Status: True
Assertion
The Sahara is the largest hot desert in the world.
Results
<|assistant|> – True
The given statement can be considered true based on the provided information about the scientific criteria used to define desert regions, the reliability of geographic data sources for countries and territories where the Sahara Desert is located, temperature measurements obtained from weather stations in the region during summer months, and the general understanding that temperatures in winter nights are lower but still relatively high compared to more moderate climates. Therefore, it can be classified as true.
Assumptions
Here’s a bullet-pointed list of assumptions required to support the given statement:
* The definition and boundaries used to determine the size, area, or extent of desert regions are accurate and consistent across relevant scientific sources.
* Existing geographic data on countries, their borders, and territories where the Sahara Desert is located have been properly collected and validated by authoritative organizations.
* The temperature measurements provided for summer months in the Sahara represent average temperatures or a representative sample of recorded values that can be considered accurate.
* Temperature data during winter nights accurately reflects cold conditions experienced within the desert region.
* Reliable and consistent rainfall data is available to support the claim about annual precipitation in the Sahara Desert, as well as an understanding of how this impacts its classification as a hot desert.
* The scientific consensus on what constitutes a “hot” or “cold” climate based on temperature extremes and averages agreed upon by relevant experts is used to describe the Sahara’s climatic conditions accurately.
* There are no significant changes in the size, area, or geographic location of countries within which the desert resides
Fact Checker Output
<|assistant|> 1. True – The definition and boundaries used to determine the size, area, or extent of desert regions are typically based on established scientific criteria such as vegetation cover, precipitation levels, temperature patterns, etc. While there may be slight variations in definitions across sources, these differences generally align with standard scientific understanding.
2. True – Existing geographic data on countries and their territories where the Sahara Desert is located have been collected and validated by authoritative organizations such as the United Nations (UN), World Bank, or various national governments’ statistical departments. These sources ensure that borders are accurate and consistent with recognized international standards.
3. True – Temperature measurements provided for summer months in the Sahara Desert are typically obtained through weather stations scattered throughout the region. The data collected over a period of time is generally considered representative of average temperatures experienced during those months, although there may be some variation from year to year due to natural climate variability.
4. True – Temperature data for winter nights in desert regions like the Sahara Desert are typically lower than summer daytime temperatures but still relatively high compared to more moderate climates. This reflects the cold conditions experienced
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)
Leave a Reply