feat: simplify and standardize examples #412
Conversation
- Standardize all examples to use 'nova-3' or 'aura-asteria-en' models - Update live transcription examples to stream from a consistent source - Add simple, clear READMEs and secure API key handling for all examples - Remove obsolete 'test/' directory to clean up the project structure
WalkthroughThis update restructures and simplifies the example and test directories for the Deepgram JS SDK. It introduces new and revised README files, updates and refactors example scripts for clarity and modern usage, adds or updates Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant ExampleScript
participant DeepgramClient
participant DeepgramAPI
User->>ExampleScript: Provide API key / Start example
ExampleScript->>DeepgramClient: Initialize with API key
DeepgramClient->>DeepgramAPI: Authenticate and connect
User->>ExampleScript: Trigger action (e.g., Start, Transcribe, Speak)
ExampleScript->>DeepgramClient: Send audio/text or request transcription
DeepgramClient->>DeepgramAPI: Stream data / request processing
DeepgramAPI-->>DeepgramClient: Return transcript/audio
DeepgramClient-->>ExampleScript: Emit event with result
ExampleScript-->>User: Display transcript/audio or log output
Possibly related PRs
Suggested reviewers
✨ Finishing Touches
🧪 Generate Unit Tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 17
🔭 Outside diff range comments (1)
examples/browser-live/index.html (1)
39-63: Remove conflicting audio source configuration.The code sets up both BBC stream fetching and MediaRecorder for microphone input, but only the microphone should be used for interactive live transcription.
connection.on(deepgram.LiveTranscriptionEvents.Open, () => { console.log("Connection opened."); - - fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service") - .then((response) => response.body) - .then((body) => { - const reader = body.getReader(); - function read() { - reader - .read() - .then(({ done, value }) => { - if (done) { - console.log("Stream complete"); - return; - } - connection.send(value); - read(); - }) - .catch((error) => { - console.error("Stream read error:", error); - }); - } - read(); - }) - .catch((error) => { - console.error("Fetch error:", error); - }); });
♻️ Duplicate comments (6)
examples/node-speak-live/index.js (1)
2-2: Same ESLint configuration issue as in other examples.This file has the same TypeScript ESLint rule definition issues identified in the static analysis.
examples/node-speak/README.md (1)
5-12: Same prerequisite caveat as the live-transcription READMEThe “Setup” section assumes
pnpm. Repeat the clarification about Node version and alternative package managers for consistency across READMEs.examples/node-agent-live/README.md (1)
5-12: Prerequisite clarificationMirror the note suggested for the other READMEs so users without
pnpmare not surprised.examples/node-live-token/README.md (1)
5-12: Prerequisite clarificationSame comment as above: mention required Node version and alternatives to
pnpm.examples/node-read/index.js (1)
2-2: ESLint configuration issue - same as other files.This file has the same ESLint rule definition issues as
examples/node-prerecorded/index.js. This is a project-wide configuration issue, not a code problem.examples/node-agent-live/index.js (1)
1-2: Fix ESLint rule configuration issues.The static analysis indicates that TypeScript ESLint rules are not found. This is a duplicate issue from the previous file.
🧹 Nitpick comments (22)
examples/node-agent-live/.gitignore (1)
2-4: Consider broader ignore patterns for.envand audio artifactsNice addition—ignoring
node_modulesand env files keeps the examples tidy.
Two optional tweaks:
- Environment files often appear with suffixes (
.env.local,.env.production, etc.).-.env
+.env*2. The WAV ignore can be broadened in case future scripts write differently-named files: ```diff -output-*.wav +*.wavThese are non-blocking; feel free to keep the current patterns if they better match the example conventions.
examples/node-live/.gitignore (1)
1-2: Consider ignoring lock-files as wellThe examples are using
pnpm, but users might swap tonpmoryarnwhile experimenting. Adding the common lock-files keeps the repo clean and avoids accidental commits.node_modules .env +package-lock.json +yarn.lock +pnpm-lock.yamlexamples/node-speak/.gitignore (1)
1-3: Minor: also ignore potential text-to-speech artefactsIf users change the output format or filename, auxiliary artefacts (e.g.
.wav) could get committed. A wildcard keeps the intent but stays future-proof.output.mp3 +output.*examples/node-speak-live/.gitignore (1)
1-3: Align ignore rules with other examplesFor consistency with
node-speak, consider the wildcard pattern so both live and non-live examples behave the same when filenames change.output.mp3 +output.*examples/node-speak-live/package.json (1)
1-12: Mark the example package as private to avoid accidentalnpm publishAdding
"private": trueprevents an inadvertent publish and matches typical example-app practice."name": "deepgram-node-speak-live-example", "version": "1.0.0", + "private": true,examples/node-live/package.json (1)
1-12: Addprivateflag for safetySame reasoning as the speak-live example—marking the package private guards against an unintended publish.
"name": "deepgram-node-live-example", "version": "1.0.0", + "private": true,examples/node-prerecorded/.gitignore (1)
1-2: Consider broadening environment-file patternsIgnoring
.envis good, but teams often use variants like.env.local,.env.dev, etc. Adding a wildcard prevents accidental commits of secrets.node_modules -.env +.env*examples/node-prerecorded/README.md (1)
1-20: Add missing prerequisite & output details
- Mention that the SDK must be built from the repo root before running:
pnpm run build # from project root- Clarify which audio file the script transcribes or how to pass a custom path.
- Note that the
.envfile can reside in either the example folder or repo root—newcomers often trip over dotenv path issues.examples/node-read/README.md (1)
1-20: README could briefly describe expected console outputA single sentence like “The script logs the sentiment / topics JSON to the console” helps users know what success looks like.
examples/node-speak-live/README.md (1)
1-20: Mention generated artefact & playback requirementThe example writes
output.mp3; indicate where the file is saved and that users need an MP3 player to hear the result. Small addition but improves UX.examples/node-live/README.md (1)
5-12: Clarify tooling prerequisites & add npm/yarn alternativesNot every user will have
pnpmpre-installed. Consider adding a short prerequisite note (“requires Node ≥18 and pnpm (or runnpm install/yarnas an alternative)”) so newcomers aren’t blocked.## Setup @@ -2. Install the dependencies: +2. Install the dependencies + *(requires `pnpm`; if you don’t use pnpm, replace with `npm install` or `yarn`)*:examples/node-live-token/package.json (1)
1-12: Include basic metadata & mark example as privateMinor polish: adding
private: trueprevents accidental publishing, and including alicense(even “UNLICENSED”) aligns with npm recommendations.{ "name": "deepgram-node-live-token-example", "version": "1.0.0", "description": "A simple example of using a temporary token to transcribe a live audio stream in Node.js.", + "license": "UNLICENSED", + "private": true, "main": "index.js",examples/node-read/package.json (1)
1-8: Mark example packages asprivateand declaretype":"module"
index.js(added in the same PR) usesimportsyntax. Node treats that as ESM only if"type": "module"is set.
