""" A sophisticated analyzer using the Google Gemini Pro API. This module provides structured analysis of financial text, including: - Nuanced sentiment with reasoning. - Key entity extraction (e.g., cryptocurrencies). - Topic classification. - Potential market impact assessment. - Synthesis of multiple news items into a daily briefing. """ import os import logging import httpx import json from typing import Optional, TypedDict, List, Union # Configure logging logger = logging.getLogger(__name__) # --- Type Definitions for Structured Data --- class AnalysisResult(TypedDict): sentiment: str sentiment_score: float reason: str entities: List[str] topic: str impact: str summary: str error: Optional[str] url: Optional[str] # To store the article URL class GeminiAnalyzer: """Manages interaction with the Google Gemini API for deep text analysis.""" API_URL = "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro-latest:generateContent" def __init__(self, client: httpx.AsyncClient, api_key: Optional[str] = None): self.client = client self.api_key = api_key or os.getenv("GEMINI_API_KEY") if not self.api_key: raise ValueError("GEMINI_API_KEY is not set. Please add it as a repository secret.") self.params = {"key": self.api_key} self.headers = {"Content-Type": "application/json"} def _build_analysis_prompt(self, text: str) -> dict: """Creates the structured JSON prompt for analyzing a single piece of text.""" return { "contents": [{ "parts": [{ "text": f""" Analyze the following financial text from the cryptocurrency world. Provide your analysis as a single, minified JSON object with NO markdown formatting. The JSON object must have these exact keys: "sentiment", "sentiment_score", "reason", "entities", "topic", "impact", "summary". - "sentiment": MUST be one of "POSITIVE", "NEGATIVE", or "NEUTRAL". - "sentiment_score": A float between -1.0 (very negative) and 1.0 (very positive). - "reason": A brief, one-sentence explanation for the sentiment score. - "entities": A JSON array of strings listing the primary cryptocurrencies or tokens mentioned (e.g., ["Bitcoin", "ETH"]). - "topic": MUST be one of "Regulation", "Partnership", "Technical Update", "Market Hype", "Security", or "General News". - "impact": Assess the potential short-term market impact. MUST be one of "LOW", "MEDIUM", or "HIGH". - "summary": A concise, one-sentence summary of the provided text. Text to analyze: "{text}" """ }] }] } async def analyze_text(self, text: str) -> AnalysisResult: """Sends text to Gemini and returns a structured analysis.""" prompt = self._build_analysis_prompt(text) try: response = await self.client.post(self.API_URL, headers=self.headers, params=self.params, json=prompt, timeout=60.0) response.raise_for_status() full_response = response.json() json_text = full_response["candidates"][0]["content"]["parts"][0]["text"] analysis: AnalysisResult = json.loads(json_text) analysis["error"] = None return analysis except Exception as e: logger.error(f"❌ Gemini Analysis Error: {e}") return { "sentiment": "ERROR", "sentiment_score": 0, "reason": str(e), "entities": [], "topic": "Unknown", "impact": "Unknown", "summary": "Failed to analyze text due to an API or parsing error.", "error": str(e) } async def generate_daily_briefing(self, analysis_items: List[dict]) -> str: """Generates a high-level market briefing from a list of analyzed news items.""" if not analysis_items: return "### Briefing Unavailable\nNo news items were analyzed in the last period." context = "\n".join([f"- {item.get('summary')} (Impact: {item.get('impact')}, Topic: {item.get('topic')})" for item in analysis_items]) briefing_prompt = { "contents": [{ "parts": [{ "text": f""" You are a senior crypto market analyst named 'Sentinel'. Your tone is professional, concise, and insightful. Based on the following list of analyzed news items from the last 24 hours, write a "Daily Market Briefing". The briefing must have three sections using markdown: 1. "### Executive Summary": A single, impactful paragraph summarizing the overall market mood and key events. 2. "### Top Bullish Signals": 2-3 bullet points on the most positive developments. 3. "### Top Bearish Signals": 2-3 bullet points on the most significant risks or negative news. Here is the data to analyze: {context} """ }] }], "safetySettings": [ {"category": "HARM_CATEGORY_HARASSMENT", "threshold": "BLOCK_NONE"}, {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"}, {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "BLOCK_NONE"}, {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "BLOCK_NONE"}, ] } try: response = await self.client.post(self.API_URL, headers=self.headers, params=self.params, json=briefing_prompt, timeout=120.0) response.raise_for_status() full_response = response.json() briefing_text = full_response["candidates"][0]["content"]["parts"][0]["text"] return briefing_text except Exception as e: logger.error(f"❌ Gemini Briefing Error: {e}") return "### Briefing Unavailable\nCould not generate the daily market briefing due to a Gemini API error."