chore: rename api_key to hf_token (#6437)

* chore: rename api_key to hf_token

The param name changed in the past but these comments and error
messages are stale.

* add changeset

* demos

* notebooks

---------

Co-authored-by: gradio-pr-bot <gradio-pr-bot@users.noreply.github.com>
Co-authored-by: Abubakar Abid <abubakar@huggingface.co>

.changeset/violet-mammals-cut.md

@@ -0,0 +1,5 @@
+---
+"gradio": minor
+---
+
+feat:chore: rename api_key to hf_token

demo/autocomplete/run.ipynb

@@ -1 +1 @@
-{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: autocomplete\n", "### This text generation demo works like autocomplete. There's only one textbox and it's used for both the input and the output. The demo loads the model as an interface, and uses that interface as an API. It then uses blocks to create the UI. All of this is done in less than 10 lines of code.\n", "        "]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio "]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "import os\n", "\n", "# save your HF API token from https:/hf.co/settings/tokens as an env variable to avoid rate limiting\n", "auth_token = os.getenv(\"auth_token\")\n", "\n", "# load a model from https://hf.co/models as an interface, then use it as an api \n", "# you can remove the api_key parameter if you don't care about rate limiting. \n", "api = gr.load(\"huggingface/gpt2-xl\", hf_token=auth_token)\n", "\n", "def complete_with_gpt(text):\n", "    return text[:-50] + api(text[-50:])\n", "\n", "with gr.Blocks() as demo:\n", "    textbox = gr.Textbox(placeholder=\"Type here...\", lines=4)\n", "    btn = gr.Button(\"Autocomplete\")\n", "    \n", "    # define what will run when the button is clicked, here the textbox is used as both an input and an output\n", "    btn.click(fn=complete_with_gpt, inputs=textbox, outputs=textbox, queue=False)\n", "\n", "demo.launch()"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}
+{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: autocomplete\n", "### This text generation demo works like autocomplete. There's only one textbox and it's used for both the input and the output. The demo loads the model as an interface, and uses that interface as an API. It then uses blocks to create the UI. All of this is done in less than 10 lines of code.\n", "        "]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio "]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "import os\n", "\n", "# save your HF API token from https:/hf.co/settings/tokens as an env variable to avoid rate limiting\n", "hf_token = os.getenv(\"hf_token\")\n", "\n", "# load a model from https://hf.co/models as an interface, then use it as an api \n", "# you can remove the hf_token parameter if you don't care about rate limiting. \n", "api = gr.load(\"huggingface/gpt2-xl\", hf_token=hf_token)\n", "\n", "def complete_with_gpt(text):\n", "    return text[:-50] + api(text[-50:])\n", "\n", "with gr.Blocks() as demo:\n", "    textbox = gr.Textbox(placeholder=\"Type here...\", lines=4)\n", "    btn = gr.Button(\"Autocomplete\")\n", "    \n", "    # define what will run when the button is clicked, here the textbox is used as both an input and an output\n", "    btn.click(fn=complete_with_gpt, inputs=textbox, outputs=textbox, queue=False)\n", "\n", "demo.launch()"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}

demo/autocomplete/run.py

@@ -2,11 +2,11 @@ import gradio as gr
 import os
 
 # save your HF API token from https:/hf.co/settings/tokens as an env variable to avoid rate limiting
-auth_token = os.getenv("auth_token")
+hf_token = os.getenv("hf_token")
 
 # load a model from https://hf.co/models as an interface, then use it as an api 
-# you can remove the api_key parameter if you don't care about rate limiting. 
-api = gr.load("huggingface/gpt2-xl", hf_token=auth_token)
+# you can remove the hf_token parameter if you don't care about rate limiting. 
+api = gr.load("huggingface/gpt2-xl", hf_token=hf_token)
 
 def complete_with_gpt(text):
     return text[:-50] + api(text[-50:])