Also marking the packageprivateprevents accidentalnpm publish.{ "name": "deepgram-node-read-example", + "private": true, "version": "1.0.0", @@ "main": "index.js", + "type": "module",examples/node-agent-live/package.json (1)
1-8: Consider ESM flag and private fieldIf
index.jsusesimportyou need"type": "module". Also mark as private.{ "name": "deepgram-node-agent-live-example", + "private": true, "version": "1.0.0", @@ "main": "index.js", + "type": "module",examples/node-speak/package.json (1)
1-8: Set"type": "module"and"private": truefor consistencyAlign with the other examples and avoid accidental publish.
{ "name": "deepgram-node-speak-example", + "private": true, "version": "1.0.0", @@ "main": "index.js", + "type": "module",examples/browser-live/README.md (1)
17-20: Passing the API key as a query-string is convenient but insecureAnyone who inspects browser history or server logs can read the key. For public/production demos prefer retrieving the key from a secured backend or a short-lived token endpoint instead of a persistent secret in the URL.
examples/browser-prerecorded/README.md (1)
17-20: Same security caveat about API key in URLStoring the secret in a URL is fine for quick local demos but unsafe for anything else. Consider adding a short note or link to token-based auth here as well, mirroring the comment in the live example.
examples/node-prerecorded/index.js (1)
99-112: Add null safety for nested property access.The new
transcribefunction is well-structured, but directly accessingresult.results.channels[0].alternatives[0].transcriptcould throw a runtime error if the response structure is unexpected or incomplete.Consider adding null safety:
if (error) { console.error(error); } else { - console.log(result.results.channels[0].alternatives[0].transcript); + const transcript = result?.results?.channels?.[0]?.alternatives?.[0]?.transcript; + if (transcript) { + console.log(transcript); + } else { + console.log("No transcript found in response"); + } }examples/browser-prerecorded/index.html (2)
33-37: Add null safety for nested property access.Similar to the Node.js example, directly accessing nested properties could cause runtime errors if the response structure is unexpected.
if (error) { console.error(error); } else { - console.log(result.results.channels[0].alternatives[0].transcript); + const transcript = result?.results?.channels?.[0]?.alternatives?.[0]?.transcript; + console.log(transcript || "No transcript found in response"); }
15-21: API key handling is acceptable for examples but not production.Using URL query strings for API keys is convenient for examples but poses security risks in production. Consider adding a note in the documentation about secure API key handling practices.
Consider adding a comment in the code to clarify this is for example purposes only:
const transcribe = async () => { const urlParams = new URLSearchParams(window.location.search); + // Note: For production applications, use secure methods to handle API keys const apiKey = urlParams.get("key");examples/node-speak/index.js (2)
10-10: Add validation for the API key.The code assumes the API key is available from environment variables but doesn't validate its presence, which could lead to runtime errors.
const speak = async () => { + if (!process.env.DEEPGRAM_API_KEY) { + console.error("DEEPGRAM_API_KEY environment variable is required"); + process.exit(1); + } const deepgram = createClient(process.env.DEEPGRAM_API_KEY);
24-29: Consider using async stream processing utilities.The manual Promise wrapper for stream processing could be simplified using Node.js stream utilities or async iterators for better readability and error handling.
- const buffer = await new Promise((resolve, reject) => { - const chunks = []; - stream.on("data", (chunk) => chunks.push(chunk)); - stream.on("end", () => resolve(Buffer.concat(chunks))); - stream.on("error", reject); - }); + const chunks = []; + for await (const chunk of stream) { + chunks.push(chunk); + } + const buffer = Buffer.concat(chunks);
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (37)
README.md(1 hunks)examples/README.md(1 hunks)examples/browser-live/README.md(1 hunks)examples/browser-live/index.html(2 hunks)examples/browser-prerecorded/README.md(1 hunks)examples/browser-prerecorded/index.html(1 hunks)examples/disabled_deno-prerecorded/index.js(0 hunks)examples/node-agent-live/.gitignore(1 hunks)examples/node-agent-live/README.md(1 hunks)examples/node-agent-live/index.js(1 hunks)examples/node-agent-live/package.json(1 hunks)examples/node-live-token/.gitignore(1 hunks)examples/node-live-token/README.md(1 hunks)examples/node-live-token/index.js(1 hunks)examples/node-live-token/package.json(1 hunks)examples/node-live/.gitignore(1 hunks)examples/node-live/README.md(1 hunks)examples/node-live/index.js(1 hunks)examples/node-live/package.json(1 hunks)examples/node-prerecorded/.gitignore(1 hunks)examples/node-prerecorded/README.md(1 hunks)examples/node-prerecorded/index.js(3 hunks)examples/node-prerecorded/package.json(1 hunks)examples/node-read/.gitignore(1 hunks)examples/node-read/README.md(1 hunks)examples/node-read/index.js(1 hunks)examples/node-read/package.json(1 hunks)examples/node-speak-live/.gitignore(1 hunks)examples/node-speak-live/README.md(1 hunks)examples/node-speak-live/index.js(1 hunks)examples/node-speak-live/package.json(1 hunks)examples/node-speak/.gitignore(1 hunks)examples/node-speak/README.md(1 hunks)examples/node-speak/index.js(1 hunks)examples/node-speak/package.json(1 hunks)test/enhanced_websocket_errors.test.ts(0 hunks)tests/README.md(1 hunks)
💤 Files with no reviewable changes (2)
- examples/disabled_deno-prerecorded/index.js
- test/enhanced_websocket_errors.test.ts
🧰 Additional context used
🧠 Learnings (22)
📓 Common learnings
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .markdownlint.jsonc:3-5
Timestamp: 2024-10-08T01:22:26.486Z
Learning: In the deepgram-js-sdk project, disabling the MarkdownLint rules `"line-length"`, `"no-bare-urls"`, and `"no-duplicate-heading"` is acceptable for GitHub documentation files.
