updated the rest of the core and examples to use pydantic and added doc strings

Author: createreadupdate

examples/binary_classify_list_example.py

@@ -1,13 +1,18 @@
 import asyncio
-from core.binary_classify_list_agent import BinaryClassifyListAgent
+from core.binary_classify_list_agent import BinaryClassifyListAgent, BinaryClassifyListInput
 
 async def run_binary_classify_list_example():
-    items_to_classify = ['Apple', 'Chocolate', 'Carrot']
-    criteria = 'Classify each item as either healthy (true) or unhealthy (false)'
-    agent = BinaryClassifyListAgent(list_to_classify=items_to_classify, criteria=criteria)
+    input_data = BinaryClassifyListInput(
+        list_to_classify=['Apple', 'Chocolate', 'Carrot'],
+        criteria='Classify each item as either healthy (true) or unhealthy (false)',
+        max_tokens=1000,
+        temperature=0.0
+    )
+    
+    agent = BinaryClassifyListAgent(input_data)
     classified_items = await agent.classify_list()
 
-    print("Original list:", items_to_classify)
+    print("Original list:", input_data.list_to_classify)
     print("Binary classified results:", classified_items)
 
 if __name__ == "__main__":

examples/chain_of_thought_example.py

@@ -1,12 +1,17 @@
 import asyncio
-from core.chain_of_thought_agent import ChainOfThoughtAgent
+from core.chain_of_thought_agent import ChainOfThoughtAgent, ChainOfThoughtInput
 
 async def run_chain_of_thought_example():
-    question = 'What is the square root of 144?'
-    agent = ChainOfThoughtAgent(question=question)
+    input_data = ChainOfThoughtInput(
+        question='What is the square root of 144?',
+        max_tokens=1000,
+        temperature=0.0
+    )
+    
+    agent = ChainOfThoughtAgent(input_data)
     result = await agent.chain_of_thought()
 
-    print("Question:", question)
+    print("Question:", input_data.question)
     print("Chain of Thought Reasoning:", result)
 
 if __name__ == "__main__":

examples/classify_list_example.py

@@ -1,14 +1,18 @@
 import asyncio
-from core.classify_list_agent import ClassifyListAgent
+from core.classify_list_agent import ClassifyListAgent, ClassifyListInput
 
 async def run_classify_list_example():
-    items_to_classify = ['Apple', 'Chocolate', 'Carrot']
-    classification_criteria = 'Classify each item as healthy or unhealthy snack'
-    agent = ClassifyListAgent(list_to_classify=items_to_classify, classification_criteria=classification_criteria)
-    classified_items = await agent.classify_list()
+    input_data = ClassifyListInput(
+        list_to_classify=["Apple", "Banana", "Carrot"],
+        classification_criteria="Classify each item as a fruit or vegetable.",
+        max_tokens=1000
+    )
+    
+    agent = ClassifyListAgent(input_data)
+    classifications = await agent.classify_list()
 
-    print("Original list:", items_to_classify)
-    print("Classified results:", classified_items)
+    print("Original list:", input_data.list_to_classify)
+    print("Classified results:", classifications)
 
 if __name__ == "__main__":
-    asyncio.run(run_classify_list_example())
+    asyncio.run(run_classify_list_example())

examples/filter_list_example.py

@@ -1,23 +1,27 @@
 import asyncio
-from core.filter_list_agent import FilterListAgent
+from core.filter_list_agent import FilterListAgent, FilterListInput
 
 async def run_filter_list_example():
-    goal = "Remove items that are unhealthy snacks."
-    items_to_filter = [
-        "Apple",
-        "Chocolate bar",
-        "Carrot",
-        "Chips",
-        "Orange"
-    ]
-
-    agent = FilterListAgent(goal=goal, items_to_filter=items_to_filter)
+    input_data = FilterListInput(
+        goal="Remove items that are unhealthy snacks.",
+        items_to_filter=[
+            "Apple",
+            "Chocolate bar",
+            "Carrot",
+            "Chips",
+            "Orange"
+        ],
+        max_tokens=500,
+        temperature=0.0
+    )
+    
+    agent = FilterListAgent(input_data)
     filtered_results = await agent.filter()
 
