Fix auth

app.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -18,10 +18,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
+    "# |export\n",
     "if Path(\".env\").is_file():\n",
     "    load_dotenv(\".env\")\n",
     "\n",
@@ -30,7 +31,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -42,7 +43,7 @@
     "    top_p\n",
     "):\n",
     "    API_URL = f\"https://api-inference.huggingface.co/models/{model_id}\"\n",
-    "    headers = {\"Authorization\": \"Bearer \", \"x-wait-for-model\": \"1\"}\n",
+    "    headers = {\"Authorization\": f\"Bearer {HF_TOKEN}\", \"x-wait-for-model\": \"1\"}\n",
     "\n",
     "    payload = {\n",
     "        \"inputs\": inputs,\n",
@@ -64,16 +65,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[{'generated_text': 'YES'}]"
+       "[{'generated_text': 'love'}]"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -86,7 +87,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -100,7 +101,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -129,6 +130,14 @@
     "    return {chatbot: chat, state: history}\n"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Prompt templates"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 6,
@@ -644,9 +653,17 @@
     "    json.dump({\"prompt\": template}, f)"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## App"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -678,14 +695,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Running on local URL:  http://127.0.0.1:7871\n",
+      "Running on local URL:  http://127.0.0.1:7860\n",
       "\n",
       "To create a public link, set `share=True` in `launch()`.\n"
      ]
@@ -693,7 +710,7 @@
     {
      "data": {
       "text/html": [
-       "<div><iframe src=\"http://127.0.0.1:7871/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -706,25 +723,9 @@
      "data": {
       "text/plain": []
      },
-     "execution_count": 36,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Traceback (most recent call last):\n",
-      "  File \"/Users/lewtun/miniconda3/envs/hf/lib/python3.8/site-packages/gradio/routes.py\", line 337, in run_predict\n",
-      "    output = await app.get_blocks().process_api(\n",
-      "  File \"/Users/lewtun/miniconda3/envs/hf/lib/python3.8/site-packages/gradio/blocks.py\", line 1018, in process_api\n",
-      "    data = self.postprocess_data(fn_index, result[\"prediction\"], state)\n",
-      "  File \"/Users/lewtun/miniconda3/envs/hf/lib/python3.8/site-packages/gradio/blocks.py\", line 924, in postprocess_data\n",
-      "    predictions = convert_component_dict_to_list(\n",
-      "  File \"/Users/lewtun/miniconda3/envs/hf/lib/python3.8/site-packages/gradio/blocks.py\", line 397, in convert_component_dict_to_list\n",
-      "    raise ValueError(\n",
-      "ValueError: Returned component chatbot not specified as output of function.\n"
-     ]
     }
    ],
    "source": [
@@ -761,9 +762,9 @@
     "                interactive=True,\n",
     "            )\n",
     "            temperature = gr.Slider(\n",
-    "                minimum=0.5,\n",
+    "                minimum=0.0,\n",
     "                maximum=3.0,\n",
-    "                value=1.0,\n",
+    "                value=0.5,\n",
     "                step=0.1,\n",
     "                interactive=True,\n",
     "                label=\"Temperature\",\n",
@@ -772,7 +773,7 @@
     "            top_p = gr.Slider(\n",
     "                minimum=-0,\n",
     "                maximum=1.0,\n",
-    "                value=0.8,\n",
+    "                value=0.9,\n",
     "                step=0.05,\n",
     "                interactive=True,\n",
     "                label=\"Top-p (nucleus sampling)\",\n",
@@ -828,14 +829,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 193,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Closing server running on port: 7905\n"
+      "Closing server running on port: 7860\n"
      ]
     }
    ],
@@ -845,7 +846,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [

app.py

@@ -1,7 +1,7 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: app.ipynb.
 
 # %% auto 0
-__all__ = ['title', 'description', 'query_chat_api', 'inference_chat']
+__all__ = ['HF_TOKEN', 'title', 'description', 'query_chat_api', 'inference_chat']
 
 # %% app.ipynb 0
 import gradio as gr
@@ -13,6 +13,13 @@ from pathlib import Path
 from dotenv import load_dotenv
 
 
+# %% app.ipynb 1
+if Path(".env").is_file():
+    load_dotenv(".env")
+
+HF_TOKEN = os.getenv("HF_TOKEN")
+
+
 # %% app.ipynb 2
 def query_chat_api(
     model_id,
@@ -21,7 +28,7 @@ def query_chat_api(
     top_p
 ):
     API_URL = f"https://api-inference.huggingface.co/models/{model_id}"
-    headers = {"Authorization": "Bearer ", "x-wait-for-model": "1"}
+    headers = {"Authorization": f"Bearer {HF_TOKEN}", "x-wait-for-model": "1"}
 
     payload = {
         "inputs": inputs,
@@ -66,7 +73,7 @@ def inference_chat(
     return {chatbot: chat, state: history}
 
 
-# %% app.ipynb 13
+# %% app.ipynb 15
 title = """<h1 align="center">Chatty Language Models</h1>"""
 description = """Language models can be conditioned to act like dialogue agents through a conversational prompt that typically takes the form:
 
@@ -91,7 +98,7 @@ So far, the following prompts are available:
 As you can see, most of these prompts exceed the maximum context size of models like Flan-T5, so an error usually means the Inference API has timed out.
 """
 
-# %% app.ipynb 14
+# %% app.ipynb 16
 with gr.Blocks(
     css="""
     .message.svelte-w6rprc.svelte-w6rprc.svelte-w6rprc {font-size: 20px; margin-top: 20px}
@@ -124,9 +131,9 @@ with gr.Blocks(
                 interactive=True,
             )
             temperature = gr.Slider(
-                minimum=0.5,
+                minimum=0.0,
                 maximum=3.0,
-                value=1.0,
+                value=0.5,
                 step=0.1,
                 interactive=True,
                 label="Temperature",
@@ -135,7 +142,7 @@ with gr.Blocks(
             top_p = gr.Slider(
                 minimum=-0,
                 maximum=1.0,
-                value=0.8,
+                value=0.9,
                 step=0.05,
                 interactive=True,
                 label="Top-p (nucleus sampling)",