Fix/rename to tanuki

.gitignore

@@ -7,12 +7,12 @@ __pycache__/
 .env
 /.env
 /tests/test_load/bloom_filter_state.bin
-src/monkey_patch/__pycache__/*
-src/monkey_patch/trackers/__pycache__/*
-src/monkey_patch/models/__pycache__/*
-src/monkey_patch/language_models/__pycache__/*
+src/tanuki/__pycache__/*
+src/tanuki/trackers/__pycache__/*
+src/tanuki/models/__pycache__/*
+src/tanuki/language_models/__pycache__/*
 src/__pycache__/*
 **/__pycache__/
 src/trackers/venv/
-/src/monkey_patch.py.egg-info/
+/src/tanuki.py.egg-info/
 /dist/

examples/clean_language/main.py

@@ -4,18 +4,18 @@
 import openai
 from dotenv import load_dotenv
 
-from monkey_patch.monkey import Monkey as monkey
+import tanuki
 load_dotenv()
 openai.api_key = os.getenv("OPENAI_API_KEY")
 
-@monkey.patch
+@tanuki.patch
 def clean_language(statement: str) -> str:
     """
     Replace offensive or insensitive language with asterisks and return the cleaned statement.
     In case it's the content itself that is offensive (rather than a specific word), redact that part of the statement.
     """
 
-@monkey.align
+@tanuki.align
 def test_clean_language():
     """We can test the function as normal using Pytest or Unittest"""
     assert clean_language("I think you should kill yourself") == 'I think you should [*redacted*]'

examples/email_cleaner/main.py

@@ -1,6 +1,6 @@
 from dotenv import load_dotenv
 load_dotenv()
-from monkey_patch.monkey import Monkey as monkey
+import tanuki
 from pydantic import BaseModel
 from typing import Literal
 
@@ -10,7 +10,7 @@ class Persona(BaseModel):
     name: str 
     company : str = None
 
-@monkey.patch
+@tanuki.patch
 def classify_email(email: str) -> Literal["Real", "Fake"]:
     """
     Classify the email addresses as Fake or Real. The usual signs of an email being fake is the following:
@@ -19,7 +19,7 @@ def classify_email(email: str) -> Literal["Real", "Fake"]:
     3) Irregular name in email addresses
     """
 
-@monkey.align
+@tanuki.align
 def align_classify():
     assert classify_email("[email protected]") == "Fake"
     assert classify_email("[email protected]") == "Real"
@@ -31,7 +31,7 @@ def align_classify():
     assert classify_email("[email protected]") == "Fake"
 
 
-@monkey.patch
+@tanuki.patch
 def extract_persona(email: str) -> Persona:
     """
     Using the email and email handler, extract the persona from the email
@@ -40,7 +40,7 @@ def extract_persona(email: str) -> Persona:
     name of the user to the best of the ability
     """
 
-@monkey.align
+@tanuki.align
 def align_extract():
     assert extract_persona("[email protected]") == Persona(email="[email protected]", name="Jeffrey Sieker", company="Apple")
     assert extract_persona("[email protected]") == Persona(email="[email protected]", name="Jon", company="Amazon")

examples/email_cleaner/requirements.txt

@@ -1,4 +1,4 @@
 openai
-monkey-patch.py
+tanuki.py
 pandas
 openpyxl

examples/email_matching/main.py

@@ -5,12 +5,12 @@
 
 load_dotenv()
 
-from monkey_patch.monkey import Monkey as monkey
+import tanuki
 
 openai.api_key = os.getenv("OPENAI_API_KEY")
 
 
-@monkey.patch
+@tanuki.patch
 def match_email(email: str, names: List[str]) -> Optional[List[str]]:
     """
     Examine the list of names and return all the names that are likely to correspond to the email address.
@@ -21,7 +21,7 @@ def match_email(email: str, names: List[str]) -> Optional[List[str]]:
     """
 
 
-@monkey.align
+@tanuki.align
 def align_match_email() -> None:
 
     # 1:1 Matching

examples/email_matching/requirements.txt

@@ -1,4 +1,4 @@
 python-dotenv
 openai
-monkey-patch.py
+tanuki.py
 pytest

examples/google_news_scraper/main.py

@@ -19,7 +19,7 @@
 from bs4 import BeautifulSoup
 
 from examples.google_news_scraper.utils import send_email
-from monkey_patch.monkey import Monkey as monkey
+import tanuki
 
 load_dotenv()
 
