styling

.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

.ipynb_checkpoints/app-checkpoint.py

@@ -11,27 +11,16 @@ import os, random
 from pathlib import Path
 import tiktoken
 from getpass import getpass
-from rich.markdown import Markdown
 
 import openai
-import wandb
-from pprint import pprint
-from wandb.integration.openai import autolog
 from langchain.text_splitter import MarkdownHeaderTextSplitter
 import numpy as np
 
 from langchain.embeddings import OpenAIEmbeddings
-from langchain.vectorstores import Chroma
+# from langchain.vectorstores import Chroma
 
 
 
-from tenacity import (
-    retry,
-    stop_after_attempt,
-    wait_random_exponential, # for exponential backoff
-)  
-
-
 
 
 if os.getenv("OPENAI_API_KEY") is None:
@@ -43,10 +32,27 @@ if os.getenv("OPENAI_API_KEY") is None:
 assert os.getenv("OPENAI_API_KEY", "").startswith("sk-"), "This doesn't look like a valid OpenAI API key"
 print("OpenAI API key configured")
 
+embeddings_model = OpenAIEmbeddings()
+
+md = ""
+directory_path = "safety_docs"
 
+for filename in os.listdir(directory_path):
+    if filename.endswith(".md"):
+        with open(os.path.join(directory_path, filename), 'r') as file:
+            content = file.read()
+            md = md + content
 
+markdown_document = md
 
+headers_to_split_on = [
+    ("#", "Header 1"),
+    ("##", "Header 2"),
+    ("###", "Header 3"),
+]
 
+markdown_splitter = MarkdownHeaderTextSplitter(headers_to_split_on=headers_to_split_on)
+md_header_splits = markdown_splitter.split_text(markdown_document)
 
 def find_nearest_neighbor(argument="", max_args_in_output=3):
     '''
@@ -56,28 +62,7 @@ def find_nearest_neighbor(argument="", max_args_in_output=3):
         RETURN the nearest neighbor(s) in vectorDB to argument as string
     '''
 
-    md = ""
-    print(argument)
-    directory_path = "../../safety_docs"
-
-    for filename in os.listdir(directory_path):
-        if filename.endswith(".md"):
-            with open(os.path.join(directory_path, filename), 'r') as file:
-                content = file.read()
-                md = md + content
-
-    markdown_document = md
-
-    headers_to_split_on = [
-        ("#", "Header 1"),
-        ("##", "Header 2"),
-        ("###", "Header 3"),
-    ]
-
-    markdown_splitter = MarkdownHeaderTextSplitter(headers_to_split_on=headers_to_split_on)
-    md_header_splits = markdown_splitter.split_text(markdown_document)
-
-    embeddings = OpenAIEmbeddings()
+    embeddings = embeddings_model
     embedding_matrix = np.array([embeddings.embed_query(text.page_content) for text in md_header_splits])
     argument_embedding = embeddings.embed_query(argument)
 
@@ -94,7 +79,7 @@ def find_nearest_neighbor(argument="", max_args_in_output=3):
 
     return output
 
-def get_gpt_response(argument, user_prompt, system_prompt=default_config.system_prompt, model=default_config.model_name, n=1, max_tokens=200):
+def get_gpt_response(user_prompt, system_prompt=default_config.system_prompt, model=default_config.model_name, n=1, max_tokens=200):
     '''
     INPUT: 
     Argument
@@ -103,55 +88,56 @@ def get_gpt_response(argument, user_prompt, system_prompt=default_config.system_
     model
     '''
 
-    @retry(wait=wait_random_exponential(min=1, max=3), stop=stop_after_attempt(1))
-    def completion_with_backoff(**kwargs):
-        return openai.ChatCompletion.create(**kwargs)
-    
     messages=[
-            {"role": "system", "content": system_prompt},
-            {"role": "user", "content": user_prompt},
-        ]
-    responses = completion_with_backoff(
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_prompt},
+            ]
+    response = openai.ChatCompletion.create(
         model=model,
         messages=messages,
-        n = n,
+        n=n,
         max_tokens=max_tokens
-        )
-    for response in responses.choices:
-        generation = response.message.content
-        return generation
+    )
     
 
-def greet(argument):
-    nearest_neighbor = find_nearest_neighbor(argument)
+    for choice in response.choices:
+        generation = choice.message.content
+        return generation
+
+    
+# return the gpt generated response
+def greet1(argument):
     user_prompt = default_config.user_prompt_1 + argument + default_config.user_prompt_2
-    # response = get_gpt_response(argument, user_prompt)
-    response = "chatbot response here"
-    # return "Hello " + "\n We think your argument matches common arguments in our database, is it one of these?:\n " + nearest_neighbor + "\n\n\n ------------------------- \n\n\n Lengthy response: \n" + response
-    return "english", "german"
+    response = get_gpt_response(user_prompt=user_prompt)
+    return response
 
