Refactor

app.ipynb

@@ -10,7 +10,22 @@
     "import gradio as gr\n",
     "import requests\n",
     "import json\n",
-    "import requests"
+    "import requests\n",
+    "import os\n",
+    "from pathlib import Path\n",
+    "from dotenv import load_dotenv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if Path(\".env\").is_file():\n",
+    "    load_dotenv(\".env\")\n",
+    "\n",
+    "HF_TOKEN = os.getenv(\"HF_TOKEN\")\n"
    ]
   },
   {
@@ -27,7 +42,7 @@
     "    top_p\n",
     "):\n",
     "    API_URL = f\"https://api-inference.huggingface.co/models/{model_id}\"\n",
-    "    headers = {\"Authorization\": \"Bearer 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\", \"x-wait-for-model\": \"1\"}\n",
+    "    headers = {\"Authorization\": \"Bearer \", \"x-wait-for-model\": \"1\"}\n",
     "\n",
     "    payload = {\n",
     "        \"inputs\": inputs,\n",
@@ -830,7 +845,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 38,
    "metadata": {},
    "outputs": [],
    "source": [

app.py

@@ -8,8 +8,12 @@ import gradio as gr
 import requests
 import json
 import requests
+import os
+from pathlib import Path
+from dotenv import load_dotenv
 
-# %% app.ipynb 1
+
+# %% app.ipynb 2
 def query_chat_api(
     model_id,
     inputs,
@@ -17,7 +21,7 @@ def query_chat_api(
     top_p
 ):
     API_URL = f"https://api-inference.huggingface.co/models/{model_id}"
-    headers = {"Authorization": "Bearer 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", "x-wait-for-model": "1"}
+    headers = {"Authorization": "Bearer ", "x-wait-for-model": "1"}
 
     payload = {
         "inputs": inputs,
@@ -37,7 +41,7 @@ def query_chat_api(
         return "Error: " + response.text
 
 
-# %% app.ipynb 4
+# %% app.ipynb 5
 def inference_chat(
     model_id,
     prompt_template,
@@ -62,7 +66,7 @@ def inference_chat(
     return {chatbot: chat, state: history}
 
 
-# %% app.ipynb 12
+# %% app.ipynb 13
 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:
 
@@ -87,7 +91,7 @@ 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 13
+# %% app.ipynb 14
 with gr.Blocks(
     css="""
     .message.svelte-w6rprc.svelte-w6rprc.svelte-w6rprc {font-size: 20px; margin-top: 20px}

requirements.txt

@@ -1 +1,2 @@
 requests
+python-dotenv