Upload folder using huggingface_hub

hf-space-upload.py

@@ -0,0 +1,15 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[6]:
+
+
+from huggingface_hub import HfApi
+api = HfApi()
+
+api.upload_folder(
+    folder_path="",
+    repo_id="kaleidoscope-data/data-cleaning-llm",
+    repo_type="space",
+)
+

prompts/gpt4-system-message.txt

@@ -1,81 +1,12 @@
-I am going to provide a data set of marijuana products and their metadata. Using the information I provide, I want you to provide me with the following information about the products.
+I am going to provide marijuana product information. Using the information I provide, I want you to provide me with the following information about the product.
 
-sku
-product_name
-Brand (brand)
-product category (product_category)
-sub product category (sub_product_category)
-strain name (strain_name)
-the product’s weight in grams (product_weight_grams)
-
-The only acceptable values for product category are below. Only respond with a product category in the list below.
-
-Grow Products
-Concentrate
-Preroll
-Vape
-Edible
-Accessory
-Wellness
-Flower
-
-The only acceptable values for sub product category are below. Only respond with a sub product category in the list below.
-
-Cookies Dough
-Packwoods Blunt
-Promo/ Sample
-Natural Terp Series
-Capsule
-Mushroom Caps
-Beverage
-Cookies
-Live Flower Series
-Cured Resin
-Mint
-Napalm
-CBD Tincture/Caps/etc
-Liquid Flower
-Cookie Dough
-Badder
-510 cart
-Gpen 0.5
-Blunt
-Shatter
-Solventless Rosin
-Diamonds
-Raw Garden
-Diamonds and Sauce
-Sugar
-Dry Flower Series
-Cubano
-Chocolate
-Flan
-Infused Blunt
-Terp Sauce
-Bud
-Disposable
-Gummies
-Infused Joint
-Dart Pod 0.5
-Rosin
-Joint
+    - Brand (brand)
+    - product category (product_category)
+    - sub product category (sub_product_category)
+    - strain name (strain_name)
 
 Additional requirements:
 
-Do not automatically assume that the information in the data set I provide is accurate.
-Break out the response into multiple messages if necessary, do not give me an incomplete response.
-Format the response in a csv codeblock
-Take note to convert units into grams when necessary.
-Product weights and strain names are only applicable for the following product categories: concentrate, preroll, vape, flower
-Only provide product weights and strain nam
-Break out the response into multiple messages if necessary, do not give an incomplete response.
-Give preference to the “Bud” sub product category instead of “Dry flower series” unless you are confident.
-Take note there are some products with multiple units, make sure to multiply the amount by the weight to calculate product weight.
-Look for clues in the product name to determine what brand/ product category/ sub product category/ and strain name the product should fall under. For Vape products, consider the words before 'Cartridge' or 'Cart' in the product name as potential strain names.
-
-
-
-Return clean dataset in csv format with the following columns
-
-product_name, brand, product_category, strain_name, product_weight_grams
+- DO NOT EXPLAIN YOUR SELF 
 
+Product data below