-    print("Original list:", items_to_filter)
+    print("Original list:", input_data.items_to_filter)
     print("Filtered results:")
     for result in filtered_results:
         print(result)
 
 if __name__ == "__main__":
-    asyncio.run(run_filter_list_example())
+    asyncio.run(run_filter_list_example())

examples/grounded_answer_example.py

@@ -1,15 +1,19 @@
 import asyncio
-from core.grounded_answer_agent import GroundedAnswerAgent
+from core.grounded_answer_agent import GroundedAnswerAgent, GroundedAnswerInput
 
 async def run_grounded_answer_example():
-    question = "What is the capital of France?"
-    context = "France is a country in Western Europe. Paris is its capital and largest city."
-    instructions = "Ensure the answer is grounded only in the provided context."
-    agent = GroundedAnswerAgent(question=question, context=context, instructions=instructions)
-    result = await agent.answer()
+    input_data = GroundedAnswerInput(
+        question="What is the capital of France?",
+        context="France is a country in Western Europe known for its wine and cuisine. The capital is a major global center for art, fashion, and culture.",
+        instructions="",
+        max_tokens=1000
+    )
+    
+    agent = GroundedAnswerAgent(input_data)
+    answer = await agent.answer()
 
-    print("Question:", question)
-    print("Result:", result)
+    print("Question:", input_data.question)
+    print("Answer:", answer)
 
 if __name__ == "__main__":
-    asyncio.run(run_grounded_answer_example())
+    asyncio.run(run_grounded_answer_example())

examples/map_list_example.py

@@ -1,13 +1,17 @@
 import asyncio
-from core.map_list_agent import MapListAgent
+from core.map_list_agent import MapListAgent, MapListInput
 
 async def run_map_list_example():
-    items_to_map = ['Apple', 'Banana', 'Carrot']
-    transformation = 'Convert all items to uppercase'
-    agent = MapListAgent(list_to_map=items_to_map, transformation=transformation)
+    input_data = MapListInput(
+        list_to_map=['Apple', 'Banana', 'Carrot'],
+        transformation='Convert all items to uppercase',
+        max_tokens=1000
+    )
+    
+    agent = MapListAgent(input_data)
     transformed_items = await agent.map_list()
 
-    print("Original list:", items_to_map)
+    print("Original list:", input_data.list_to_map)
     print("Transformed list:", transformed_items)
 
 if __name__ == "__main__":

examples/project_list_example.py

@@ -1,13 +1,17 @@
 import asyncio
-from core.project_list_agent import ProjectListAgent
+from core.project_list_agent import ProjectListAgent, ProjectListInput
 
 async def run_project_list_example():
-    items_to_project = ['Apple', 'Banana', 'Carrot']
-    projection_rule = 'Project these items as their vitamin content'
-    agent = ProjectListAgent(list_to_project=items_to_project, projection_rule=projection_rule)
+    input_data = ProjectListInput(
+        list_to_project=['Apple', 'Banana', 'Carrot'],
+        projection_rule='Project these items as their vitamin content',
+        max_tokens=1000
+    )
+    
+    agent = ProjectListAgent(input_data)
     projected_items = await agent.project_list()
 
-    print("Original list:", items_to_project)
+    print("Original list:", input_data.list_to_project)
     print("Projected results:", projected_items)
 
 if __name__ == "__main__":

examples/reduce_list_example.py

@@ -1,14 +1,18 @@
 import asyncio
-from core.reduce_list_agent import ReduceListAgent
+from core.reduce_list_agent import ReduceListAgent, ReduceListInput
 
 async def run_reduce_list_example():
-    items_to_reduce = ['Banana', 'Apple', 'Carrot']
-    reduction_goal = 'Reduce these items to a single word representing their nutritional value'
-    agent = ReduceListAgent(list_to_reduce=items_to_reduce, reduction_goal=reduction_goal)
+    input_data = ReduceListInput(
+        list_to_reduce=["Apple", "Banana", "Carrot"],
+        reduction_goal="Reduce each item to its first letter.",
+        max_tokens=1000
+    )
+    
+    agent = ReduceListAgent(input_data)
     reduced_items = await agent.reduce_list()
 
