Merge pull request #36 from ajcwebdev/docs

Ollama Docker Support

.env.example

@@ -4,6 +4,8 @@ GEMINI_API_KEY=""
 COHERE_API_KEY=""
 MISTRAL_API_KEY=""
 OCTOAI_API_KEY=""
+TOGETHER_API_KEY=""
+FIREWORKS_API_KEY=""
 
 DEEPGRAM_API_KEY=""
 ASSEMBLY_API_KEY=""

docker-compose.yml

@@ -11,10 +11,9 @@ services:
       - /var/run/docker.sock:/var/run/docker.sock
     depends_on:
       - whisper
-    #   - ollama
-    # environment:
-    #   - OLLAMA_HOST=ollama
-    #   - OLLAMA_PORT=11434
+      - ollama
+    environment:
+      - OLLAMA_HOST=ollama
     networks:
       - autoshownet
   whisper:
@@ -29,20 +28,16 @@ services:
     stdin_open: true
     networks:
       - autoshownet
-  # ollama:
-  #   image: ollama/ollama
-  #   command: ["ollama", "serve", "--address", "0.0.0.0"]  # Listen on all interfaces
-  #   ports:
-  #     - "11434:11434"
-  #   volumes:
-  #     - ./ollama:/root/.ollama
-  #   healthcheck:
-  #     test: ["CMD", "curl", "-f", "http://localhost:11434/healthz"]
-  #     interval: 10s
-  #     timeout: 5s
-  #     retries: 5
-  #   networks:
-  #     - autoshownet
+  ollama:
+    image: ollama/ollama
+    volumes:
+      - ollama:/root/.ollama
+    environment:
+      - OLLAMA_HOST=0.0.0.0
+    networks:
+      - autoshownet
 networks:
   autoshownet:
-    driver: bridge
+    driver: bridge
+volumes:
+  ollama:

docs/examples.md

@@ -281,6 +281,22 @@ npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --together Q
 npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --together QWEN_2_5_7B
 ```
 
+### Groq
+
+```bash
+npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --groq
+```
+
+Select Groq model:
+
+```bash
+npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --groq LLAMA_3_1_70B_VERSATILE
+npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --groq LLAMA_3_1_8B_INSTANT
+npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --groq LLAMA_3_2_1B_PREVIEW
+npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --groq LLAMA_3_2_3B_PREVIEW
+npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --groq MIXTRAL_8X7B_32768
+```
+
 ### Llama.cpp
 
 ```bash
@@ -334,6 +350,9 @@ npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --whisper me
 
 # large-v2 model
 npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --whisper large-v2
+
+# large-v3-turbo model
+npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --whisper large-v3-turbo
 ```
 
 Run `whisper.cpp` in a Docker container with `--whisperDocker`:
@@ -342,6 +361,22 @@ Run `whisper.cpp` in a Docker container with `--whisperDocker`:
 npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --whisperDocker base
 ```
 
+### Whisper Python
+
+Use the original [`openai/whisper`](https://github.com/openai/whisper) Python library with the newly released [`turbo`](https://github.com/openai/whisper/discussions/2363) model:
+
+```bash
+npm run as -- --file "content/audio.mp3" --whisperPython turbo
+```
+
+### Whisper Diarization
+
+Use [`whisper-diarization`](https://github.com/MahmoudAshraf97/whisper-diarization) to provide speaker labels:
+
+```bash
+npm run as -- --file "content/audio.mp3" --whisperDiarization tiny
+```
+
 ### Deepgram
 
 Create a `.env` file and set API key as demonstrated in `.env.example` for `DEEPGRAM_API_KEY`.
@@ -424,25 +459,29 @@ npm run as -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --prompt tit
 
 ### Docker Compose
 
-This will start both `whisper.cpp` and the AutoShow Commander CLI in their own Docker containers.
+This will start `whisper.cpp`, Ollama, and the AutoShow Commander CLI in their own Docker containers.
 
 ```bash
 npm run docker-up
 ```
 
