0xWheatyz/SPARC
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
16 Commits 1 Branch 0 Tags 25 MiB
d7cf80f02f
Commit Graph

3 Commits

Author SHA1 Message Date
0xWheatyz
d7cf80f02f feat: add LLM integration for patent analysis 
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>
 2026-02-19 18:55:35 -05:00
0xWheatyz
26a23c02ae feat: add patent content minimization for LLM consumption 
Implemented minimize_patent_for_llm() function that reduces patent
content by keeping only essential sections (abstract, claims, summary)
and explicitly excludes the verbose detailed description section.

This reduces token usage while preserving core innovation details
needed for company performance estimation.

Added comprehensive test coverage (5 new tests) for:
- Essential section inclusion
- Description section exclusion
- Missing section handling
- Empty section handling
- Section separator formatting

All 13 tests passing.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-02-19 18:54:07 -05:00
0xWheatyz
6533cef56f test: add pytest framework and initial test suite 
Added pytest and pytest-mock to requirements.txt for testing infrastructure.

Created tests/ directory with comprehensive test coverage for:
- Text cleaning functions (figure references, whitespace, line numbers)
- Section extraction logic (abstract, claims, case sensitivity)

All 8 tests passing. This provides a foundation for test-driven
development as we continue building the LLM integration.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-02-19 18:52:54 -05:00