Status: True

Assertion

Eating spicy food can cause ulcers.

Results

The assertion that spicy food does not directly cause ulcers in most individuals is supported by medical consensus, which points to H. pylori and lifestyle factors as the primary causes of peptic ulcers. This aligns with current understanding within gastroenterology. While some may experience discomfort from spicy food due to pre-existing conditions or sensitivities, it is not a direct cause for most people. Excessive consumption of spicy food might contribute to the development of ulcers in rare cases but should not be generalized as an underlying factor. Hence, this statement can be classified as true based on current medical knowledge and consensus.
– False: This classification does not apply because the provided information supports that spicy food is not a direct cause for most individuals’ ulcer formation.
– Debatable: There is no clear indication from the given data that it would lead to an unequivocal conclusion; however, based on medical consensus and evidence presented, this statement leans towards being true rather than debatable. The statement could be seen as slightly ambiguous because “excessive consumption” can vary between individuals, but in general context, it’s not a

Assumptions

– Spicy food does not directly cause ulcers in most individuals.
– The primary causes of peptic ulcers are H. pylori infection and lifestyle factors such as smoking and alcohol consumption.
– Some individuals may experience discomfort from consuming spicy food if they have pre-existing conditions or sensitivities, but this does not lead to ulcer formation.
– Excessive consumption of spicy food is a rare contributing factor to the development of ulcers and should be considered in specific cases rather than as a general cause.
– The relationship between spicy food and discomfort experienced by some individuals may vary, making it an unreliable indicator for ulcer formation.
– Individuals with pre-existing conditions or sensitivities who consume hot and spicy food should be cautious but not necessarily at a significantly higher risk of developing ulcers compared to the general population.
– The majority of peptic ulcer cases are caused by H. pylori infection, NSAIDs use, smoking, and excessive alcohol consumption, with no significant evidence linking spicy food as a direct cause for most individuals.
–

Fact Checker Output

<|assistant|> – True: Spicy food does not directly cause ulcers in most individuals because the primary causes of peptic ulcers are H. pylori infection and lifestyle factors such as smoking and alcohol consumption. This assertion aligns with medical consensus, which identifies these factors as major contributors to ulcer formation.
– True: Some individuals may experience discomfort from consuming spicy food if they have pre-existing conditions or sensitivities, but this does not lead to ulcer formation. The assertion is consistent with the fact that while some people might find spicy food irritating due to specific health issues, it’s not a direct cause of ulcers for most individuals.
– True: Excessive consumption of spicy food is a rare contributing factor to the development of ulcers and should be considered in specific cases rather than as a general cause. This statement accurately reflects that while there may be isolated cases where excessively hot or spicy food could contribute, it’s not common practice to consider spicy food intake as an underlying cause for ulcer development broadly.
– True: The relationship between spicy food and discomfort experienced by some individuals may

Model Used

microsoft/Phi-3-mini-4k-instruct-gguf

Script Name

fact_checker_mongodb.py

Script Code

import os
import sys
import requests
from langchain_openai.llms import OpenAI
from langchain.prompts import PromptTemplate
from dotenv import load_dotenv
from statements import get_random_statement
from mongodb_helper import insert_record  # Import MongoDB helper functions
import html

# Load environment variables from .env file
load_dotenv()

# Define category IDs
CATEGORY_IDS = {
    "True": 2,
    "False": 3,
    "Debatable": 4,
    "Unknown": 6
}

def create_wordpress_post(title, content, category):
    data = {
        "title": title,
        "content": content,
        "status": "publish",
        "categories": [CATEGORY_IDS[category]]
    }

    response = requests.post(
        os.getenv("WORDPRESS_POSTS_URL"),
        json=data,
        auth=(os.getenv("WORDPRESS_USERNAME"), os.getenv("WORDPRESS_PASSWORD"))
    )

    if response.status_code == 201:
        print("Blog post created successfully.")
    else:
        print(f"Failed to create blog post: {response.status_code} - {response.text}")

def fact_check(assertion):
    llm = OpenAI(temperature=0.7, model=os.getenv("MODEL_NAME"))