examples/node-live-token/README.md (2)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .markdownlint.jsonc:3-5
Timestamp: 2024-10-08T01:22:26.486Z
Learning: In the deepgram-js-sdk project, disabling the MarkdownLint rules `"line-length"`, `"no-bare-urls"`, and `"no-duplicate-heading"` is acceptable for GitHub documentation files.
examples/node-prerecorded/README.md (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-live-token/package.json (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-agent-live/README.md (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-speak/.gitignore (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-live/README.md (2)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .markdownlint.jsonc:3-5
Timestamp: 2024-10-08T01:22:26.486Z
Learning: In the deepgram-js-sdk project, disabling the MarkdownLint rules `"line-length"`, `"no-bare-urls"`, and `"no-duplicate-heading"` is acceptable for GitHub documentation files.
examples/node-read/README.md (2)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .markdownlint.jsonc:3-5
Timestamp: 2024-10-08T01:22:26.486Z
Learning: In the deepgram-js-sdk project, disabling the MarkdownLint rules `"line-length"`, `"no-bare-urls"`, and `"no-duplicate-heading"` is acceptable for GitHub documentation files.
examples/node-speak-live/README.md (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-agent-live/.gitignore (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/README.md (2)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .markdownlint.jsonc:3-5
Timestamp: 2024-10-08T01:22:26.486Z
Learning: In the deepgram-js-sdk project, disabling the MarkdownLint rules `"line-length"`, `"no-bare-urls"`, and `"no-duplicate-heading"` is acceptable for GitHub documentation files.
examples/node-read/package.json (2)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .markdownlint.jsonc:3-5
Timestamp: 2024-10-08T01:22:26.486Z
Learning: In the deepgram-js-sdk project, disabling the MarkdownLint rules `"line-length"`, `"no-bare-urls"`, and `"no-duplicate-heading"` is acceptable for GitHub documentation files.
examples/node-agent-live/package.json (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-speak-live/package.json (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-live/package.json (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-speak/package.json (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-prerecorded/package.json (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-speak/README.md (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-prerecorded/index.js (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-read/index.js (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
examples/node-speak/index.js (1)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
tests/README.md (2)
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .markdownlint.jsonc:3-5
Timestamp: 2024-10-08T01:22:26.486Z
Learning: In the deepgram-js-sdk project, disabling the MarkdownLint rules `"line-length"`, `"no-bare-urls"`, and `"no-duplicate-heading"` is acceptable for GitHub documentation files.
Learnt from: naomi-lgbt
PR: deepgram/deepgram-js-sdk#333
File: .github/workflows/CI.yml:50-51
Timestamp: 2024-10-08T01:26:16.711Z
Learning: In the `deepgram-js-sdk` project, linting configuration files may have custom names that differ from the default ones.
🧬 Code Graph Analysis (4)
examples/node-prerecorded/index.js (1)
src/packages/ListenRestClient.ts (2)
transcribeUrl(35-72)transcribeFile(82-115)
examples/node-read/index.js (6)
examples/node-live/index.js (2)
require(4-4)deepgram(9-9)examples/node-live-token/index.js (2)
require(4-4)deepgram(9-9)examples/node-agent-live/index.js (2)
require(4-4)deepgram(9-9)examples/node-prerecorded/index.js (9)
require(4-4)require(5-5)require(6-6)deepgram(65-65)deepgram(68-75)deepgram(84-84)deepgram(91-93)deepgram(100-100)deepgram(103-105)examples/node-speak/index.js (5)
require(4-4)require(5-5)require(6-6)deepgram(10-10)text(11-11)examples/node-speak-live/index.js (4)
require(4-4)require(5-5)require(6-6)deepgram(10-10)
examples/node-speak/index.js (3)
examples/node-read/index.js (4)
require(4-4)deepgram(8-8)deepgram(11-16)text(9-9)examples/node-speak-live/index.js (5)
require(4-4)require(5-5)require(6-6)speak(9-36)deepgram(10-10)src/DeepgramClient.ts (1)
speak(90-92)
examples/node-agent-live/index.js (5)
examples/node-live/index.js (4)
require(4-4)fetch(5-5)deepgram(9-9)connection(10-12)examples/node-read/index.js (3)
require(4-4)deepgram(8-8)deepgram(11-16)examples/node-speak-live/index.js (5)
require(4-4)require(5-5)require(6-6)deepgram(10-10)connection(11-13)src/DeepgramClient.ts (1)
agent(100-102)src/index.ts (1)
createClient(46-46)
🪛 GitHub Check: Test / OS ubuntu-latest / Node 22
examples/node-live/index.js
[failure] 2-2:
Definition for rule '@typescript-eslint/no-require-imports' was not found
[failure] 2-2:
Definition for rule '@typescript-eslint/no-var-requires' was not found
examples/node-prerecorded/index.js
[failure] 2-2:
Definition for rule '@typescript-eslint/no-require-imports' was not found
[failure] 2-2:
Definition for rule '@typescript-eslint/no-var-requires' was not found
examples/node-read/index.js
[failure] 2-2:
Definition for rule '@typescript-eslint/no-require-imports' was not found
[failure] 2-2:
Definition for rule '@typescript-eslint/no-var-requires' was not found
examples/node-live-token/index.js
[failure] 2-2:
Definition for rule '@typescript-eslint/no-require-imports' was not found
[failure] 2-2:
Definition for rule '@typescript-eslint/no-var-requires' was not found
examples/node-agent-live/index.js
[failure] 2-2:
Definition for rule '@typescript-eslint/no-require-imports' was not found
[failure] 2-2:
Definition for rule '@typescript-eslint/no-var-requires' was not found
🪛 GitHub Actions: CI
examples/node-agent-live/index.js
[error] 2-2: ESLint: Definition for rule '@typescript-eslint/no-var-requires' was not found.
