Status: False
Assertion
Cracking your knuckles causes arthritis.
Results
<|assistant|> False – While there might be associations between habitual knuckle cracking and certain symptoms or conditions like decreased grip strength in some individuals, current scientific consensus does not definitively prove a direct causal relationship between knuckle-cracking and arthritis.
Assumptions
<|assistant|> – Scientific research has not definitively proven a direct link between knuckle-cracking and arthritis.
– Habitual knuckle-cracking may contribute to decreased grip strength in some individuals.
– Frequent knuckle-cracking could be associated with joint swelling over time for a small percentage of people who crack their knuckles often.
– Arthritis has various causes, including genetics, age, previous injuries, and environmental factors.
– There are different types of arthritis (e.g., OA and RA), each with unique symptoms and treatments.
Fact Checker Output
<|assistant|> – True: Scientific research has not definitively proven a direct link between knuckle-cracking and arthritis. While there have been studies suggesting a possible association, the majority of current scientific consensus does not support a clear causal relationship. For example, an article published in The BMJ (British Medical Journal) stated that “There is no evidence for a causal link between knuckle cracking and arthritis.”
– True: Habitual knuckle-cracking may contribute to decreased grip strength in some individuals. This could be due to the potential localized effects on joint mechanics or muscle habituation over time, although more research is needed in this area for a conclusive answer.
– Partially true: Frequent knuckle-cracking could be associated with joint swelling over time for some people who crack their knuckles often, but it’s not applicable to the majority of individuals who occasionally or rarely crack their knuckles. This is due to individual differences in anatomy and susceptibility to potential adverse effects.
– True: Arthritis has various causes, including genet
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 = """In light of the above information, how would you classify the statement? (True / False) '{}'""".format(assertion)
answer_template = """{facts}\n""" + answer_template
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,
}
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 = "True" if "true" in final_output.lower() else "False" if "false" in final_output.lower() else "Debatable"
# 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)
Leave a Reply