New examples naming format (#479)

02_building_containers/screenshot.py

@@ -76,5 +76,5 @@ def main(url: str = "https://modal.com"):
     print(f"wrote {len(data)} bytes to {filename}")
 
 
-# And we're done! Please also see our [introductory guide](/docs/guide/web-scraper) for another
+# And we're done! Please also see our [introductory guide](/docs/examples/web-scraper) for another
 # example of a web scraper, with more in-depth logic.

06_gpu_and_ml/falcon_bitsandbytes.py

@@ -11,7 +11,7 @@
 # to the sheer size of the model, the cold start time on Modal is around 2 minutes.
 #
 # For faster cold start at the expense of inference speed, check out
-# [Running Falcon-40B with AutoGPTQ](/docs/guide/ex/falcon_gptq).
+# [Running Falcon-40B with AutoGPTQ](/docs/examples/falcon_gptq).
 #
 # ## Setup
 #

06_gpu_and_ml/falcon_gptq.py

@@ -8,8 +8,8 @@
 # cold start time on Modal is around 25s.
 #
 # For faster inference at the expense of a slower cold start, check out
-# [Running Falcon-40B with `bitsandbytes` quantization](/docs/guide/ex/falcon_bitsandbytes). You can also
-# run a smaller, 7-billion-parameter model with the [OpenLLaMa example](/docs/guide/ex/openllama).
+# [Running Falcon-40B with `bitsandbytes` quantization](/docs/examples/falcon_bitsandbytes). You can also
+# run a smaller, 7-billion-parameter model with the [OpenLLaMa example](/docs/examples/openllama).
 #
 # ## Setup
 #

06_gpu_and_ml/llm-frontend/index.html

@@ -15,7 +15,7 @@
     <section x-data="state()" class="max-w-2xl mx-auto pt-16 px-4">
       <div class="text-xs font-semibold tracking-wide uppercase text-center text-white">
         <a
-          href="https://modal.com/docs/guide/ex/text_generation_inference"
+          href="https://modal.com/docs/examples/text_generation_inference"
           class="inline-flex gap-x-1 items-center bg-lime-400 py-0.5 px-3 rounded-full hover:text-lime-400 hover:ring hover:ring-lime-400 hover:bg-white focus:outline-neutral-400"
           target="_blank"
         >

06_gpu_and_ml/openllama.py

@@ -141,6 +141,6 @@ def main():
 # you could use OpenLLaMa to perform a more useful downstream task.
 #
 # If you're looking for useful responses out-of-the-box like ChatGPT, you could try Vicuna-13B, which is larger and has been instruction-tuned.
-# However, note that this model is not permissively licensed due to the dataset it was trained on. Refer to our [LLM voice chat](/docs/guide/llm-voice-chat)
+# However, note that this model is not permissively licensed due to the dataset it was trained on. Refer to our [LLM voice chat](/docs/examples/llm-voice-chat)
 # post for how to build a complete voice chat app using Vicuna, or go straight to the [file](https://github.com/modal-labs/quillman/blob/main/src/llm_vicuna.py)
 # if you want to run it by itself.

06_gpu_and_ml/stable_diffusion/stable_diffusion_aitemplate.py

@@ -6,7 +6,7 @@
 # Example by [@maxscheel](https://github.com/maxscheel)
 #
 # This example shows the Stable Diffusion 2.1 compiled with [AITemplate](https://github.com/facebookincubator/AITemplate) to run faster on Modal.
-# There is also a [Stable Diffusion CLI example](/docs/guide/ex/stable_diffusion_cli).
+# There is also a [Stable Diffusion CLI example](/docs/examples/stable_diffusion_cli).
 #
 # #### Upsides
 #  - Image generation improves over the CLI example to about 550ms per image generated (A10G, 10 steps, 512x512, png).

06_gpu_and_ml/stable_diffusion/stable_diffusion_cli.py

@@ -9,14 +9,14 @@
 # that makes it run faster on Modal. The example takes about 10s to cold start
 # and about 1.0s per image generated.
 #
-# To use the new XL 1.0 model, see the example posted [here](/docs/guide/ex/stable_diffusion_xl).
+# To use the new XL 1.0 model, see the example posted [here](/docs/examples/stable_diffusion_xl).
 #
 # For instance, here are 9 images produced by the prompt
 # `An 1600s oil painting of the New York City skyline`
 #
 # ![stable diffusion slackbot](./stable_diffusion_montage.png)
 #
-# There is also a [Stable Diffusion Slack bot example](/docs/guide/ex/stable_diffusion_slackbot)
+# There is also a [Stable Diffusion Slack bot example](/docs/examples/stable_diffusion_slackbot)
 # which does not have all the optimizations, but shows how you can set up a Slack command to
 # trigger Stable Diffusion.
 #