🔇 Additional comments (13)
tests/README.md (1)
1-46: LGTM! Clean and well-structured test documentation.The simplified test documentation is clear, concise, and provides all the necessary commands for running different types of tests. The structure follows good documentation practices and aligns well with the PR's objective of simplification.
examples/node-read/.gitignore (1)
1-3: LGTM! Standard Node.js gitignore patterns.The gitignore file correctly excludes common Node.js artifacts (
node_modules) and sensitive environment files (.env), following best practices for Node.js projects.examples/node-live-token/.gitignore (1)
1-3: LGTM! Consistent gitignore patterns across examples.This gitignore file maintains consistency with other example directories by using the same standard Node.js patterns, supporting the PR's goal of standardization.
README.md (1)
1021-1021: Double-check for lingeringnpm run buildreferencesThis line now uses
pnpm, but several other docs (e.g. CONTRIBUTING, DEVELOPMENT, individual example READMEs) may still instructnpm run build. A quick grep will confirm consistency.examples/README.md (1)
1-16: LGTM! Clean and focused documentation structure.The simplified README effectively delegates detailed instructions to individual example directories while providing the essential setup steps. The use of
pnpmfor the build command is appropriate for this project.examples/node-prerecorded/package.json (1)
1-12: LGTM! Well-structured package configuration.The package.json follows standard conventions with appropriate metadata and dependencies. The inclusion of
dotenvsupports secure environment variable management, which is a best practice for handling API keys.examples/node-prerecorded/index.js (3)
1-7: LGTM! Clean imports and environment configuration.The destructured imports and dotenv configuration improve code organization and follow security best practices for API key management.
86-88: LGTM! Improved path handling.The use of destructured
resolveandreadFileSyncfunctions is cleaner and more maintainable than the previous full module imports.
2-2: ESLint configuration issue - not a code problem.The static analysis failure indicates missing ESLint rule definitions, which is likely a configuration issue rather than a code problem. This should be addressed in the project's ESLint configuration.
The missing ESLint rules suggest the project's linting configuration may need updates. Based on the retrieved learnings, this project may have custom linting configuration files.
#!/bin/bash # Check for ESLint configuration files and verify rule definitions echo "Searching for ESLint configuration files..." fd -t f -e json -e js -e yaml -e yml | grep -E "(eslint|lint)" | head -10 echo -e "\nChecking for TypeScript ESLint plugin installation..." if [ -f "package.json" ]; then cat package.json | jq '.dependencies, .devDependencies' | grep -E "(typescript-eslint|eslint)" fi echo -e "\nSearching for any custom ESLint config files..." fd -t f -e jsonc | grep -i eslint | head -5examples/browser-prerecorded/index.html (1)
7-11: LGTM! Improved user experience with interactive transcription.The HTML structure and button-triggered transcription provide a better user experience compared to automatic transcription on page load.
examples/node-read/index.js (2)
4-5: LGTM! Clean imports and environment configuration.The simplified imports and dotenv configuration follow best practices for environment variable management.
7-23: LGTM! Well-structured and simplified example.The refactored
analyzefunction is clean and follows good practices:
- Simple test text for demonstration
- Consistent use of "nova-3" model
- Proper error handling with logging instead of throwing
- Clean result output with appropriate depth
examples/node-live-token/index.js (1)
1-2: ```bash
#!/bin/bashLocate ESLint configuration files
echo "ESLint config files:"
fd -t f -g ".eslintrc*"Check each config for TypeScript ESLint plugin/parser usage
echo "Checking for '@typescript-eslint' in these files:"
fd -t f -g ".eslintrc*" -x grep -H "@typescript-eslint" {} ;</details> </blockquote></details> </details> <!-- This is an auto-generated comment by CodeRabbit for review status -->
| fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service") | ||
| .then((r) => r.body) | ||
| .then((res) => { | ||
| res.on("readable", () => { | ||
| connection.send(res.read()); | ||
| }); | ||
| }); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add error handling for the stream connection.
The fetch operation and stream processing lack error handling, which could lead to unhandled promise rejections or runtime errors if the BBC stream is unavailable.
- fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service")
- .then((r) => r.body)
- .then((res) => {
- res.on("readable", () => {
- connection.send(res.read());
- });
- });
+ fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service")
+ .then((r) => {
+ if (!r.ok) {
+ throw new Error(`HTTP error! status: ${r.status}`);
+ }
+ return r.body;
+ })
+ .then((res) => {
+ res.on("readable", () => {
+ connection.send(res.read());
+ });
+ res.on("error", (error) => {
+ console.error("Stream error:", error);
+ });
+ })
+ .catch((error) => {
+ console.error("Failed to connect to audio stream:", error);
+ });📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service") | |
| .then((r) => r.body) | |
| .then((res) => { | |
| res.on("readable", () => { | |
| connection.send(res.read()); | |
| }); | |
| }); | |
| fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service") | |
| .then((r) => { | |
| if (!r.ok) { | |
| throw new Error(`HTTP error! status: ${r.status}`); | |
| } | |
| return r.body; | |
| }) | |
| .then((res) => { | |
| res.on("readable", () => { | |
| connection.send(res.read()); | |
| }); | |
| res.on("error", (error) => { | |
| console.error("Stream error:", error); | |
| }); | |
| }) | |
| .catch((error) => { | |
| console.error("Failed to connect to audio stream:", error); | |
| }); |
🤖 Prompt for AI Agents
In examples/node-live/index.js around lines 17 to 23, the fetch call and stream
processing lack error handling, risking unhandled promise rejections or runtime
errors if the BBC stream is unavailable. Add catch blocks to the fetch promise
chain to handle fetch errors, and add error event listeners on the stream object
to handle stream errors gracefully. Ensure any errors are logged or handled
appropriately to prevent the application from crashing.
| @@ -1,87 +1,34 @@ | |||
| /* eslint-env node */ | |||
| /* eslint-disable @typescript-eslint/no-var-requires, @typescript-eslint/no-require-imports, no-console */ | |||
There was a problem hiding this comment.
🧩 Verification correct
Fix ESLint configuration issues.
