Harwinder bf6c890029 Implement Gemini batch sentiment scoring; replace FinBERT/transformers ...

- Migrate news_engine to google-genai SDK with gemini-2.5-flash-lite
- Batch all headlines into one API call per scan (30 calls -> 1)
- In-memory cache keyed by headline hash; fallback to keyword scoring
- Update requirements.txt: add google-genai, python-dotenv; remove transformers
- Add .gitignore; update CLAUDE.md with Gemini live section

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-05-06 09:58:44 -04:00

__pycache__

News model fix2 main.py

2026-05-05 22:44:58 -04:00

.gitignore

Implement Gemini batch sentiment scoring; replace FinBERT/transformers

2026-05-06 09:58:44 -04:00

CLAUDE.md

Implement Gemini batch sentiment scoring; replace FinBERT/transformers

2026-05-06 09:58:44 -04:00

config.py

Tighten signal pipeline: yfinance-only XAU/XAG, leaner Telegram /scan

2026-05-05 19:52:41 -04:00

data_provider.py

XAU/XAG: 3-TF analysis (M15+H1+H4 resampled) via per-symbol override

2026-05-05 20:12:22 -04:00

engine.py

Fixed code

2026-05-04 14:29:32 +00:00

LOGIC.md

Scan only M15 and H1; keep D1 as confirmation, drop W1 entirely

2026-05-05 14:13:44 -04:00

main.py

Tighten signal pipeline: yfinance-only XAU/XAG, leaner Telegram /scan

2026-05-05 19:52:41 -04:00

news_engine.py

Implement Gemini batch sentiment scoring; replace FinBERT/transformers

2026-05-06 09:58:44 -04:00

requirements.txt

Implement Gemini batch sentiment scoring; replace FinBERT/transformers

2026-05-06 09:58:44 -04:00

script.txt

Fixed code

2026-05-04 14:29:32 +00:00

ScriptsActivate.ps1

Changed news engine code a little

2026-05-05 22:33:43 -04:00

signal_aggregator.py

XAU/XAG: 3-TF analysis (M15+H1+H4 resampled) via per-symbol override

2026-05-05 20:12:22 -04:00

telegram_bot.py

XAU/XAG: 3-TF analysis (M15+H1+H4 resampled) via per-symbol override

2026-05-05 20:12:22 -04:00

USAGE.md

Update USAGE.md to match current behaviour

2026-05-05 14:45:09 -04:00

S

Description

No description provided

28 MiB

Languages

Python 92.4%

HTML 6.6%

PHP 1%