cmagganas commited on
Commit
31b5de7
β€’
1 Parent(s): 867c567

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +2 -8
  2. app.py +29 -0
  3. hf-space-upload.ipynb +32 -4
README.md CHANGED
@@ -1,8 +1,2 @@
1
- ---
2
- title: Kaleidoscope Data - LLM Data Cleaner
3
- emoji: 🧹
4
- sdk: streamlit
5
- sdk_version: 1.24.0
6
- app_file: app.py
7
- pinned: false
8
- ---
 
1
+ # llm-data-cleaner
2
+ Kaleidoscope Data - LLM Data Cleaner
 
 
 
 
 
 
app.py ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # this app is streamlit app for the current project hosted on huggingface spaces
2
+
3
+ import streamlit as st
4
+ from app.openai_chat_completion import OpenAIChatCompletions
5
+
6
+ st.title("Kaleidoscope Data - Data Cleaning LLM App")
7
+
8
+ 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.")
9
+
10
+ # text box or csv upload
11
+ text_input = st.text_input("Enter text", "Enter text here")
12
+ # csv_file = st.file_uploader("Upload CSV", type=['csv'])
13
+
14
+ # button to run data cleaning API on text via c class in openai_chat_completion.py
15
+ if st.button("Run Data Cleaning API"):
16
+
17
+ # if text_input is not empty, run data cleaning API on text_input
18
+
19
+ model = "gpt-4" # "gpt-3.5-turbo"
20
+ sys_mes = "prompts/gpt4-system-message.txt"
21
+
22
+ # instantiate OpenAIChatCompletions class
23
+ # get response from openai_chat_completion method
24
+ chat = OpenAIChatCompletions(model=model, system_message=sys_mes)
25
+ response = chat.openai_chat_completion(text_input, n_shot=5)
26
+
27
+ # display response
28
+ st.write(response)
29
+
hf-space-upload.ipynb CHANGED
@@ -2,16 +2,36 @@
2
  "cells": [
3
  {
4
  "cell_type": "code",
5
- "execution_count": null,
6
  "metadata": {},
7
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "source": [
9
  "from huggingface_hub import HfApi\n",
10
  "api = HfApi()\n",
11
  "\n",
12
  "api.upload_folder(\n",
13
- " folder_path=\"/path/to/local/space\",\n",
14
- " repo_id=\"username/my-cool-space\",\n",
15
  " repo_type=\"space\",\n",
16
  ")"
17
  ]
@@ -24,7 +44,15 @@
24
  "name": "python3"
25
  },
26
  "language_info": {
 
 
 
 
 
 
27
  "name": "python",
 
 
28
  "version": "3.10.11"
29
  },
30
  "orig_nbformat": 4
 
2
  "cells": [
3
  {
4
  "cell_type": "code",
5
+ "execution_count": 1,
6
  "metadata": {},
7
+ "outputs": [
8
+ {
9
+ "name": "stderr",
10
+ "output_type": "stream",
11
+ "text": [
12
+ "/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",
13
+ " from .autonotebook import tqdm as notebook_tqdm\n",
14
+ "run-rbtf91s6.wandb: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 7.96M/7.96M [00:16<00:00, 488kB/s] \n"
15
+ ]
16
+ },
17
+ {
18
+ "data": {
19
+ "text/plain": [
20
+ "'https://huggingface.co/spaces/kaleidoscope-data/data-cleaning-llm/tree/main/'"
21
+ ]
22
+ },
23
+ "execution_count": 1,
24
+ "metadata": {},
25
+ "output_type": "execute_result"
26
+ }
27
+ ],
28
  "source": [
29
  "from huggingface_hub import HfApi\n",
30
  "api = HfApi()\n",
31
  "\n",
32
  "api.upload_folder(\n",
33
+ " folder_path=\"\",\n",
34
+ " repo_id=\"kaleidoscope-data/data-cleaning-llm\",\n",
35
  " repo_type=\"space\",\n",
36
  ")"
37
  ]
 
44
  "name": "python3"
45
  },
46
  "language_info": {
47
+ "codemirror_mode": {
48
+ "name": "ipython",
49
+ "version": 3
50
+ },
51
+ "file_extension": ".py",
52
+ "mimetype": "text/x-python",
53
  "name": "python",
54
+ "nbconvert_exporter": "python",
55
+ "pygments_lexer": "ipython3",
56
  "version": "3.10.11"
57
  },
58
  "orig_nbformat": 4