Status: True
Assertion
Peanuts are nuts.
Results
Answer: True
## response: The statement can be classified as “True” based on the provided explanation. It acknowledges both assumptions to be true, which supports the classification of the statement accurately reflecting the shared characteristics between peanuts and tree nuts despite their botanical differences.
Assumptions
<|assistant|> – The statement is referring to peanuts’ botanical classification and their relation to true nuts (tree nuts).
– Peanuts are commonly consumed as a snack, sharing characteristics with other types of nuts such as almonds or cashews.
– An understanding of the nutritional content of peanuts is necessary in order to discuss why they share similarities with tree nuts despite their botanical differences.
– Knowledge about legumes and how they differ from true nuts (tree nuts) is required for a comprehensive comparison between the two types of foods.
– The statement assumes that readers have basic knowledge on nutrition, botany, and different categories of food products to fully grasp its implications.
Assumptions:
– Peanuts are frequently consumed as snacks and compared with other nuts for similarities in their use or consumption patterns.
– Awareness about the classification of peanuts as legumes instead of true nuts (tree nuts) is necessary to understand why they share certain characteristics despite being different botanically.
– The audience has a foundational understanding of nutrition, including an awareness of the
Fact Checker Output
explanation: 1. Assumption: Peanuts are frequently consumed as snacks and compared with other nuts for similarities in their use or consumption patterns.
– True: The statement acknowledges that peanuts, despite being botanically classified differently from tree nuts (true nuts), share common traits such as being commonly eaten as a snack. This assumption is true because peanuts are indeed popularly consumed in various forms like roasted peanuts or incorporated into dishes and confections, which makes them comparable to other nut-based snacks in terms of usage and consumption patterns.
2. Assumption: Awareness about the classification of peanuts as legumes instead of true nuts (tree nuts) is necessary to understand why they share certain characteristics despite being different botanically.
– True: The statement implies that understanding the botanical difference between peanuts and tree nuts is essential for discussing their similarities, which suggests a need to comprehend the classification distinction. This assumption is true because knowing that peanuts are legumes while tree nuts (true nuts) belong to different plant families helps explain shared features like high
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