Upload folder using huggingface_hub

README.md

@@ -1,8 +1,2 @@
----
-title: Kaleidoscope Data - LLM Data Cleaner
-emoji: 🧹
-sdk: streamlit
-sdk_version: 1.24.0
-app_file: app.py
-pinned: false
----
+# llm-data-cleaner
+Kaleidoscope Data - LLM Data Cleaner

app.py

@@ -0,0 +1,29 @@
+# this app is streamlit app for the current project hosted on huggingface spaces
+
+import streamlit as st
+from app.openai_chat_completion import OpenAIChatCompletions
+
+st.title("Kaleidoscope Data - Data Cleaning LLM App")
+
+st.write("This app is a demo of the LLM model for data cleaning. It is a work in progress and is not yet ready for production use.")
+
+# text box or csv upload
+text_input = st.text_input("Enter text", "Enter text here")
+# csv_file = st.file_uploader("Upload CSV", type=['csv'])
+
+# button to run data cleaning API on text via c class in openai_chat_completion.py
+if st.button("Run Data Cleaning API"):
+    
+    # if text_input is not empty, run data cleaning API on text_input
+    
+    model = "gpt-4" # "gpt-3.5-turbo"
+    sys_mes = "prompts/gpt4-system-message.txt"
+    
+    # instantiate OpenAIChatCompletions class
+    # get response from openai_chat_completion method
+    chat = OpenAIChatCompletions(model=model, system_message=sys_mes)
+    response = chat.openai_chat_completion(text_input, n_shot=5)
+    
+    # display response
+    st.write(response)
+    

hf-space-upload.ipynb

@@ -2,16 +2,36 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/christos/opt/miniconda3/envs/kd-llm-dc/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "run-rbtf91s6.wandb: 100%|██████████| 7.96M/7.96M [00:16<00:00, 488kB/s] \n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'https://huggingface.co/spaces/kaleidoscope-data/data-cleaning-llm/tree/main/'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "from huggingface_hub import HfApi\n",
     "api = HfApi()\n",
     "\n",
     "api.upload_folder(\n",
-    "    folder_path=\"/path/to/local/space\",\n",
-    "    repo_id=\"username/my-cool-space\",\n",
+    "    folder_path=\"\",\n",
+    "    repo_id=\"kaleidoscope-data/data-cleaning-llm\",\n",
     "    repo_type=\"space\",\n",
     ")"
    ]
@@ -24,7 +44,15 @@
    "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"
   },
   "orig_nbformat": 4