-    print("Original list:", items_to_reduce)
+    print("Original list:", input_data.list_to_reduce)
     print("Reduced results:", reduced_items)
 
 if __name__ == "__main__":
-    asyncio.run(run_reduce_list_example())
+    asyncio.run(run_reduce_list_example())

examples/summarize_list_example.py

@@ -1,12 +1,19 @@
 import asyncio
-from core.summarize_list_agent import SummarizeListAgent
+from core.summarize_list_agent import SummarizeListAgent, SummarizeListInput
 
 async def run_summarize_list_example():
-    items_to_summarize = ['The quick brown fox jumps over the lazy dog.', 'Python is a popular programming language.']
-    agent = SummarizeListAgent(list_to_summarize=items_to_summarize)
+    input_data = SummarizeListInput(
+        list_to_summarize=[
+            'The quick brown fox jumps over the lazy dog.',
+            'Python is a popular programming language.'
+        ],
+        max_tokens=1000
+    )
+    
+    agent = SummarizeListAgent(input_data)
     summaries = await agent.summarize_list()
 
-    print("Original list:", items_to_summarize)
+    print("Original list:", input_data.list_to_summarize)
     print("Summarized results:", summaries)
 
 if __name__ == "__main__":

src/core/binary_classify_list_agent.py

@@ -1,18 +1,54 @@
+from pydantic import BaseModel, Field
 import asyncio
 from typing import List, Dict
 from .openai_api import OpenAIClient
 from .logging import Logger  # Using correct logging abstraction
 
+class BinaryClassifyListInput(BaseModel):
+    list_to_classify: List[str] = Field(..., description="The list of items to classify")
+    criteria: str = Field(..., description="The criteria for binary classification")
+    max_tokens: int = Field(1000, description="The maximum number of tokens to generate")
+    temperature: float = Field(0.0, description="Sampling temperature for the OpenAI model")
+
 class BinaryClassifyListAgent:
-    def __init__(self, list_to_classify: List[str], criteria: str, max_tokens: int = 1000, temperature: float = 0.0):
-        self.list_to_classify = list_to_classify
-        self.criteria = criteria
-        self.max_tokens = max_tokens
-        self.temperature = temperature
+    """
+    A class to classify items in a list based on binary criteria using the OpenAI API.
+
+    Attributes:
+        list_to_classify (List[str]): The list of items to classify.
+        criteria (str): The criteria for binary classification.
+        max_tokens (int): The maximum number of tokens to generate.
+        temperature (float): Sampling temperature for the OpenAI model.
+        openai_client (OpenAIClient): An instance of OpenAIClient to interact with the API.
+        logger (Logger): An instance of Logger to log classification requests and responses.
+
+    Methods:
+        classify_list(): Classifies the entire list of items.
+        classify_item(user_prompt): Classifies a single item based on the criteria.
+    """
+
+    def __init__(self, data: BinaryClassifyListInput):
+        """
+        Constructs all the necessary attributes for the BinaryClassifyListAgent object.
+
+        Args:
+            data (BinaryClassifyListInput): An instance of BinaryClassifyListInput containing 
+            the list of items, criteria, max_tokens, and temperature.
+        """
+        self.list_to_classify = data.list_to_classify
+        self.criteria = data.criteria
+        self.max_tokens = data.max_tokens
+        self.temperature = data.temperature
         self.openai_client = OpenAIClient()
         self.logger = Logger()
 
     async def classify_list(self) -> List[Dict]:
+        """
+        Classifies the entire list based on the provided items and criteria.
+
+        Returns:
+            List[Dict]: A list of dictionaries with the classification results.
+        """
         tasks = []
         for item in self.list_to_classify:
             user_prompt = f"Based on the following criteria '{self.criteria}', classify the item '{item}' as true or false."
@@ -22,6 +58,15 @@ async def classify_list(self) -> List[Dict]:
         return results
 
     async def classify_item(self, user_prompt: str) -> Dict:
+        """
+        Classifies a single item based on the criteria.
+
+        Args:
+            user_prompt (str): The prompt describing the classification criteria and item.
+
+        Returns:
+            Dict: A dictionary with the classification result.
+        """
         system_prompt = "You are an assistant tasked with binary classification of items."
 
         self.logger.info(f"Classifying item: {user_prompt}")  # Logging the classification request