert
+    inputs:
+      data: pyarrow-sender/data
+    env:
+      DATA: "pa.array([1, 2, 3, 4, 5])"

examples/speech-to-text/.gitignore

@@ -0,0 +1 @@
+*.pt

examples/speech-to-text/README.md

@@ -0,0 +1,12 @@
+# Dora echo example
+
+Make sure to have, dora, pip and cargo installed.
+
+```bash
+dora up
+dora build dataflow.yml
+dora start dataflow.yml
+
+# In another terminal
+terminal-print
+```

examples/speech-to-text/dataflow.yml

@@ -0,0 +1,20 @@
+nodes:
+  - id: dora-microphone
+    build: pip install -e ../../node-hub/dora-microphone
+    path: dora-microphone
+    outputs:
+      - audio
+
+  - id: dora-distil-whisper
+    build: pip install -e ../../node-hub/dora-distil-whisper
+    path: dora-distil-whisper
+    inputs:
+      input: dora-microphone/audio
+    outputs:
+      - text
+
+  - id: terminal-print
+    build: cargo build -p terminal-print
+    path: dynamic
+    inputs:
+      text: dora-distil-whisper/text

node-hub/dora-distil-whisper/README.md

@@ -0,0 +1,3 @@
+# Dora Node for transforming speech to text (English only)
+
+Check example at [examples/speech-to-text](examples/speech-to-text)

node-hub/dora-distil-whisper/dora_distil_whisper/__init__.py

@@ -0,0 +1,11 @@
+import os
+
+# Define the path to the README file relative to the package directory
+readme_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), "README.md")
+
+# Read the content of the README file
+try:
+    with open(readme_path, "r", encoding="utf-8") as f:
+        __doc__ = f.read()
+except FileNotFoundError:
+    __doc__ = "README file not found."

node-hub/dora-distil-whisper/dora_distil_whisper/main.py

@@ -0,0 +1,42 @@
+import torch
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+from dora import Node
+import pyarrow as pa
+import os
+
+os.environ["TRANSFORMERS_OFFLINE"] = "1"
+
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+
+model_id = "distil-whisper/distil-large-v3"
+
+model = AutoModelForSpeechSeq2Seq.from_pretrained(
+    model_id,
+    torch_dtype=torch_dtype,
+    low_cpu_mem_usage=True,
+    use_safetensors=True,
+    local_files_only=True,
+)
+model.to(device)
+
+processor = AutoProcessor.from_pretrained(model_id)
+pipe = pipeline(
+    "automatic-speech-recognition",
+    model=model,
+    tokenizer=processor.tokenizer,
+    feature_extractor=processor.feature_extractor,
+    max_new_tokens=128,
+    torch_dtype=torch_dtype,
+    device=device,
+    generate_kwargs={"language": "chinese"},
+)
+
+
+def main():
+    node = Node()
+    for event in node:
+        if event["type"] == "INPUT":
+            audio = event["value"].to_numpy()
+            result = pipe(audio)
+            node.send_output("text", pa.array([result["text"]]))

node-hub/dora-distil-whisper/pyproject.toml

@@ -0,0 +1,31 @@
+[tool.poetry]
+name = "dora-distil-whisper"
+version = "0.3.5"
+authors = [
+    "Haixuan Xavier Tao <[email protected]>",
+    "Enzo Le Van <[email protected]>",
+]
+description = "Dora dora-distil-whisper"
+license = "MIT License"
+homepage = "https://github.com/dora-rs/dora.git"
+documentation = "https://github.com/dora-rs/dora/blob/main/node-hub/dora-distil-whisper/README.md"
+readme = "README.md"
+packages = [{ include = "dora_distil_whisper" }]
+
+[tool.poetry.dependencies]
+dora-rs = "0.3.5"
+numpy = "< 2.0.0"
+pyarrow = ">= 5.0.0"
+transformers = ">= 4.0.0"
+accelerate = "^0.29.2"
+torch = "^2.1.1"
+
+[tool.poetry.scripts]
+dora-distil-whisper = "dora_distil_whisper.main:main"
+
+[build-system]
+requires = ["poetry-core>=1.8.0"]
+build-backend = "poetry.core.masonry.api"
+
+[project]
+readme = "README.md"

node-hub/dora-distil-whisper/tests/test_placeholder.py

@@ -0,0 +1,2 @@
+def test_placeholder():
+    pass

node-hub/dora-echo/README.md

@@ -0,0 +1,5 @@
+# Dora echo node
+
+This node will just echo whatever it receives as is.
+
+Check example at [examples/echo](examples/echo)

node-hub/dora-echo/dora_echo/__init__.py

@@ -0,0 +1,11 @@
+import os
+
+# Define the path to the README file relative to the package directory
+readme_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), "README.md")
+
+# Read the content of the README file
+try:
+    with open(readme_path, "r", encoding="utf-8") as f:
+        __doc__ = f.read()
+except FileNotFoundError:
+    __doc__ = "README file not found."

node-hub/dora-echo/dora_echo/main.py

@@ -0,0 +1,32 @@
+import argparse
+import os
+from dora import Node
+
+RUNNER_CI = True if os.getenv("CI") == "true" else False
+
+
+def main():
+
+    # Handle dynamic nodes, ask for the name of the node in the dataflow, and the same values as the ENV variables.
+    parser = argparse.ArgumentParser(description="Simple arrow sender")
+
+    parser.add_argument(
+        "--name",
+        type=str,
+        required=False,
+        help="The name of the node in the dataflow.",
+        default="echo",
+    )
+    args = parser.parse_args()
+
+    node = Node(
+        args.name
+    )  # provide the name to connect to the dataflow if dynamic node
+
+    for event in node:
+        if event["type"] == "INPUT":
+            node.send_output("echo", event["value"])
+
+
+if __name__ == "__main__":
+    main()

node-hub/dora-echo/pyproject.toml

@@ -0,0 +1,28 @@
+[tool.poetry]
+name = "dora-echo"
+version = "0.3.5"
+authors = [
+    "Haixuan Xavier Tao <[email protected]>",
+    "Enzo Le Van <[email protected]>",
+]
+description = "Dora echo"
+license = "MIT License"
+homepage = "https://github.com/dora-rs/dora.git"
+documentation = "https://github.com/dora-rs/dora/blob/main/node-hub/dora-echo/README.md"
+readme = "README.md"
+packages = [{ include = "dora_echo" }]
+
+[tool.poetry.dependencies]
+dora-rs = "0.3.5"
+numpy = "< 2.0.0"
+pyarrow = ">= 5.0.0"
+
+[tool.poetry.scripts]
+dora-echo = "dora_echo.main:main"
+
+[build-system]
+requires = ["poetry-core>=1.8.0"]
+build-backend = "poetry.core.masonry.api"
+
+[project]
+readme = "README.md"

node-hub/dora-echo/tests/test_placeholder.py

@@ -0,0 +1,2 @@
+def test_placeholder():
+    pass

node-hub/dora-keyboard/README.md

@@ -0,0 +1,3 @@
+# Dora Node for listening to keyboard input.
+
+Send char only in the `char` output stream, as string, on press.

node-hub/dora-keyboard/dora_keyboard/__init__.py

@@ -0,0 +1,11 @@
+import os
+
+# Define the path to the README file relative to the package directory
+readme_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), "README.md")
+
+# Read the content of the README file
+try:
+    with open(readme_path, "r", encoding="utf-8") as f:
+        __doc__ = f.read()
+except FileNotFoundError:
+    __doc__ = "README file not found."