    # Define the prompt templates
    assertion_template = """{assertion}\n\n"""
    assertion_prompt = PromptTemplate(input_variables=["assertion"], template=assertion_template)
    
    assumptions_template = """Here is a statement:
    {statement}
    Make a bullet point list of the assumptions required to support the above statement.\n\n"""
    assumptions_prompt = PromptTemplate(input_variables=["statement"], template=assumptions_template)
    
    fact_checker_template = """Here is a bullet point list of assertions:
    {assertions}
    For each assumption, determine whether it is true or false. Explain your reasoning.\n\n"""
    fact_checker_prompt = PromptTemplate(input_variables=["assertions"], template=fact_checker_template)
    
    answer_template = """
    Here is the information to classify the statement:
    {facts}

    Based on the above information, how would you classify the statement? Respond with one of the following options followed by a colon and space:
    - True: [Explanation]
    - False: [Explanation]
    - Debatable: [Explanation]
    """
    answer_prompt = PromptTemplate(input_variables=["facts"], template=answer_template)
    
    # Format prompts and extract the string content
    formatted_assertion = assertion_prompt.format_prompt(assertion=assertion).text
    assertion_output = llm.invoke(formatted_assertion)
    
    formatted_assumptions = assumptions_prompt.format_prompt(statement=assertion_output).text
    assumptions_output = llm.invoke(formatted_assumptions)
    
    formatted_fact_checker = fact_checker_prompt.format_prompt(assertions=assumptions_output).text
    fact_checker_output = llm.invoke(formatted_fact_checker)
    
    formatted_answer = answer_prompt.format_prompt(facts=fact_checker_output).text
    final_output = llm.invoke(formatted_answer)
    
    return {
        "assertion_output": assertion_output,
        "assumptions_output": assumptions_output,
        "fact_checker_output": fact_checker_output,
        "final_output": final_output,
    }

def extract_status_and_reasoning(final_output):
    final_output = final_output.strip()
    if "True:" in final_output:
        status_start = final_output.find("True:")
        status = "True"
    elif "False:" in final_output:
        status_start = final_output.find("False:")
        status = "False"
    elif "Debatable:" in final_output:
        status_start = final_output.find("Debatable:")
        status = "Debatable"
    else:
        return "Unknown", final_output

    reasoning = final_output[status_start + len(status) + 1:].strip()
    return status, reasoning

if __name__ == "__main__":
    if len(sys.argv) > 1:
        assertion = sys.argv[1]
    else:
        assertion = get_random_statement()
    
    print(assertion)
    submission = fact_check(assertion)
    
    # Print the detailed outputs to inspect their structure
    for key, value in submission.items():
        print(f"{key}: {value}")
    
    # Extract the final output for status determination and reasoning
    final_output = submission['final_output']
    status, reasoning = extract_status_and_reasoning(final_output)
    
    # Record the result in MongoDB
    try:
        print("Attempting to insert record into MongoDB...")
        insert_record(
            script_name="fact_checker_mongodb.py",
            script_code=html.escape(open(__file__).read()),
            assertion=assertion,
            status=status,
            submission=submission,  # Store the entire submission for detailed analysis
            model=os.getenv("MODEL_NAME")
        )
        print("Record inserted into MongoDB successfully.")
    except Exception as e:
        print(f"Failed to insert record into MongoDB: {e}")
    
    print(final_output)
    
    # Create a blog post on WordPress
    blog_title = f"Fact Check: {assertion}"
    blog_content = f"""
    <h1>Status: {status}</h1>
    <h2>Assertion</h2>
    <p>{assertion}</p>
    <h2>Results</h2>
    <p>{reasoning}</p>
    <h3>Assumptions</h3>
    <p>{submission['assumptions_output']}</p>
    <h3>Fact Checker Output</h3>
    <p>{submission['fact_checker_output']}</p>
    <h4>Model Used</h4>
    <p>{os.getenv("MODEL_NAME")}</p>
    <h4>Script Name</h4>
    <p>fact_checker_mongodb.py</p>
    <h4>Script Code</h4>
    <pre>{html.escape(open(__file__).read())}</pre>
    """
    create_wordpress_post(blog_title, blog_content, status)