The static analysis indicates that TypeScript ESLint rules are not found, suggesting a configuration problem that could affect the development workflow.
Please verify the ESLint configuration includes the necessary TypeScript rules:
🏁 Script executed:
#!/bin/bash
# Description: Check ESLint configuration for TypeScript rules
echo "Checking ESLint configuration files..."
# Look for ESLint config files
fd -t f "\.(eslintrc|eslint\.config)\.(js|json|yml|yaml|mjs)$" .
fd -t f "\.eslintrc$" .
# Check package.json for ESLint config
cat package.json | jq '.eslintConfig // empty'
# Check if TypeScript ESLint packages are installed
cat package.json | jq '.devDependencies | keys[] | select(contains("typescript-eslint"))'Length of output: 383
Fix ESLint configuration issues.
The static analysis indicates that TypeScript ESLint rules are not found, suggesting a configuration problem that could affect the development workflow.
Please verify the ESLint configuration includes the necessary TypeScript rules:
#!/bin/bash
# Description: Check ESLint configuration for TypeScript rules
echo "Checking ESLint configuration files..."
# Look for ESLint config files
fd -t f "\.(eslintrc|eslint\.config)\.(js|json|yml|yaml|mjs)$" .
fd -t f "\.eslintrc$" .
# Check package.json for ESLint config
cat package.json | jq '.eslintConfig // empty'
# Check if TypeScript ESLint packages are installed
cat package.json | jq '.devDependencies | keys[] | select(contains("typescript-eslint"))'🧰 Tools
🪛 GitHub Check: Test / OS ubuntu-latest / Node 22
[failure] 2-2:
Definition for rule '@typescript-eslint/no-require-imports' was not found
[failure] 2-2:
Definition for rule '@typescript-eslint/no-var-requires' was not found
🤖 Prompt for AI Agents
In examples/node-live/index.js at line 2, the ESLint configuration is missing or
incorrectly set up for TypeScript ESLint rules, causing static analysis errors.
Verify that your ESLint config files (like .eslintrc.js, .eslintrc.json, or
eslint.config.js) include the TypeScript ESLint plugin and parser settings.
Also, ensure that the necessary TypeScript ESLint packages are installed as
devDependencies in package.json. Run the provided shell commands to locate
ESLint config files and confirm the presence of TypeScript ESLint packages, then
update the configuration and dependencies accordingly.
| connection.on(LiveTranscriptionEvents.Transcript, (data) => { | ||
| console.log(data.channel.alternatives[0].transcript); | ||
| }); | ||
|
|
||
| connection.on(LiveTranscriptionEvents.Close, () => { | ||
| console.log("Connection closed."); | ||
| }); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Move event listeners outside the Open event handler.
Event listeners for Transcript and Close events are registered inside the Open event handler, which could lead to unexpected behavior or multiple registrations if the connection reopens.
connection.on(LiveTranscriptionEvents.Open, () => {
console.log("Connection opened.");
fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service")
.then((r) => r.body)
.then((res) => {
res.on("readable", () => {
connection.send(res.read());
});
});
-
- connection.on(LiveTranscriptionEvents.Transcript, (data) => {
- console.log(data.channel.alternatives[0].transcript);
- });
-
- connection.on(LiveTranscriptionEvents.Close, () => {
- console.log("Connection closed.");
- });
});
+
+ connection.on(LiveTranscriptionEvents.Transcript, (data) => {
+ console.log(data.channel.alternatives[0].transcript);
+ });
+
+ connection.on(LiveTranscriptionEvents.Close, () => {
+ console.log("Connection closed.");
+ });📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| connection.on(LiveTranscriptionEvents.Transcript, (data) => { | |
| console.log(data.channel.alternatives[0].transcript); | |
| }); | |
| connection.on(LiveTranscriptionEvents.Close, () => { | |
| console.log("Connection closed."); | |
| }); | |
| connection.on(LiveTranscriptionEvents.Open, () => { | |
| console.log("Connection opened."); | |
| fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service") | |
| .then((r) => r.body) | |
| .then((res) => { | |
| res.on("readable", () => { | |
| connection.send(res.read()); | |
| }); | |
| }); | |
| }); | |
| connection.on(LiveTranscriptionEvents.Transcript, (data) => { | |
| console.log(data.channel.alternatives[0].transcript); | |
| }); | |
| connection.on(LiveTranscriptionEvents.Close, () => { | |
| console.log("Connection closed."); | |
| }); |
🤖 Prompt for AI Agents
In examples/node-live/index.js around lines 25 to 31, the event listeners for
LiveTranscriptionEvents.Transcript and LiveTranscriptionEvents.Close are
currently registered inside the Open event handler, which can cause multiple
registrations if the connection reopens. Move these event listener registrations
outside and before the Open event handler to ensure they are only registered
once and avoid unexpected behavior.
