ChemaVX
d0e55ddb50
Build & Deploy ResearchOwl / build-and-push (push) Successful in 45s
processor.py: split _score_quality into _score_with_claude and _score_with_ollama; if ANTHROPIC_API_KEY is set, use Claude Haiku (claude-haiku-4-5) with max_tokens=10 for fast, accurate 0-10 relevance scoring; falls back to Ollama on any error requirements.txt: add anthropic>=0.40.0 k8s: ANTHROPIC_API_KEY added to researchowl-secrets and mounted in deployment; QUALITY_THRESHOLD restored to 0.4 (Claude scoring is accurate enough to use the threshold) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
35 lines
531 B
Plaintext
35 lines
531 B
Plaintext
# Core
|
|
fastapi==0.115.0
|
|
uvicorn==0.30.0
|
|
python-telegram-bot==21.5
|
|
httpx==0.27.0
|
|
aiohttp==3.10.0
|
|
|
|
# Scraping
|
|
beautifulsoup4==4.12.3
|
|
lxml==5.2.2
|
|
trafilatura==1.12.0
|
|
youtube-transcript-api==0.6.2
|
|
pdfplumber==0.11.3
|
|
feedparser==6.0.11
|
|
duckduckgo-search==6.2.6
|
|
|
|
# Storage & Embeddings
|
|
sqlite-vec==0.1.6
|
|
aiosqlite==0.20.0
|
|
|
|
# Processing
|
|
tiktoken==0.7.0
|
|
numpy==1.26.4
|
|
scikit-learn==1.5.1
|
|
|
|
# Claude API (scoring)
|
|
anthropic>=0.40.0
|
|
|
|
# Utilities
|
|
pydantic==2.8.0
|
|
pydantic-settings==2.4.0
|
|
tenacity==9.0.0
|
|
structlog==24.4.0
|
|
python-dotenv==1.0.1
|