Status: True

Assertion

Freezing temperatures can kill germs.

Results

Response:
solution>
– True

Assumptions

<|assistant|> – Freezing temperatures have an impact on the activity and viability of germs/microorganisms.
– Some types of germs can be rendered dormant or slowed down by freezing, although not necessarily killed outright.
– The effectiveness of freezing in controlling microbial growth depends on factors such as temperature, duration of exposure to cold temperatures, and the specific characteristics of the microorganism (e.g., psychrophilic vs. mesophilic).
– Improper food handling practices can allow surviving germs/microorganisms to become active again after being frozen.
– Some bacteria and viruses may retain infectivity even when frozen, although many experience reduced stability at low temperatures.
– The statement assumes that the primary goal of freezing is not necessarily complete elimination of germs but rather reducing their activity or growth rate to prevent foodborne illnesses.
– The effectiveness of freezing as a method to control germs may vary depending on the type and concentration of microorganisms present in the food being frozen.
– There are exceptions where certain bacteria, such as psychrophiles,

Fact Checker Output

Response:

– True. Freezing temperatures generally have an impact on microbial activity and viability because most microorganisms cannot survive or grow at these low temperatures. However, the extent tozymic effect varies among different types of germs/microorganisms.
– True. While freezing can slow down or inhibit the growth of many bacteria and other microorganisms, it doesn’t necessarily kill them outright. Some microorganisms are more resistant to cold temperatures than others.
– True. The effectiveness of freezing in controlling microbial growth depends on various factors such as temperature (usually below 32°F or -0°C is considered safe for food preservation), duration, and the specific characteristics of the microorganisms involved. Psychrophilic organisms can survive at lower temperatures compared to mesophiles.
– True. Improper handling after freezing (e.g., thawing in unsafe conditions) could potentially activate dormant or slowed germs, posing a risk of foodborne illnesses if the temperature allows for their growth again.
– True. While many bacter

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
}

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)

    # 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:
    - True
    - False
    - Debatable
    """
    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(final_output):
    final_output = final_output.lower().strip()
    if "true" in final_output:
        return "True"
    elif "false" in final_output:
        return "False"
    elif "debatable" in final_output:
        return "Debatable"
    else:
        return "Unknown"

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
    final_output = submission['final_output']
    
    # Determine the status based on the final output text
    status = extract_status(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>{final_output}</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)