| const speak = async () => { | ||
| const deepgram = createClient(process.env.DEEPGRAM_API_KEY); | ||
|
|
||
| const dgConnection = deepgram.speak.live({ | ||
| model: "aura-2-thalia-en", | ||
| encoding: "linear16", | ||
| sample_rate: 48000, | ||
| const connection = deepgram.speak.live({ | ||
| model: "aura-asteria-en", | ||
| }); | ||
|
|
||
| let audioBuffer = Buffer.from(wavHeader); | ||
|
|
||
| dgConnection.on(LiveTTSEvents.Open, () => { | ||
| console.log("Connection opened"); | ||
|
|
||
| // Send text data for TTS synthesis | ||
| dgConnection.sendText(text); | ||
| const audioChunks = []; | ||
|
|
||
| // Send Flush message to the server after sending the text | ||
| dgConnection.flush(); | ||
|
|
||
| dgConnection.on(LiveTTSEvents.Close, () => { | ||
| console.log("Connection closed"); | ||
| }); | ||
|
|
||
| dgConnection.on(LiveTTSEvents.Metadata, (data) => { | ||
| console.dir(data, { depth: null }); | ||
| }); | ||
|
|
||
| dgConnection.on(LiveTTSEvents.Audio, (data) => { | ||
| console.log("Deepgram audio data received"); | ||
| // Concatenate the audio chunks into a single buffer | ||
| const buffer = Buffer.from(data); | ||
| audioBuffer = Buffer.concat([audioBuffer, buffer]); | ||
| }); | ||
|
|
||
| dgConnection.on(LiveTTSEvents.Flushed, () => { | ||
| console.log("Deepgram Flushed"); | ||
| // Write the buffered audio data to a file when the flush event is received | ||
| writeFile(); | ||
| }); | ||
| connection.on(LiveTTSEvents.Open, () => { | ||
| console.log("Connection opened."); | ||
| connection.sendText("Hello, world! This is a live text-to-speech test."); | ||
| connection.sendText("This is a second sentence."); | ||
| connection.finish(); | ||
| }); | ||
|
|
||
| dgConnection.on(LiveTTSEvents.Error, (err) => { | ||
| console.error(err); | ||
| }); | ||
| connection.on(LiveTTSEvents.Audio, (audio) => { | ||
| console.log("Received audio chunk."); | ||
| audioChunks.push(audio); | ||
| }); | ||
|
|
||
| const writeFile = () => { | ||
| if (audioBuffer.length > 0) { | ||
| fs.writeFile("output.wav", audioBuffer, (err) => { | ||
| if (err) { | ||
| console.error("Error writing audio file:", err); | ||
| } else { | ||
| console.log("Audio file saved as output.wav"); | ||
| } | ||
| }); | ||
| audioBuffer = Buffer.from(wavHeader); // Reset buffer after writing | ||
| } | ||
| }; | ||
| connection.on(LiveTTSEvents.Close, () => { | ||
| console.log("Connection closed."); | ||
| const buffer = Buffer.concat(audioChunks); | ||
| const filePath = resolve(__dirname, "output.mp3"); | ||
| writeFileSync(filePath, buffer); | ||
| console.log(`Audio file saved to ${filePath}`); | ||
| }); | ||
| }; | ||
|
|
||
| live(); | ||
| speak(); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add error handling for connection events.
The example lacks error handling for potential connection issues or TTS service errors, which could help users understand what went wrong.
Add an error event handler:
connection.on(LiveTTSEvents.Close, () => {
console.log("Connection closed.");
const buffer = Buffer.concat(audioChunks);
const filePath = resolve(__dirname, "output.mp3");
writeFileSync(filePath, buffer);
console.log(`Audio file saved to ${filePath}`);
});
+
+ connection.on(LiveTTSEvents.Error, (error) => {
+ console.error("Connection error:", error);
+ });📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| const speak = async () => { | |
| const deepgram = createClient(process.env.DEEPGRAM_API_KEY); | |
| const dgConnection = deepgram.speak.live({ | |
| model: "aura-2-thalia-en", | |
| encoding: "linear16", | |
| sample_rate: 48000, | |
| const connection = deepgram.speak.live({ | |
| model: "aura-asteria-en", | |
| }); | |
| let audioBuffer = Buffer.from(wavHeader); | |
| dgConnection.on(LiveTTSEvents.Open, () => { | |
| console.log("Connection opened"); | |
| // Send text data for TTS synthesis | |
| dgConnection.sendText(text); | |
| const audioChunks = []; | |
| // Send Flush message to the server after sending the text | |
| dgConnection.flush(); | |
| dgConnection.on(LiveTTSEvents.Close, () => { | |
| console.log("Connection closed"); | |
| }); | |
| dgConnection.on(LiveTTSEvents.Metadata, (data) => { | |
| console.dir(data, { depth: null }); | |
| }); | |
| dgConnection.on(LiveTTSEvents.Audio, (data) => { | |
| console.log("Deepgram audio data received"); | |
| // Concatenate the audio chunks into a single buffer | |
| const buffer = Buffer.from(data); | |
| audioBuffer = Buffer.concat([audioBuffer, buffer]); | |
| }); | |
| dgConnection.on(LiveTTSEvents.Flushed, () => { | |
| console.log("Deepgram Flushed"); | |
| // Write the buffered audio data to a file when the flush event is received | |
| writeFile(); | |
| }); | |
| connection.on(LiveTTSEvents.Open, () => { | |
| console.log("Connection opened."); | |
| connection.sendText("Hello, world! This is a live text-to-speech test."); | |
| connection.sendText("This is a second sentence."); | |
| connection.finish(); | |
| }); | |
| dgConnection.on(LiveTTSEvents.Error, (err) => { | |
| console.error(err); | |
| }); | |
| connection.on(LiveTTSEvents.Audio, (audio) => { | |
| console.log("Received audio chunk."); | |
| audioChunks.push(audio); | |
| }); | |
| const writeFile = () => { | |
| if (audioBuffer.length > 0) { | |
| fs.writeFile("output.wav", audioBuffer, (err) => { | |
| if (err) { | |
| console.error("Error writing audio file:", err); | |
| } else { | |
| console.log("Audio file saved as output.wav"); | |
| } | |
| }); | |
| audioBuffer = Buffer.from(wavHeader); // Reset buffer after writing | |
| } | |
| }; | |
| connection.on(LiveTTSEvents.Close, () => { | |
| console.log("Connection closed."); | |
| const buffer = Buffer.concat(audioChunks); | |
| const filePath = resolve(__dirname, "output.mp3"); | |
| writeFileSync(filePath, buffer); | |
| console.log(`Audio file saved to ${filePath}`); | |
| }); | |
| }; | |
| live(); | |
| speak(); | |
| const speak = async () => { | |
| const deepgram = createClient(process.env.DEEPGRAM_API_KEY); | |
| const connection = deepgram.speak.live({ | |
| model: "aura-asteria-en", | |
| }); | |
| const audioChunks = []; | |
| connection.on(LiveTTSEvents.Open, () => { | |
| console.log("Connection opened."); | |
| connection.sendText("Hello, world! This is a live text-to-speech test."); | |
| connection.sendText("This is a second sentence."); | |
| connection.finish(); | |
| }); | |
| connection.on(LiveTTSEvents.Audio, (audio) => { | |
| console.log("Received audio chunk."); | |
| audioChunks.push(audio); | |
| }); | |
| connection.on(LiveTTSEvents.Close, () => { | |
| console.log("Connection closed."); | |
| const buffer = Buffer.concat(audioChunks); | |
| const filePath = resolve(__dirname, "output.mp3"); | |
| writeFileSync(filePath, buffer); | |
| console.log(`Audio file saved to ${filePath}`); | |
| }); | |
| connection.on(LiveTTSEvents.Error, (error) => { | |
| console.error("Connection error:", error); | |
| }); | |
| }; | |
| speak(); |
🤖 Prompt for AI Agents
In examples/node-speak-live/index.js around lines 9 to 38, the code lacks error
handling for the live TTS connection events. Add an event listener for the error
event on the connection object to catch and log any errors that occur during the
connection or TTS process. This will help users understand and debug issues by
providing clear error messages.
