matt/recon
1
0
Fork 0
mirror of https://github.com/zvx-echo6/recon.git synced 2026-08-26 17:21:33 +00:00
Code Issues Projects Releases Packages Wiki Activity

Enforce gemini-2.5-flash-lite per Echo6 model policy

Browse source 
Replace gemini-2.0-flash with gemini-2.5-flash-lite across the enrichment
and extraction pipeline (config.yaml, lib/extractor.py) and the six
maintenance scripts. Flash Lite is the mandated model for all Gemini calls.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Matt 2026-06-14 22:59:36 +00:00
commit f3705d10c6
8 changed files with 8 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

2
scripts/domain_reenrich.py
View file

@ -98,7 +98,7 @@ def classify_concept(title, subdomains, content, key):
)
genai.configure(api_key=key)
model = genai.GenerativeModel(
"gemini-2.0-flash",
"gemini-2.5-flash-lite",
generation_config={"response_mime_type": "application/json"}
)
for attempt in range(4):