-# demo = gr.Interface(
-#     fn=greet,
-#     inputs=gr.Textbox(lines=2, placeholder="Anything past 200 tokens (roughly 200 words) will be cutoff. Please enter <=1 paragraph"),
-#     outputs="text"
-# )
+# return the nearest neighbor arguments
+def greet2(argument):
+    nearest_neighbor = find_nearest_neighbor(argument)
+    return "Your argument may fall under the common arguments against AI safety. \n Is it one of these? \n " + nearest_neighbor + "\n See the taxonomy of arguments below"
 
-# # demo.queue(max_size=20)
-# demo.launch()
 
 
-with gr.Blocks() as demo:
+css = """
+body{background-color:red !important}
+"""
+with gr.Blocks(css=css) as demo:
     with gr.Row():
         with gr.Column():
-            seed = gr.Text(label="Input Phrase")
-            english = gr.Text(label="Generated English Text")
+            seed = gr.Text(label="Explanation / argument for how ASI development will go well")
+            english = gr.Text(label="Predicted Argument")
 
         with gr.Column():
-            german = gr.Text(label="Generated German Text",lines=4)
+            german = gr.Text(label="AI Generated Response")
     btn = gr.Button("Generate")
-    btn.click(greet, inputs=[seed], outputs=[english, german])
-    gr.Examples(["AGI is far away", "AI is confined to a computer and cannot interact with the physical world", "AI isn't concious"], inputs=[seed])
+    btn.click(greet2, inputs=[seed],outputs=english)
+    btn.click(greet1, inputs=[seed],outputs=german)
+
+
+    gr.Examples(["AGI is far away", "AI is confined to a computer and cannot interact with the physical world", "AI isn't concious", "If we don't develop AGI, China will!", "If we don't develop AGI, the Americans will!"], inputs=[seed])
+
 
+demo.queue()
 demo.launch()
 
 

.ipynb_checkpoints/themebuilder-checkpoint.py

@@ -0,0 +1,3 @@
+import gradio as gr
+
+gr.themes.builder()

Untitled.ipynb

@@ -0,0 +1,187 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ac22dd5d-c6b5-4c7a-a7de-67c4c3c5f04b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7861\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7861/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import gradio as gr\n",
+    "\n",
+    "gr.themes.builder(server_port=7861)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b4c3c6c4-f9f9-477c-af90-9e078e6b3de1",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d7ea55b9-91d8-486a-9f51-2c927ca98331",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d4283b3a-07db-4b9e-a45a-383e4523a1de",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "c9abfe47-b72e-4205-9dc6-ba63a775adf5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\u001b[0;31mInit signature:\u001b[0m\n",
+       "\u001b[0mgr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mthemes\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mColor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mc50\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mc100\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mc200\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mc300\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mc400\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mc500\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mc600\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mc700\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mc800\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mc900\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mc950\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mname\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+       "\u001b[0;31mDocstring:\u001b[0m      <no docstring>\n",
+       "\u001b[0;31mSource:\u001b[0m        \n",
+       "\u001b[0;32mclass\u001b[0m \u001b[0mColor\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0mall\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mc50\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mc100\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mc200\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mc300\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mc400\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mc500\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mc600\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mc700\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mc800\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mc900\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mc950\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mname\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m \u001b[0;34m|\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc50\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mc50\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc100\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mc100\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc200\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mc200\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc300\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mc300\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc400\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mc400\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc500\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mc500\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc600\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mc600\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc700\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mc700\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc800\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mc800\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc900\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mc900\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc950\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mc950\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mname\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0mColor\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mall\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mexpand\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc50\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc100\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc200\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc300\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc400\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc500\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc600\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc700\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc800\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc900\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc950\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+       "\u001b[0;34m\u001b[0m        \u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+       "\u001b[0;31mFile:\u001b[0m           ~/anaconda3/lib/python3.10/site-packages/gradio/themes/utils/colors.py\n",
+       "\u001b[0;31mType:\u001b[0m           type\n",
+       "\u001b[0;31mSubclasses:\u001b[0m     "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "??gr.themes.monochrome\n",
+    "??gr.themes.Color"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c6411099-03cd-4bfa-88a7-e0fda5cd6366",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "z"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

app.py

@@ -18,7 +18,10 @@ import numpy as np
 
 from langchain.embeddings import OpenAIEmbeddings
 # from langchain.vectorstores import Chroma
-
+from typing import Iterable
+from gradio.themes.base import Base
+from gradio.themes.utils import colors, fonts, sizes
+import time
 
 
 
@@ -54,7 +57,7 @@ headers_to_split_on = [
 markdown_splitter = MarkdownHeaderTextSplitter(headers_to_split_on=headers_to_split_on)
 md_header_splits = markdown_splitter.split_text(markdown_document)
 