| connection.on(LiveTTSEvents.Close, () => { | ||
| console.log("Connection closed."); | ||
| const buffer = Buffer.concat(audioChunks); | ||
| const filePath = resolve(__dirname, "output.mp3"); | ||
| writeFileSync(filePath, buffer); | ||
| console.log(`Audio file saved to ${filePath}`); | ||
| }); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Use asynchronous file operations to avoid blocking.
The synchronous writeFileSync operation could block the event loop, especially for larger audio files. Consider using the asynchronous version with proper error handling.
+ const { writeFile } = require("fs").promises;
connection.on(LiveTTSEvents.Close, () => {
console.log("Connection closed.");
const buffer = Buffer.concat(audioChunks);
const filePath = resolve(__dirname, "output.mp3");
- writeFileSync(filePath, buffer);
- console.log(`Audio file saved to ${filePath}`);
+ writeFile(filePath, buffer)
+ .then(() => {
+ console.log(`Audio file saved to ${filePath}`);
+ })
+ .catch((error) => {
+ console.error("Failed to save audio file:", error);
+ });
});📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| connection.on(LiveTTSEvents.Close, () => { | |
| console.log("Connection closed."); | |
| const buffer = Buffer.concat(audioChunks); | |
| const filePath = resolve(__dirname, "output.mp3"); | |
| writeFileSync(filePath, buffer); | |
| console.log(`Audio file saved to ${filePath}`); | |
| }); | |
| const { writeFile } = require("fs").promises; | |
| connection.on(LiveTTSEvents.Close, () => { | |
| console.log("Connection closed."); | |
| const buffer = Buffer.concat(audioChunks); | |
| const filePath = resolve(__dirname, "output.mp3"); | |
| writeFile(filePath, buffer) | |
| .then(() => { | |
| console.log(`Audio file saved to ${filePath}`); | |
| }) | |
| .catch((error) => { | |
| console.error("Failed to save audio file:", error); | |
| }); | |
| }); |
🤖 Prompt for AI Agents
In examples/node-speak-live/index.js around lines 29 to 35, replace the
synchronous writeFileSync call with the asynchronous writeFile function from the
fs module. Use async/await or a callback to handle the file writing operation
and include error handling to catch and log any errors during the file save
process, ensuring the event loop is not blocked.
| fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service") | ||
| .then((r) => r.body) | ||
| .then((res) => { | ||
| res.on("readable", () => { | ||
| console.log("Sending audio chunk"); | ||
| connection.send(res.read()); | ||
| }); | ||
| }); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add error handling for the audio stream fetch.
The fetch operation lacks proper error handling, which could cause unhandled promise rejections.
fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service")
.then((r) => r.body)
.then((res) => {
res.on("readable", () => {
connection.send(res.read());
});
- });
+ })
+ .catch((error) => {
+ console.error("Error fetching audio stream:", error);
+ });📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service") | |
| .then((r) => r.body) | |
| .then((res) => { | |
| res.on("readable", () => { | |
| console.log("Sending audio chunk"); | |
| connection.send(res.read()); | |
| }); | |
| }); | |
| fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service") | |
| .then((r) => r.body) | |
| .then((res) => { | |
| res.on("readable", () => { | |
| connection.send(res.read()); | |
| }); | |
| }) | |
| .catch((error) => { | |
| console.error("Error fetching audio stream:", error); | |
| }); |
🤖 Prompt for AI Agents
In examples/node-agent-live/index.js between lines 26 and 32, the fetch call for
the audio stream does not handle errors, risking unhandled promise rejections.
Add a .catch() block after the fetch promise chain to catch and handle any
errors that occur during the fetch or stream processing. This should log the
error or handle it appropriately to prevent the application from crashing.
| connection.on(AgentEvents.ConversationText, (data) => { | ||
| console.log(data.role, data.content); | ||
| }); | ||
|
|
||
| connection.on(AgentEvents.Unhandled, (data) => { | ||
| console.dir(data, { depth: null }); | ||
| connection.on(AgentEvents.Close, () => { | ||
| console.log("Connection closed."); | ||
| }); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Move event handlers outside the Open event to prevent multiple registrations.
Similar to the token example, event handlers are nested inside the Open event handler, which could lead to multiple registrations.
connection.on(AgentEvents.Open, () => {
console.log("Connection opened.");
connection.configure({
agent: {
listen: {
model: "nova-3",
},
speak: {
model: "aura-asteria-en",
},
},
});
fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service")
.then((r) => r.body)
.then((res) => {
res.on("readable", () => {
connection.send(res.read());
});
});
-
- connection.on(AgentEvents.ConversationText, (data) => {
- console.log(data.role, data.content);
- });
-
- connection.on(AgentEvents.Close, () => {
- console.log("Connection closed.");
- });
});
+
+ connection.on(AgentEvents.ConversationText, (data) => {
+ console.log(data.role, data.content);
+ });
+
+ connection.on(AgentEvents.Close, () => {
+ console.log("Connection closed.");
+ });📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| connection.on(AgentEvents.ConversationText, (data) => { | |
| console.log(data.role, data.content); | |
| }); | |
| connection.on(AgentEvents.Unhandled, (data) => { | |
| console.dir(data, { depth: null }); | |
| connection.on(AgentEvents.Close, () => { | |
| console.log("Connection closed."); | |
| }); | |
| connection.on(AgentEvents.Open, () => { | |
| console.log("Connection opened."); | |
| connection.configure({ | |
| agent: { | |
| listen: { | |
| model: "nova-3", | |
| }, | |
| speak: { | |
| model: "aura-asteria-en", | |
| }, | |
| }, | |
| }); | |
| fetch("http://stream.live.vc.bbcmedia.co.uk/bbc_world_service") | |
| .then((r) => r.body) | |
| .then((res) => { | |
| res.on("readable", () => { | |
| connection.send(res.read()); | |
| }); | |
| }); | |
| }); | |
| connection.on(AgentEvents.ConversationText, (data) => { | |
| console.log(data.role, data.content); | |
| }); | |
| connection.on(AgentEvents.Close, () => { | |
| console.log("Connection closed."); | |
| }); |
🤖 Prompt for AI Agents
In examples/node-agent-live/index.js around lines 34 to 40, the event handlers
for ConversationText and Close are currently inside the Open event handler,
causing multiple registrations on repeated opens. Move these event handler
registrations outside and before the Open event handler to ensure they are
registered only once and prevent duplicate event handling.
