Skip to content

feat: implement configuration gui #304

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 11 commits into from
Nov 14, 2024
+937 −7
Merged

feat: implement configuration gui #304

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
89aed59
feat: implement configuration gui
maciejmajek Nov 4, 2024
9277916
chore: add license
maciejmajek Nov 5, 2024
d3acba4
refactor: configurator, feat: expanded config.toml
maciejmajek Nov 5, 2024
2b41f41
docs: mention configurator in README.md
maciejmajek Nov 5, 2024
c754255
feat: handle asr and tts parameters
maciejmajek Nov 5, 2024
62e0ffc
refactor: simplify tests, feat: test asr
maciejmajek Nov 5, 2024
58153d2
feat(configurator.py): add TTS testing functionality for ElevenLabs a…
maciejmajek Nov 7, 2024
b53b0d6
Apply suggestions from code review
maciejmajek Nov 13, 2024
1f7f133
fix: advanced config state
maciejmajek Nov 13, 2024
8d16c76
fix: handle session_state
maciejmajek Nov 13, 2024
63b6e09
docs: add note in case the browser does not start automatically
maciejmajek Nov 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,6 +106,18 @@ rosdep install --from-paths src --ignore-src -r -y
> poetry install --with openset,nomad
> ```

#### 1.4 Configure RAI

Run the configuration tool to set up your vendor and other settings:

```bash
poetry shell
streamlit run src/rai/rai/utils/configurator.py
```

> [!TIP]
> If the web browser does not open automatically, open the URL displayed in the terminal manually.

### 2. Build the project:

#### 2.1 Build RAI workspace
Expand Down
20 changes: 17 additions & 3 deletions config.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
[vendor]
simple_model = "openai" # openai, aws, ollama
embeddings_model = "ollama"
simple_model = "openai"
complex_model = "openai"
embeddings_model = "openai"

[aws]
simple_model = "anthropic.claude-3-haiku-20240307-v1:0"
Expand All @@ -25,7 +25,21 @@ project = "rai"

[tracing.langfuse]
use_langfuse = false
host = "https://cloud.langfuse.com"
host = "http://localhost:3000"

[tracing.langsmith]
use_langsmith = false

[asr]
recording_device_name = "default"
vendor = "whisper"
language = "en"
silence_grace_period = 0.3
use_wake_word = false
vad_threshold = 0.3
wake_word_model = ""
wake_word_threshold = 0.5
Comment on lines +33 to +41
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codebase verification

🛠️ Refactor suggestion

Parameter validation for ASR configuration is missing

  • vad_threshold and wake_word_threshold are not validated to be between 0 and 1.
  • silence_grace_period is not validated to be positive.
  • recording_device_name is not verified against available devices.
🔗 Analysis chain

Add parameter validation for ASR configuration

The ASR configuration includes several parameters that should be validated:

  1. vad_threshold and wake_word_threshold should be between 0 and 1
  2. silence_grace_period should be positive
  3. recording_device_name should be verified against available devices
🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Description: Check for parameter validation in ASR configuration loading

# Search for ASR config validation
echo "Checking for ASR config validation..."
ast-grep --pattern 'def $_(config: $_) {
  $$$
  asr$_
  $$$
}'

# Search for device name validation
echo "Checking for recording device validation..."
rg -l "recording_device.*validation|check.*recording.*device"

Length of output: 346


[tts]
vendor = "elevenlabs"
keep_speaker_busy = false
Comment on lines +43 to +45
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codebase verification

Missing API Key Configuration for ElevenLabs in TTS

The TTS configuration lacks API key setup for ElevenLabs integration:

  • API key configuration not found in src/rai/rai/utils/configurator.py
🔗 Analysis chain

Consider additional TTS configuration parameters

The TTS configuration appears minimal and might be missing important parameters:

  1. API key configuration for ElevenLabs
  2. Voice selection options
  3. Speech parameters (speed, pitch, etc.)
🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Description: Check for TTS vendor integration and configuration handling

# Search for ElevenLabs integration
echo "Checking for ElevenLabs integration..."
rg -l "elevenlabs.*api|elevenlabs.*key"

# Search for TTS configuration handling
echo "Checking for TTS configuration handling..."
ast-grep --pattern 'class $TTS {
  $$$
  def $_($_, config: $_) {
    $$$
  }
  $$$
}'

Length of output: 346

18 changes: 17 additions & 1 deletion poetry.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 1 addition & 0 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,7 @@ deprecated = "^1.2.14"
tomli = "^2.0.1"
openwakeword = { git = "https://github.com/maciejmajek/openWakeWord.git", branch = "chore/remove-tflite-backend" }
pytest-timeout = "^2.3.1"
tomli-w = "^1.1.0"
[tool.poetry.group.dev.dependencies]
ipykernel = "^6.29.4"

Expand Down
Loading