-def find_nearest_neighbor(argument="", max_args_in_output=3):
+def find_nearest_neighbor(argument="", max_args_in_output=2):
     '''
         INPUT:
             argument (string)
@@ -114,23 +117,81 @@ def greet1(argument):
 # return the nearest neighbor arguments
 def greet2(argument):
     nearest_neighbor = find_nearest_neighbor(argument)
-    return "Your argument may fall under the common arguments against AI safety. \n Is it one of these? \n " + nearest_neighbor + "\n See the taxonomy of arguments below"
-
-
-with gr.Blocks(gr.themes.Soft()) as demo:
-    with gr.Row():
-        with gr.Column():
-            seed = gr.Text(label="Explanation / argument for how ASI development will go well")
-            english = gr.Text(label="Predicted Argument")
+    return "Your argument may fall under the common arguments against AI safety. \nIs it one of these? \n" + nearest_neighbor + "\nSee the taxonomy of arguments below"
+
+
+
+
+# theme = gr.themes.Monochrome()
+theme = gr.themes.Monochrome(
+    # neutral_hue=gr.themes.colors.red,
+
+    #                           n,     boxes,   text,       nothing                      bottom text            most text
+    neutral_hue=gr.themes.Color("red", "#636363", "#636363", "lightgrey", "lightgrey", "lightgrey", "lightgrey", "grey",        "red", "#636363",       "red"),
+    primary_hue=gr.themes.Color("#8c0010", "#8c0010", "#8c0010", "#8c0010", "#8c0010", "#8c0010", "#8c0010", "#8c0010", "#8c0010", "#8c0010", "#8c0010"),
+    secondary_hue=gr.themes.Color("white", "white", "white", "white", "white", "white", "white", "white", "white", "white", "white"),
+)
+
+
+theme = theme.set(
+    body_background_fill="black",
+    block_title_background_fill="black",
+    block_background_fill="black",
+    body_text_color="white",
+    link_text_color='*primary_50',
+    link_text_color_dark='*primary_50',
+    link_text_color_active='*primary_50',
+    link_text_color_active_dark='*primary_50',
+    link_text_color_hover='*primary_50',
+    link_text_color_hover_dark='*primary_50',
+    link_text_color_visited='*primary_50',
+    link_text_color_visited_dark='*primary_50'
+)
+
+css_string = """
+@import url('https://fonts.googleapis.com/css2?family=Gabarito&family=Gothic+A1:wght@100;200;300;400;500;600;700;800;900&display=swap');
+# .gradio-container *{
+#     background-color: black !important;
+#     color: white !important;
+#     font-family: 'Gabarito', cursive !important;
+# }
+
+
+# .block > *{
+#     background: black !important;
+#     color: white !important;
+# }
+
+
+force_black_bg {
+    background-color: blue !important;
+    color: white !important;
+    font-family: 'Gabarito', cursive !important;
+}
+force_black_bg *{
+    background-color: blue !important;
+    color: white !important;
+    font-family: 'Gabarito', cursive !important;
+}
+
+"""
+css_string2 = ""
+
+with gr.Blocks(theme=theme, css=css_string2) as demo:
+    with gr.Row(elem_id="force_black_bg"):
+        with gr.Column(elem_id="force_black_bg"):
+            seed = gr.Text( label="AI Safety Skepticism: What's Your Take?", placeholder="Enter an argument or something you'd like to say!")
+            # make a version of english with placeholder text
+            english = gr.Text(elem_id="themed_question_box", label="Common Argument Classifier")
 
         with gr.Column():
-            german = gr.Text(label="AI Generated Response")
+            german = gr.Text(label="Safetybot Response")
     btn = gr.Button("Generate")
     btn.click(greet2, inputs=[seed],outputs=english)
     btn.click(greet1, inputs=[seed],outputs=german)
 
 
-    gr.Examples(["AGI is far away", "AI is confined to a computer and cannot interact with the physical world", "AI isn't concious", "If we don't develop AGI, China will!", "If we don't develop AGI, the Americans will!"], inputs=[seed])
+    gr.Examples(["AGI is far away, I'm not worried", "AI is confined to a computer and cannot interact with the physical world", "AI isn't concious", "If we don't develop AGI, China will!", "If we don't develop AGI, the Americans will!"], inputs=[seed])
 
 
 demo.queue()

fe/index.html

@@ -0,0 +1,21 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Document</title>
+</head>
+
+<style>
+    body{
+        background-color: aqua;
+    }
+</style>
+<body>
+    <iframe src="https://sevdeawesome-safetybot.hf.space"
+	frameborder="0"
+	width="850"
+	height="450"></iframe>
+
+</body>
+</html>

index.css

@@ -0,0 +1,3 @@
+body{
+    background: blue;
+}

themebuilder.py

@@ -0,0 +1,3 @@
+import gradio as gr
+
+gr.themes.builder()