-Replace `as` with `docker` to run most other commands explained in this document.
+Replace `as` with `docker` to run most other commands explained in this document. Does not support all options at this time, notably `--llama`, `--whisperPython`, and `--whisperDiarization`.
+
+```bash
+npm run docker -- --video "https://www.youtube.com/watch?v=MORMZXEaONk"
+npm run docker -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --whisperDocker tiny
+```
 
-- Does not support all commands at this time, notably `--llama` and `--ollama`.
-- Currently working on the `llama.cpp` Docker integration so the entire project can be encapsulated in one local Docker Compose file.
+Currently supports Ollama's official Docker image so the entire project can be encapsulated in one local Docker Compose file:
 
 ```bash
-npm run docker -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --whisperDocker base
+npm run docker -- --video "https://www.youtube.com/watch?v=MORMZXEaONk" --whisperDocker tiny --ollama
 ```
 
 To reset your Docker images and containers, run:
 
 ```bash
-docker system prune -af --volumes
+npm run prune
 ```
 
 ### Bun

package.json

@@ -19,11 +19,13 @@
   },
   "scripts": {
     "setup": "bash ./scripts/setup.sh",
+    "setup-python": "bash ./scripts/setup-python.sh",
     "autoshow": "tsx --env-file=.env --no-warnings src/autoshow.ts",
     "as": "tsx --env-file=.env --no-warnings src/autoshow.ts",
-    "docker": "docker compose run --remove-orphans autoshow",
+    "docker": "docker compose run --remove-orphans --rm autoshow --whisperDocker",
     "docker-up": "docker compose up --build -d --remove-orphans --no-start",
     "ds": "docker compose images && docker compose ls",
+    "prune": "docker system prune -af --volumes && docker image prune -af && docker container prune -f && docker volume prune -af",
     "v": "tsx --env-file=.env --no-warnings src/autoshow.ts --whisper large-v2 --video",
     "u": "tsx --env-file=.env --no-warnings src/autoshow.ts --whisper large-v2 --urls",
     "p": "tsx --env-file=.env --no-warnings src/autoshow.ts --whisper large-v2 --playlist",
@@ -34,8 +36,9 @@
     "fetch-local": "tsx --env-file=.env --no-warnings packages/server/tests/fetch-local.ts",
     "fetch-all": "tsx --env-file=.env --no-warnings packages/server/tests/fetch-all.ts",
     "t": "npm run test-local",
-    "test-local": "tsx --test test/local.test.js",
-    "test-all": "tsx --test test/all.test.js",
+    "test-local": "tsx --test test/local.test.ts",
+    "test-docker": "tsx --test test/docker.test.ts",
+    "test-integrations": "tsx --test test/integrations.test.ts",
     "clean": "tsx scripts/cleanContent.ts",
     "bun-as": "bun --env-file=.env --no-warnings src/autoshow.ts",
     "deno-as": "deno run --allow-sys --allow-read --allow-run --allow-write --allow-env src/autoshow.ts"
@@ -53,7 +56,6 @@
     "commander": "12.1.0",
     "fast-xml-parser": "4.5.0",
     "fastify": "5.0.0",
-    "ffmpeg-static": "5.2.0",
     "file-type": "19.5.0",
     "inquirer": "12.0.0",
     "node-llama-cpp": "3.1.1",
@@ -64,6 +66,7 @@
     "@types/inquirer": "9.0.7",
     "@types/node": "22.7.5",
     "tsx": "4.19.1",
+    "typedoc": "^0.26.10",
     "typescript": "5.6.3"
   }
 }

scripts/setup-python.sh

@@ -1,14 +1,33 @@
 #!/bin/bash
 
-# Clone the repository
-git clone https://github.com/MahmoudAshraf97/whisper-diarization.git
+# scripts/setup-python.sh
 
-# Create and activate virtual environment
-python3.12 -m venv whisper-diarization/venv
-source whisper-diarization/venv/bin/activate
+# Clone the repository if it doesn't exist
+if [ ! -d "whisper-diarization" ]; then
+  echo "Cloning the whisper-diarization repository..."
+  git clone https://github.com/MahmoudAshraf97/whisper-diarization.git
+else
+  echo "whisper-diarization repository already exists. Skipping clone."
+fi
 
