Spaces:
Sleeping
Sleeping
File size: 3,995 Bytes
ddd7ca8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 | import os
import requests
import gradio as gr
from cerebras.cloud.sdk import Cerebras
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.schema import Document
import numpy as np
from langchain_community.document_loaders import TextLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from sentence_transformers import SentenceTransformer
# Initialize Cerebras API client
Facts = os.getenv("Facto")
client = Cerebras(api_key= Facts)
Newskey = os.getenv("News")
# Function to fetch latest news articles from NewsAPI
def get_latest_news(query):
api_key = Newskey
url = f"https://newsapi.org/v2/everything?q={query}&apiKey={api_key}"
response = requests.get(url)
data = response.json()
return [(article["title"], article["url"], article["source"]["name"]) for article in data.get("articles", [])[:5]]
# Function to update fact_checks.txt with new user input (overwrites previous content)
def update_fact_checks_file(query):
with open("fact_checks.txt", "w", encoding="utf-8") as file:
file.write(f"{query}\n")
# Function to create a FAISS retriever dynamically
def create_faiss_retriever():
if not os.path.exists("fact_checks.txt"):
open("fact_checks.txt", "w").close() # Create file if it doesn't exist
loader = TextLoader("fact_checks.txt")
documents = loader.load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=400, chunk_overlap=50)
docs = text_splitter.split_documents(documents)
embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
vector_store = FAISS.from_documents(docs, embedding_model)
return vector_store.as_retriever(search_type="similarity", search_kwargs={"k": 8})
# Function to clear the fact_checks.txt file after execution
def clear_fact_checks_file():
open("fact_checks.txt", "w").close()
# Function to perform fact-checking with Llama 3.3
def fact_check_with_llama3(query):
# Save query to fact_checks.txt
update_fact_checks_file(query)
# Reload FAISS index with new data
retriever = create_faiss_retriever()
# Retrieve relevant facts from FAISS
retrieved_docs = retriever.invoke(query)
retrieved_texts = [doc.page_content for doc in retrieved_docs]
# Fetch real-time news
news = get_latest_news(query)
# Combine all retrieved context
context_text = "\n".join(retrieved_texts)
# Construct prompt for Llama 3.3
prompt = f"""
Claim: {query}
Context: {context_text}
Based on the provided context, determine whether the claim is True, False, or Misleading. Provide a concise explanation and cite relevant sources. Don't mention any instance of your knowledge cut-off.
"""
# Call Llama 3.3 API
stream = client.chat.completions.create(
messages=[{"role": "system", "content": prompt}],
model="llama-3.3-70b",
stream=True,
max_completion_tokens=512,
temperature=0.2,
top_p=1
)
# Generate AI response
result = "".join(chunk.choices[0].delta.content or "" for chunk in stream)
# Format results with sources
sources = "\n".join([f"{title} ({source}): {url}" for title, url, source in news])
# Clear the file after execution
clear_fact_checks_file()
return result, sources if sources else "No relevant sources found."
# Gradio Interface
def fact_check_interface(query):
response, sources = fact_check_with_llama3(query)
return response, sources
gui = gr.Interface(
fn=fact_check_interface,
inputs=gr.Textbox(placeholder="Enter a claim to fact-check"),
outputs=[gr.Textbox(label="Fact-Check Result"), gr.Textbox(label="Sources")],
title="Facto - AI Fact-Checking System",
description="Enter a claim, and the system will verify it using Llama 3.3 and external knowledge sources, citing relevant sources."
)
gui.launch(debug=True) |