demo/automatic-speech-recognition/run.ipynb

@@ -1 +1 @@
-{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: automatic-speech-recognition\n", "### Automatic speech recognition English. Record from your microphone and the app will transcribe the audio.\n", "        "]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio "]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "import os\n", "\n", "# save your HF API token from https:/hf.co/settings/tokens as an env variable to avoid rate limiting\n", "auth_token = os.getenv(\"auth_token\")\n", "\n", "# automatically load the interface from a HF model \n", "# you can remove the api_key parameter if you don't care about rate limiting. \n", "demo = gr.load(\n", "    \"huggingface/facebook/wav2vec2-base-960h\",\n", "    title=\"Speech-to-text\",\n", "    inputs=\"mic\",\n", "    description=\"Let me try to guess what you're saying!\",\n", "    hf_token=auth_token\n", ")\n", "\n", "demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}
+{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: automatic-speech-recognition\n", "### Automatic speech recognition English. Record from your microphone and the app will transcribe the audio.\n", "        "]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio "]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "import os\n", "\n", "# save your HF API token from https:/hf.co/settings/tokens as an env variable to avoid rate limiting\n", "hf_token = os.getenv(\"hf_token\")\n", "\n", "# automatically load the interface from a HF model \n", "# you can remove the hf_token parameter if you don't care about rate limiting. \n", "demo = gr.load(\n", "    \"huggingface/facebook/wav2vec2-base-960h\",\n", "    title=\"Speech-to-text\",\n", "    inputs=\"mic\",\n", "    description=\"Let me try to guess what you're saying!\",\n", "    hf_token=hf_token\n", ")\n", "\n", "demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}

demo/automatic-speech-recognition/run.py

@@ -2,16 +2,16 @@ import gradio as gr
 import os
 
 # save your HF API token from https:/hf.co/settings/tokens as an env variable to avoid rate limiting
-auth_token = os.getenv("auth_token")
+hf_token = os.getenv("hf_token")
 
 # automatically load the interface from a HF model 
-# you can remove the api_key parameter if you don't care about rate limiting. 
+# you can remove the hf_token parameter if you don't care about rate limiting. 
 demo = gr.load(
     "huggingface/facebook/wav2vec2-base-960h",
     title="Speech-to-text",
     inputs="mic",
     description="Let me try to guess what you're saying!",
-    hf_token=auth_token
+    hf_token=hf_token
 )
 
 demo.launch()

gradio/external.py

@@ -93,7 +93,7 @@ def load_blocks_from_repo(
         name = "/".join(tokens[1:])
 
     factory_methods: dict[str, Callable] = {
-        # for each repo type, we have a method that returns the Interface given the model name & optionally an api_key
+        # for each repo type, we have a method that returns the Interface given the model name & optionally an hf_token
         "huggingface": from_model,
         "models": from_model,
         "spaces": from_spaces,
@@ -149,7 +149,7 @@ def from_model(model_name: str, hf_token: str | None, alias: str | None, **kwarg
     response = requests.request("GET", api_url, headers=headers)
     if response.status_code != 200:
         raise ModelNotFoundError(
-            f"Could not find model: {model_name}. If it is a private or gated model, please provide your Hugging Face access token (https://huggingface.co/settings/tokens) as the argument for the `api_key` parameter."
+            f"Could not find model: {model_name}. If it is a private or gated model, please provide your Hugging Face access token (https://huggingface.co/settings/tokens) as the argument for the `hf_token` parameter."
         )
     p = response.json().get("pipeline_tag")
     GRADIO_CACHE = os.environ.get("GRADIO_TEMP_DIR") or str(  # noqa: N806
@@ -494,7 +494,7 @@ def from_spaces(
 
     if iframe_url is None:
         raise ValueError(
-            f"Could not find Space: {space_name}. If it is a private or gated Space, please provide your Hugging Face access token (https://huggingface.co/settings/tokens) as the argument for the `api_key` parameter."
+            f"Could not find Space: {space_name}. If it is a private or gated Space, please provide your Hugging Face access token (https://huggingface.co/settings/tokens) as the argument for the `hf_token` parameter."
         )
 
     r = requests.get(iframe_url, headers=headers)