-# Install the requirements
-pip install -c whisper-diarization/constraints.txt -r whisper-diarization/requirements.txt
+# Create the virtual environment if it doesn't exist
+if [ ! -f "whisper-diarization/venv/bin/activate" ]; then
+  echo "Creating virtual environment..."
+  python3.12 -m venv whisper-diarization/venv
+else
+  echo "Virtual environment already exists. Skipping creation."
+fi
+
+# Install requirements if not already installed
+if [ ! -f "whisper-diarization/.requirements_installed" ]; then
+  echo "Installing requirements..."
+  source whisper-diarization/venv/bin/activate
+  pip install -c whisper-diarization/constraints.txt -r whisper-diarization/requirements.txt
+  deactivate
+  touch whisper-diarization/.requirements_installed
+else
+  echo "Requirements already installed. Skipping installation."
+fi
 
 echo "Setup complete. To activate this environment in the future, run:"
 echo "source whisper-diarization/venv/bin/activate"

src/autoshow.ts

@@ -8,8 +8,7 @@
  * Automate processing of audio and video content from various sources.
  * Supports processing YouTube videos, playlists, local files, and podcast RSS feeds.
  *
- * Documentation: https://github.com/ajcwebdev/autoshow#readme
- * Report Issues: https://github.com/ajcwebdev/autoshow/issues
+ * @packageDocumentation
  */
 
 import { Command } from 'commander'
@@ -26,7 +25,9 @@ import type { ProcessingOptions, HandlerFunction, LLMServices, TranscriptService
 // Initialize the command-line interface
 const program = new Command()
 
-// Define command-line options and their descriptions
+/**
+ * Defines the command-line interface options and descriptions.
+ */
 program
   .name('autoshow')
   .version('0.0.1')
@@ -57,6 +58,7 @@ program
   .option('--octo [model]', 'Use Octo for processing')
   .option('--fireworks [model]', 'Use Fireworks AI for processing with optional model specification')
   .option('--together [model]', 'Use Together AI for processing with optional model specification')
+  .option('--groq [model]', 'Use Groq for processing with optional model specification')
   .option('--llama [model]', 'Use Node Llama for processing with optional model specification')
   .option('--ollama [model]', 'Use Ollama for processing with optional model specification')
   .option('--gemini [model]', 'Use Gemini for processing with optional model specification')
@@ -78,12 +80,16 @@ Report Issues: https://github.com/ajcwebdev/autoshow/issues
 
 /**
  * Helper function to validate that only one option from a list is provided.
- * @param {string[]} optionKeys - The list of option keys to check.
- * @param {ProcessingOptions} options - The options object.
- * @param {string} errorMessage - The prefix of the error message.
- * @returns {string | undefined} - The selected option or undefined.
+ * @param optionKeys - The list of option keys to check.
+ * @param options - The options object.
+ * @param errorMessage - The prefix of the error message.
+ * @returns The selected option or undefined.
  */
-function getSingleOption(optionKeys: string[], options: ProcessingOptions, errorMessage: string): string | undefined {
+function getSingleOption(
+  optionKeys: string[],
+  options: ProcessingOptions,
+  errorMessage: string
+): string | undefined {
   const selectedOptions = optionKeys.filter((opt) => options[opt as keyof ProcessingOptions])
   if (selectedOptions.length > 1) {
     console.error(`Error: Multiple ${errorMessage} provided (${selectedOptions.join(', ')}). Please specify only one.`)
@@ -94,8 +100,7 @@ function getSingleOption(optionKeys: string[], options: ProcessingOptions, error
 
 /**
  * Main action for the program.
- * @param {ProcessingOptions} options - The command-line options provided by the user.
- * @returns {Promise<void>}
+ * @param options - The command-line options provided by the user.
  */
 program.action(async (options: ProcessingOptions) => {
   log(opts(`Options received at beginning of command:\n`))