47 lines
1.6 KiB
Python
47 lines
1.6 KiB
Python
|
from enum import Enum
|
||
|
|
|
||
|
|
import ollama
|
||
|
|
from pydantic import BaseModel
|
||
|
|
|
||
|
|
class Category(str, Enum):
|
||
|
|
REGULATORY_NEWS = "Regulatory News"
|
||
|
|
INSTITUTIONAL_ADOPTION = "Institutional Adoption"
|
||
|
|
MARKET_SENTIMENT = "Market Sentiment"
|
||
|
|
MACROECONOMIC_FACTORS = "Macroeconomic Factors"
|
||
|
|
SECURITY_HACKS = "Security & Hacks"
|
||
|
|
TECHNOLOGICAL_DEVELOPMENTS = "Technological Developments"
|
||
|
|
WHALE_EXCHANGE_ACTIVITY = "Whale & Exchange Activity"
|
||
|
|
|
||
|
|
class ArticleClassification(BaseModel):
|
||
|
|
category: Category
|
||
|
|
sentiment: int
|
||
|
|
|
||
|
|
class ArticleAnalyzer:
|
||
|
|
def __init__(self):
|
||
|
|
self.base_prompt = """
|
||
|
|
Classify the following article into one of these categories:
|
||
|
|
- Regulatory News
|
||
|
|
- Institutional Adoption
|
||
|
|
- Market Sentiment
|
||
|
|
- Macroeconomic Factors
|
||
|
|
- Security & Hacks
|
||
|
|
- Technological Developments
|
||
|
|
- Whale & Exchange Activity
|
||
|
|
|
||
|
|
Also, assign a sentiment (1 for Positive, -1 for Negative, or 0 for Neutral).
|
||
|
|
"""
|
||
|
|
print(f"This JSON model is going to be used for structured ouput classification : {ArticleClassification.model_json_schema()}")
|
||
|
|
|
||
|
|
def classify_article(self, article_text):
|
||
|
|
prompt = f"""{self.base_prompt}
|
||
|
|
|
||
|
|
ARTICLE: {article_text}
|
||
|
|
|
||
|
|
OUTPUT FORMAT:
|
||
|
|
Category: <category>
|
||
|
|
Sentiment: <sentiment>
|
||
|
|
"""
|
||
|
|
response = ollama.chat(model="llama3.2",
|
||
|
|
messages=[{"role": "user", "content": prompt}],
|
||
|
|
format=ArticleClassification.model_json_schema())
|
||
|
|
return response['message']['content']
|