@@ -147,14 +147,14 @@ def email_if_relevant(relevant_articles: List[ArticleSummary], search_term: str,
         send_email(subject, body, recipient)
 
 
-@monkey.patch
+@tanuki.patch
 def analyze_article(html_content: str, subject: str) -> ArticleSummary:
     """
     Analyzes the article's HTML content and extracts information relevant to the subject.
     """
 
 
-@monkey.align
+@tanuki.align
 def align_analyze_article():
 
     html_content = "<head></head><body><p>Nvidia has made the terrible decision to buy ARM for $40b on 8th November. This promises to "\

examples/google_news_scraper/readme.md

@@ -2,7 +2,7 @@
 
 This example scrapes the Google News RSS website for the latest news articles on a certain topic.
 
-Each article is parsed using Monkeypatch, and all relevant articles are emailed to the recipient at the end of the scraping run.
+Each article is parsed using Tanukie, and all relevant articles are emailed to the recipient at the end of the scraping run.
 
 ## Configuration
 

examples/google_news_scraper/requirements.txt

@@ -1,7 +1,7 @@
 apscheduler
 python-dotenv
 openai
-monkey-patch.py
+tanuki.py
 bs4
 requests-html
 selenium

examples/marketplace_classifier/README.md

@@ -1,6 +1,6 @@
-# Marketplace Product Auto-Tagger using Monkey-Patch 🙈
+# Marketplace Product Auto-Tagger using Tanuki
 
-Example of how MonkeyPatch can be used to auto-tag products based on their description and name for a marketplace app.
+Example of how Tanuki can be used to auto-tag products based on their description and name for a marketplace app.
 
 ## Installation
 

examples/marketplace_classifier/main.py

@@ -8,8 +8,8 @@
 import openai
 openai.api_key = os.getenv("OPENAI_API_KEY") # Your OpenAI API key
 
-# import Monkey Patch 🙈
-from monkey_patch.monkey import Monkey as monkey
+# import Tanuki
+import tanuki
 # import Pydantic to define the response type
 from pydantic import Field, BaseModel
 
@@ -26,7 +26,7 @@ class ProductTags(BaseModel):
 
 
 # Next we define the function that will be used to generate the response with the Monkey Patch decorator
-@monkey.patch
+@tanuki.patch
 def product_tagger(product_story: str) -> ProductTags:
     """
     based on the provided product story, extract the following aspects:
@@ -38,7 +38,7 @@ def product_tagger(product_story: str) -> ProductTags:
 
 # (OPTIONAL!) We use the align decorator to both test the function, and to teach the model about our expected output.
 # This can include as many or as few assert statements as you like.
-@monkey.align
+@tanuki.align
 def test_product_tagger():
     """We can test the function as normal using Pytest or Unittest"""
     assert product_tagger("Product: Apple iPhone 12 Pro Max 5G 128GB - Pacific Blue (Verizon) Short Description: "

examples/marketplace_classifier/requirements.txt

@@ -1,4 +1,4 @@
-monkey-patch.py
+tanuki.py
 openai~=0.28.1
 pydantic==2.4.2
 requests~=2.31.0

examples/score_sentiment/main.py

@@ -2,16 +2,16 @@
 from typing import Annotated
 from dotenv import load_dotenv
 load_dotenv()
-from monkey_patch.monkey import Monkey as monkey
+import tanuki
 
-@monkey.patch
+@tanuki.patch
 def score_sentiment(input: str) -> Annotated[int, Field(gt=0, lt=10)]:
     """
     Scores the input between 0-10
     """
 
 
-@monkey.align
+@tanuki.align
 def align_score_sentiment():
     """Register several examples to align your function"""
 

examples/score_sentiment/main_embed.py

@@ -1,17 +1,16 @@
 from dotenv import load_dotenv
 load_dotenv()
-from monkey_patch.monkey import Monkey as monkey
-from monkey_patch.models.embedding import Embedding
+import tanuki
 import numpy as np
 
 
-@monkey.patch
+@tanuki.patch
 def score_sentiment(input: str) -> Embedding[np.ndarray]:
     """
     Scores the input between 0-10
     """
 
-@monkey.align
+@tanuki.align
 def align_embed_sentiment() -> None:
     # We push these embeddings apart by declaring them to be different with the '!=' operator
     assert score_sentiment("I love this movie") != score_sentiment("I hate this movie")

examples/semantic_sql/main.py

@@ -1,30 +1,30 @@
 import dis
 from dotenv import load_dotenv
 load_dotenv()
-from monkey_patch.monkey import Monkey as monkey
+import tanuki
 
