From dd4d9be8c089873ff3fa1748d6292e8cdc0a6af5 Mon Sep 17 00:00:00 2001 From: Daniel Glogowski Date: Fri, 3 Jan 2025 13:09:45 -0800 Subject: [PATCH] notebook updates --- launchable/PDFtoPodcast.ipynb | 70 +++++++++++++++++++---------------- 1 file changed, 39 insertions(+), 31 deletions(-) diff --git a/launchable/PDFtoPodcast.ipynb b/launchable/PDFtoPodcast.ipynb index 76bd41c..2dd56b1 100644 --- a/launchable/PDFtoPodcast.ipynb +++ b/launchable/PDFtoPodcast.ipynb @@ -40,7 +40,7 @@ "#### Observability & Monitoring\n", "- **Jaeger Tracing 🔍** - experience full distributed tracing built in. Watch requests flow through different services and quickly identify bottlenecks in your processing pipeline as you add your own code\n", "- **MinIO Object Storage 📦** - robust, S3-compatible storage for handling PDFs and generated audio content. Perfect for scaling from development to production workloads.\n", - "- **GPU Optimized PDF processing 🔥** - choose between docling or NV-Ingest for lighting fast optimized PDF processing\n", + "- **GPU Optimized PDF processing 🔥** - use docling for lighting fast optimized PDF processing\n", "\n", "#### Development Experience\n", "- **UV Package Management 🚀** - Lightning-fast dependency management using UV, making environment setup a breeze with `make uv`\n", @@ -271,63 +271,71 @@ ] }, { - "cell_type": "markdown", - "id": "30f0d682-b20b-4dca-b966-db6605d9dadf", + "cell_type": "code", + "execution_count": 1, + "id": "48cf647f-0f0b-45e2-959b-d96b013169a5", "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "CONTAINER ID NAMES STATUS\n" + ] + } + ], "source": [ - "You can check if the services are up by running the cells below" + "!docker ps --format \"table {{{{.ID}}}}\\t{{{{.Names}}}}\\t{{{{.Status}}}}\"" ] }, { - "cell_type": "code", - "execution_count": null, - "id": "ae45f128-fe7e-4f9d-99bb-b23f8fbc4b52", + "cell_type": "markdown", + "id": "7d90c358-f0e9-4607-8b88-32a44ffce74e", "metadata": {}, - "outputs": [], "source": [ - "!curl localhost:8002/health" + "This command should produce similiar output in the following format:\n", + "\n", + "```\n", + "CONTAINER ID NAMES STATUS\n", + "ae5db10fcf7c pdf-to-podcast-pdf-api-1 Up About a minute\n", + "fbc8d417e85c pdf-to-podcast-api-service-1 Up About a minute\n", + "b34b5d64ad4c pdf-to-podcast-celery-worker-1 Up About a minute\n", + "6050545be1e4 pdf-to-podcast-pdf-service-1 Up About a minute\n", + "c8cc9253e8a9 pdf-to-podcast-tts-service-1 Up About a minute\n", + "5d29deb76eda pdf-to-podcast-agent-service-1 Up About a minute\n", + "1dfc6c61cec9 pdf-to-podcast-minio-1 Up About a minute (healthy)\n", + "aa967d41a513 pdf-to-podcast-redis-1 Up About a minute\n", + "eb881c33cc64 pdf-to-podcast-jaeger-1 Up About a minute (healthy)\n", + "```" ] }, { "cell_type": "markdown", - "id": "284c9bc5-6b6b-471a-b122-f029b20b2fdb", + "id": "30f0d682-b20b-4dca-b966-db6605d9dadf", "metadata": {}, "source": [ - "You should get something like \n", - "\n", - "```\n", - "{\"status\":\"healthy\",\"redis\":\"up\",\"services\":{\"pdf\":\"up\",\"agent\":\"up\",\"tts\":\"up\"},\"timestamp\":1733295689.5784104}\n", - "```" + "You can check if the services are up by running the cells below" ] }, { "cell_type": "code", "execution_count": null, - "id": "48cf647f-0f0b-45e2-959b-d96b013169a5", + "id": "ae45f128-fe7e-4f9d-99bb-b23f8fbc4b52", "metadata": {}, "outputs": [], "source": [ - "!docker ps --format \"table {{{{.ID}}}}\\t{{{{.Names}}}}\\t{{{{.Status}}}}\"" + "!curl localhost:8002/health" ] }, { "cell_type": "markdown", - "id": "7d90c358-f0e9-4607-8b88-32a44ffce74e", + "id": "284c9bc5-6b6b-471a-b122-f029b20b2fdb", "metadata": {}, "source": [ - "This command should produce similiar output in the following format:\n", + "You should get something like \n", "\n", "```\n", - "CONTAINER ID NAMES STATUS\n", - "ae5db10fcf7c pdf-to-podcast-pdf-api-1 Up About a minute\n", - "fbc8d417e85c pdf-to-podcast-api-service-1 Up About a minute\n", - "b34b5d64ad4c pdf-to-podcast-celery-worker-1 Up About a minute\n", - "6050545be1e4 pdf-to-podcast-pdf-service-1 Up About a minute\n", - "c8cc9253e8a9 pdf-to-podcast-tts-service-1 Up About a minute\n", - "5d29deb76eda pdf-to-podcast-agent-service-1 Up About a minute\n", - "1dfc6c61cec9 pdf-to-podcast-minio-1 Up About a minute (healthy)\n", - "aa967d41a513 pdf-to-podcast-redis-1 Up About a minute\n", - "eb881c33cc64 pdf-to-podcast-jaeger-1 Up About a minute (healthy)\n", + "{\"status\":\"healthy\",\"redis\":\"up\",\"services\":{\"pdf\":\"up\",\"agent\":\"up\",\"tts\":\"up\"},\"timestamp\":1733295689.5784104}\n", "```" ] }, @@ -336,7 +344,7 @@ "id": "425ebd50", "metadata": {}, "source": [ - "Note: If you are running this as a Brev launchable, you can access the the API endpoint, Jaeger UI, and the MinIO Object Storage UI by going to your running launchable on Brev, clicking `Access`, and clicking the links in the `Deployments` section. It should look like the following: " + "Note: If you are running this as a launchable, you can access the the API endpoint, Jaeger UI, and the MinIO Object Storage UI by going to your running launchable on Brev, clicking `Access`, and clicking the links in the `Deployments` section. It should look like the following: " ] }, { @@ -695,7 +703,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.13.1" + "version": "3.10.13" } }, "nbformat": 4,