06_gpu_and_ml/stable_diffusion/stable_diffusion_onnx.py

@@ -1,6 +1,6 @@
 # # Stable Diffusion with ONNX Runtime
 #
-# This example is similar to the [Stable Diffusion CLI](/docs/guide/ex/stable_diffusion_cli)
+# This example is similar to the [Stable Diffusion CLI](/docs/examples/stable_diffusion_cli)
 # example, but it runs inference unsing [ONNX Runtime](https://onnxruntime.ai/) instead of PyTorch.
 
 

06_gpu_and_ml/stable_diffusion/stable_diffusion_xl.py

@@ -5,7 +5,7 @@
 # ---
 # # Stable Diffusion XL 1.0
 #
-# This example is similar to the [Stable Diffusion CLI](/docs/guide/ex/stable_diffusion_cli)
+# This example is similar to the [Stable Diffusion CLI](/docs/examples/stable_diffusion_cli)
 # example, but it generates images from the larger XL 1.0 model. Specifically, it runs the
 # first set of steps with the base model, followed by the refiner model.
 #

09_job_queues/doc_ocr_jobs.py

@@ -6,7 +6,7 @@
 #
 # This tutorial shows you how to use Modal as an infinitely scalable job queue
 # that can service async tasks from a web app. For the purpose of this tutorial,
-# we've also built a [React + FastAPI web app on Modal](/docs/guide/ex/doc_ocr_webapp)
+# we've also built a [React + FastAPI web app on Modal](/docs/examples/doc_ocr_webapp)
 # that works together with it, but note that you don't need a web app running on Modal
 # to use this pattern. You can submit async tasks to Modal from any Python
 # application (for example, a regular Django app running on Kubernetes).
@@ -117,7 +117,7 @@ def parse_receipt(image: bytes):
 #
 # Modal will auto-scale to handle all the tasks queued, and
 # then scale back down to 0 when there's no work left. To see how you could use this from a Python web
-# app, take a look at the [receipt parser frontend](/docs/guide/ex/doc_ocr_webapp)
+# app, take a look at the [receipt parser frontend](/docs/examples/doc_ocr_webapp)
 # tutorial.
 
 # ## Run manually

09_job_queues/doc_ocr_webapp.py

@@ -9,7 +9,7 @@
 # [React](https://reactjs.org/) + [FastAPI](https://fastapi.tiangolo.com/) application.
 # We're going to build a simple "Receipt Parser" web app that submits OCR transcription
 # tasks to a separate Modal app defined in the [Job Queue
-# tutorial](/docs/guide/ex/doc_ocr_jobs), polls until the task is completed, and displays
+# tutorial](/docs/examples/doc_ocr_jobs), polls until the task is completed, and displays
 # the results. Try it out for yourself
 # [here](https://modal-labs-example-doc-ocr-webapp-wrapper.modal.run/).
 #
@@ -38,7 +38,7 @@
 # and another to poll for the results of the job.
 #
 # In `parse`, we're going to submit tasks to the function defined in the [Job
-# Queue tutorial](/docs/guide/ex/doc_ocr_jobs), so we import it first using
+# Queue tutorial](/docs/examples/doc_ocr_jobs), so we import it first using
 # [`Function.lookup`](/docs/reference/modal.Function#lookup).
 #
 # We call [`.spawn()`](/docs/reference/modal.Function#spawn) on the function handle

11_notebooks/basic.ipynb

@@ -17,7 +17,8 @@
    "outputs": [],
    "source": [
     "import modal\n",
-    "assert modal.__version__ > '0.49.0'"
+    "\n",
+    "assert modal.__version__ > \"0.49.0\""
    ]
   },
   {
@@ -50,6 +51,7 @@
     "def double(x: int) -> int:\n",
     "    return x + x\n",
     "\n",
+    "\n",
     "double(5)"
    ]
   },
@@ -79,13 +81,15 @@
     "def double_with_modal(x: int) -> int:\n",
     "    return x + x\n",
     "\n",
+    "\n",
     "@stub.function()\n",
     "def quadruple(x: int) -> int:\n",
     "    if x <= 1_000_000:\n",
     "        return double(x) + double(x)\n",
     "    else:\n",
     "        return double_with_modal.remote(x) + double_with_modal.remote(x)\n",
     "\n",
+    "\n",
     "with stub.run():\n",
     "    print(quadruple(100))\n",
     "    print(quadruple.remote(100))  # run remotely\n",