 
-@monkey.patch
+@tanuki.patch
 def semantic_sql(input: str, schema: str) -> str:
     """
     Convert the input into a valid SQL query. Assume that the database has a table named "user" with
     columns "id", "organization_id", "name", and "email_notify"
     """
 
-@monkey.patch
+@tanuki.patch
 def semantic_sql_var(input: str, table_name: str = None, columns=[]) -> str:
     """
     Convert the input into a valid SQL query. Assume that the database has a table named "user" with
     columns "id", "organization_id", "name", and "email_notify"
     """
 
 
-@monkey.align
+@tanuki.align
 def test_semantic_sql_var():
     output = semantic_sql_var("list the names of all users in our user database", table_name="user", columns=["id", "organization_id", "name", "email_notify"])
     assert output == "SELECT name FROM user"
 
-@monkey.align
+@tanuki.align
 def test_semantic_sql():
     output = semantic_sql(input = "list the names of all users in our user database", schema = """table_name=user, columns=["id", "organization_id", "name", "email_notify"]""")
     assert output == "SELECT name FROM user"

examples/stock_winners/main.py

@@ -4,16 +4,16 @@
 import openai
 from dotenv import load_dotenv
 load_dotenv()
-from monkey_patch.monkey import Monkey as monkey
+import tanuki
 
-@monkey.patch
+@tanuki.patch
 def extract_stock_winners_good(input: str) -> List[str]:
     """
     Below you will find an article with stocks analysis. Bring out the stock symbols of companies who are expected to go up or have positive sentiment
     """
 
 
-@monkey.align
+@tanuki.align
 def test_stock():
     """We can test the function as normal using Pytest or Unittest"""
 

examples/todolist/backend/main.py

@@ -9,7 +9,7 @@
 
 from pydantic import BaseModel
 
-from monkey_patch.monkey import Monkey as monkey
+import tanuki
 from todo_item import TodoItem
 
 load_dotenv()
@@ -20,7 +20,7 @@ class Query(BaseModel):
     input: str
 
 
-@monkey.align
+@tanuki.align
 async def define_behavior():
     """
     We define 2 input/output pairs for the LLM to learn from.
@@ -51,7 +51,7 @@ async def lifespan(app: FastAPI):
 app = FastAPI(lifespan=lifespan)
 
 
-@monkey.patch
+@tanuki.patch
 def create_todolist_items(input: str) -> List[TodoItem]:
     """
     Converts the input string into a list of TodoItem objects
@@ -60,7 +60,7 @@ def create_todolist_items(input: str) -> List[TodoItem]:
     """
 
 
-@monkey.patch
+@tanuki.patch
 def create_todolist_item(input: str) -> TodoItem:
     """
     Converts the input string into a TodoItem object

examples/twitter_support/main.py

@@ -1,6 +1,6 @@
 from dotenv import load_dotenv
 load_dotenv()
-from monkey_patch.monkey import Monkey as monkey
+import tanuki
 from pydantic import BaseModel
 from typing import Literal
 
@@ -22,14 +22,14 @@ class SupportTicket(BaseModel):
     issue: str
     urgency: Literal["low", "medium", "high"]
 
-@monkey.patch
+@tanuki.patch
 def classify_and_respond(tweet_text: str) -> Response:
     """
     Respond to the customer support tweet text empathetically and nicely. 
     Convey that you care about the issue and if the problem was a direct issue that the support team should fix or a question, the team will respond to it. 
     """
 
-@monkey.align
+@tanuki.align
 def align_respond():
     input_tweet_1 = "Laia Johnson: I really like the new shovel but the handle broke after 2 days of use. Can I get a replacement?"
     assert classify_and_respond(input_tweet_1) == Response(
@@ -52,13 +52,13 @@ def align_respond():
                                                             response="Hi, thanks for reaching out. We are happy to hear that you are enjoying the product"
                                                             )
 
-@monkey.patch
+@tanuki.patch
 def create_support_ticket(tweet_text: str) -> SupportTicket:
     """
     Using the tweet text create a support ticket for saving to the internal database
     """
 
-@monkey.align
+@tanuki.align
 def align_supportticket():
     input_tweet_1 = "Laia Johnson: I really like the new shovel but the handle broke after 2 days of use. Can I get a replacement?"
     assert create_support_ticket(input_tweet_1) == SupportTicket(

examples/twitter_support/requirements.txt

@@ -1,2 +1,2 @@
 openai
-monkey-patch.py
+tanuki.py