0xWheatyz
d7cf80f02f
Implemented LLMAnalyzer class using Anthropic's Claude API for: - Single patent content analysis - Portfolio-wide analysis across multiple patents - Configurable API key management via environment variables Key features: - Uses Claude 3.5 Sonnet for high-quality analysis - Structured prompts for innovation assessment - Token limits optimized per use case (1024 for single, 2048 for portfolio) - Analyzes: innovation quality, market potential, strategic direction Updated config.py to support ANTHROPIC_API_KEY environment variable. Added comprehensive test suite (6 tests) covering: - Initialization from config and direct API key - Single patent analysis - Portfolio analysis - Token limit validation All 19 tests passing. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
125 lines
4.8 KiB
Python
125 lines
4.8 KiB
Python
"""Tests for LLM analysis functionality."""
|
|
|
|
import pytest
|
|
from unittest.mock import Mock, MagicMock
|
|
from SPARC.llm import LLMAnalyzer
|
|
|
|
|
|
class TestLLMAnalyzer:
|
|
"""Test LLM analyzer initialization and API interaction."""
|
|
|
|
def test_analyzer_initialization_with_api_key(self, mocker):
|
|
"""Test that analyzer initializes with provided API key."""
|
|
mock_anthropic = mocker.patch("SPARC.llm.Anthropic")
|
|
|
|
analyzer = LLMAnalyzer(api_key="test-key-123")
|
|
|
|
mock_anthropic.assert_called_once_with(api_key="test-key-123")
|
|
assert analyzer.model == "claude-3-5-sonnet-20241022"
|
|
|
|
def test_analyzer_initialization_from_config(self, mocker):
|
|
"""Test that analyzer loads API key from config when not provided."""
|
|
mock_anthropic = mocker.patch("SPARC.llm.Anthropic")
|
|
mock_config = mocker.patch("SPARC.llm.config")
|
|
mock_config.anthropic_api_key = "config-key-456"
|
|
|
|
analyzer = LLMAnalyzer()
|
|
|
|
mock_anthropic.assert_called_once_with(api_key="config-key-456")
|
|
|
|
def test_analyze_patent_content(self, mocker):
|
|
"""Test single patent content analysis."""
|
|
mock_anthropic = mocker.patch("SPARC.llm.Anthropic")
|
|
mock_client = Mock()
|
|
mock_anthropic.return_value = mock_client
|
|
|
|
# Mock the API response
|
|
mock_response = Mock()
|
|
mock_response.content = [Mock(text="Innovative GPU architecture.")]
|
|
mock_client.messages.create.return_value = mock_response
|
|
|
|
analyzer = LLMAnalyzer(api_key="test-key")
|
|
result = analyzer.analyze_patent_content(
|
|
patent_content="ABSTRACT: GPU with new cache design...",
|
|
company_name="NVIDIA",
|
|
)
|
|
|
|
assert result == "Innovative GPU architecture."
|
|
mock_client.messages.create.assert_called_once()
|
|
|
|
# Verify the prompt includes company name and content
|
|
call_args = mock_client.messages.create.call_args
|
|
prompt_text = call_args[1]["messages"][0]["content"]
|
|
assert "NVIDIA" in prompt_text
|
|
assert "GPU with new cache design" in prompt_text
|
|
|
|
def test_analyze_patent_portfolio(self, mocker):
|
|
"""Test portfolio analysis with multiple patents."""
|
|
mock_anthropic = mocker.patch("SPARC.llm.Anthropic")
|
|
mock_client = Mock()
|
|
mock_anthropic.return_value = mock_client
|
|
|
|
# Mock the API response
|
|
mock_response = Mock()
|
|
mock_response.content = [
|
|
Mock(text="Strong portfolio in AI and graphics.")
|
|
]
|
|
mock_client.messages.create.return_value = mock_response
|
|
|
|
analyzer = LLMAnalyzer(api_key="test-key")
|
|
patents_data = [
|
|
{"patent_id": "US123", "content": "AI acceleration patent"},
|
|
{"patent_id": "US456", "content": "Graphics rendering patent"},
|
|
]
|
|
|
|
result = analyzer.analyze_patent_portfolio(
|
|
patents_data=patents_data, company_name="NVIDIA"
|
|
)
|
|
|
|
assert result == "Strong portfolio in AI and graphics."
|
|
mock_client.messages.create.assert_called_once()
|
|
|
|
# Verify the prompt includes all patents
|
|
call_args = mock_client.messages.create.call_args
|
|
prompt_text = call_args[1]["messages"][0]["content"]
|
|
assert "US123" in prompt_text
|
|
assert "US456" in prompt_text
|
|
assert "AI acceleration patent" in prompt_text
|
|
assert "Graphics rendering patent" in prompt_text
|
|
|
|
def test_analyze_patent_portfolio_with_correct_token_limit(self, mocker):
|
|
"""Test that portfolio analysis uses higher token limit."""
|
|
mock_anthropic = mocker.patch("SPARC.llm.Anthropic")
|
|
mock_client = Mock()
|
|
mock_anthropic.return_value = mock_client
|
|
|
|
mock_response = Mock()
|
|
mock_response.content = [Mock(text="Analysis result.")]
|
|
mock_client.messages.create.return_value = mock_response
|
|
|
|
analyzer = LLMAnalyzer(api_key="test-key")
|
|
patents_data = [{"patent_id": "US123", "content": "Test content"}]
|
|
|
|
analyzer.analyze_patent_portfolio(patents_data, "TestCo")
|
|
|
|
call_args = mock_client.messages.create.call_args
|
|
# Portfolio analysis should use 2048 tokens
|
|
assert call_args[1]["max_tokens"] == 2048
|
|
|
|
def test_analyze_single_patent_with_correct_token_limit(self, mocker):
|
|
"""Test that single patent analysis uses lower token limit."""
|
|
mock_anthropic = mocker.patch("SPARC.llm.Anthropic")
|
|
mock_client = Mock()
|
|
mock_anthropic.return_value = mock_client
|
|
|
|
mock_response = Mock()
|
|
mock_response.content = [Mock(text="Analysis result.")]
|
|
mock_client.messages.create.return_value = mock_response
|
|
|
|
analyzer = LLMAnalyzer(api_key="test-key")
|
|
analyzer.analyze_patent_content("Test content", "TestCo")
|
|
|
|
call_args = mock_client.messages.create.call_args
|
|
# Single patent should use 1024 tokens
|
|
assert call_args[1]["max_tokens"] == 1024
|