# Conditionally translate reviews that are not english using Cortex Translate
reviews_df = reviews_df.withColumn('TRANSLATED_REVIEW',when(F.col('LANGUAGE') !=\
F.lit("en"), cortex.Translate(F.col('REVIEW'), F.col('LANGUAGE'), "en")) \
.otherwise(F.col('REVIEW')))

reviews_df.filter(F.col('LANGUAGE') != F.lit("en")) \
.select(["REVIEW","LANGUAGE","TRANSLATED_REVIEW"]).show(3)

# Prompt to get a rating based on a customer review
# We provide one shot incontext learning to better the answers we get from LLM
prompt = """[INST]
### 
You are tasked with rating cutsomer reviews for global food truck network called tasty bytes. \
Rating can be one of the following - awful, poor, okay, good, excellent such that awful is the worst \
possible rating and excellent is the best possible rating. Include only the rating in the output \
without any additional text. \
Rate the following review:
The "Freezing Point" ice cream truck in Seoul offered a mix of classic and unique \
options. The Sugar Cone and Waffle Cone were both fresh and crisp, providing a satisfying crunch. The \
Bottled Water and Ice Tea were standard, as expected. The standout, however, was the Mango Sticky Rice \
- a delightful blend of sweet and tangy, it was a refreshing twist to the usual ice cream flavors. The \
service was efficient, but lacked a personal touch. Overall, it\'s a decent choice for a quick, cool \
treat in the city.
Rating : good
Rate the following review: 
###"""

# Ask cortex complete and create a new column
review_df = reviews_df.withColumn('RATING', cortex.Complete('mixtral-8x7b', \
F.concat(F.lit(prompt), \
F.col('REVIEW'), \
F.lit("""[/INST]"""))))\
.withColumn('CLEAN_RATING', when(F.contains(F.lower(F.col('RATING')), F.lit('awful')), \
F.lit('awful')) \
.when(F.contains(F.lower(F.col('RATING')), F.lit('poor' )), \
F.lit('poor')) \
.when(F.contains(F.lower(F.col('RATING')), F.lit('okay')), \
F.lit('okay')) \
.when(F.contains(F.lower(F.col('RATING')), F.lit('good')), \
F.lit('good')) \
.when(F.contains(F.lower(F.col('RATING')), F.lit('excellent')), \
F.lit('excellent')) \
.otherwise(F.lit('unsure')))

review_df.select(["REVIEW","CLEAN_RATING"]).show(3)

# Understand the sentiment of customer review using Cortex Sentiment
reviews_df = reviews_df.withColumn('SENTIMENT', cortex.Sentiment(F.col('REVIEW')))

reviews_df.select(["REVIEW","SENTIMENT"]).show(3)

# Prompt to understand sentiment for different categories mentioned in the customer review
# We employ one shot incontext learning to inform LLM
prompt = """[INST]
### 
You are analyzing food-truck customer reviews to undertsand what a given review says about different relevant categories like \
food quality, menu options, staff, overall experience, price, ambience, customer support, \
hygiene standards etc and if sentiment is negative,positive or neutral for that category. \
Only answer in a single valid JSON containing "category", "sentiment" and "details". \
Make sure there is no additional text and not mention categories in answer which are not \
talked in the review. \
Get category based sentiment for the follwoing customer review:
"This food truck offers a disappointing experience. \
The menu lacks healthy options and the food quality is subpar. Finding a parking spot near the \
truck can also be a frustrating ordeal. Additionally, the value for money is not worth it. To top \
it all off, the service provided at this food truck is less than pleasant, adding to the overall \
negative dining experience. Tried reaching out the customer support but was unable to get through." 
Answer : [{ "category": "food quality", "sentiment": "negative", "details": "subpar quality" }, { "category": "menu options", "sentiment": "negative", "details": "lacks healthy options" }, { "category": "staff", "sentiment": "negative", "details": "unpleasant" }, { "category": "price", "sentiment": "negative", "details": "not worth the money" }, { "category": "experience", "sentiment": "negative", "details": "regrettable dining experience" }, { "category": "customer support", "sentiment": "negative", "details": "unable to get through" } ].
Get category based sentiment for the follwoing customer review:
###"""

# Ask Cortex Complete and create a new column
review_df = reviews_df.withColumn('CATEGORY_SENTIMENT', cortex.Complete('mixtral-8x7b', \
F.concat(F.lit(prompt), \
F.col('REVIEW'), \

F.lit("""Answer:[/INST]"""))))
review_df.select(["REVIEW","CATEGORY_SENTIMENT"]).show(2)