| vad_events: true, | ||
| // Time in milliseconds of silence to wait for before finalizing speech | ||
| endpointing: 300, | ||
| const deepgram = deepgram.createClient(apiKey); |
There was a problem hiding this comment.
Fix incorrect global object reference.
The code uses deepgram.createClient() but the global object from the UMD bundle is likely Deepgram (capitalized).
- const deepgram = deepgram.createClient(apiKey);
+ const deepgram = Deepgram.createClient(apiKey);📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| const deepgram = deepgram.createClient(apiKey); | |
| const deepgram = Deepgram.createClient(apiKey); |
🤖 Prompt for AI Agents
In examples/browser-live/index.html at line 31, the code incorrectly references
the global object as 'deepgram' with a lowercase 'd'. Change this to 'Deepgram'
with an uppercase 'D' to correctly use the global object from the UMD bundle
when calling createClient.
| const stream = await navigator.mediaDevices.getUserMedia({ audio: true }); | ||
| mediaRecorder = new MediaRecorder(stream); | ||
| mediaRecorder.ondataavailable = (event) => { | ||
| if (event.data.size > 0) { | ||
| connection.send(event.data); | ||
| } | ||
| }; | ||
| }; |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add error handling for getUserMedia.
The MediaRecorder setup lacks error handling for cases where microphone access is denied or unavailable.
- const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
- mediaRecorder = new MediaRecorder(stream);
- mediaRecorder.ondataavailable = (event) => {
- if (event.data.size > 0) {
- connection.send(event.data);
- }
- };
+ try {
+ const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
+ mediaRecorder = new MediaRecorder(stream);
+ mediaRecorder.ondataavailable = (event) => {
+ if (event.data.size > 0) {
+ connection.send(event.data);
+ }
+ };
+ } catch (error) {
+ console.error("Error accessing microphone:", error);
+ alert("Microphone access is required for live transcription.");
+ }📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| const stream = await navigator.mediaDevices.getUserMedia({ audio: true }); | |
| mediaRecorder = new MediaRecorder(stream); | |
| mediaRecorder.ondataavailable = (event) => { | |
| if (event.data.size > 0) { | |
| connection.send(event.data); | |
| } | |
| }; | |
| }; | |
| try { | |
| const stream = await navigator.mediaDevices.getUserMedia({ audio: true }); | |
| mediaRecorder = new MediaRecorder(stream); | |
| mediaRecorder.ondataavailable = (event) => { | |
| if (event.data.size > 0) { | |
| connection.send(event.data); | |
| } | |
| }; | |
| } catch (error) { | |
| console.error("Error accessing microphone:", error); | |
| alert("Microphone access is required for live transcription."); | |
| } | |
| }; |
🤖 Prompt for AI Agents
In examples/browser-live/index.html around lines 73 to 80, the code calls
getUserMedia without handling errors, which can cause issues if microphone
access is denied or unavailable. Wrap the getUserMedia call in a try-catch block
or use promise catch to handle errors gracefully. In the error handler, provide
user feedback or log the error to inform about the failure to access the
microphone.
| startButton.onclick = () => { | ||
| if (!connection) { | ||
| setup().then(() => { | ||
| mediaRecorder.start(1000); | ||
| }); | ||
| } else { | ||
| mediaRecorder.start(1000); | ||
| } | ||
| }; |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Prevent multiple setup calls and connection leaks.
The start button can call setup multiple times, potentially creating multiple connections and event handlers without proper cleanup.
startButton.onclick = () => {
- if (!connection) {
- setup().then(() => {
- mediaRecorder.start(1000);
- });
- } else {
- mediaRecorder.start(1000);
- }
+ if (!connection) {
+ setup().then(() => {
+ if (mediaRecorder) {
+ mediaRecorder.start(1000);
+ }
+ }).catch((error) => {
+ console.error("Setup failed:", error);
+ });
+ } else if (mediaRecorder && mediaRecorder.state === "inactive") {
+ mediaRecorder.start(1000);
+ }
};📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| startButton.onclick = () => { | |
| if (!connection) { | |
| setup().then(() => { | |
| mediaRecorder.start(1000); | |
| }); | |
| } else { | |
| mediaRecorder.start(1000); | |
| } | |
| }; | |
| startButton.onclick = () => { | |
| if (!connection) { | |
| setup().then(() => { | |
| if (mediaRecorder) { | |
| mediaRecorder.start(1000); | |
| } | |
| }).catch((error) => { | |
| console.error("Setup failed:", error); | |
| }); | |
| } else if (mediaRecorder && mediaRecorder.state === "inactive") { | |
| mediaRecorder.start(1000); | |
| } | |
| }; |
🤖 Prompt for AI Agents
In examples/browser-live/index.html around lines 82 to 90, the startButton
onclick handler calls setup multiple times if connection is not established,
which can create multiple connections and event handlers leading to leaks.
Modify the code to ensure setup is only called once by checking if a setup is
already in progress or completed before calling it again. Also, add proper
cleanup logic to close or reset existing connections and event handlers before
creating new ones to prevent leaks.
Summary by CodeRabbit
New Features
Bug Fixes
Documentation
Refactor
Chores
.gitignorefiles to example directories to exclude dependencies, environment files, and generated outputs.package.jsonfiles to example projects for dependency management.Tests