jeffemmett
/
erowid-bot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
erowid-bot/app
History
Jeff Emmett 80b398643e Drastically reduce prompt size for CPU inference speed 
- Cut context to 512 tokens, max output to 128
- Only 2 retrieval chunks of 150 chars each (no headers)
- Keep only last 2 conversation messages
- Minimized system prompt overhead

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 		2026-02-17 01:47:06 -07:00
..
scraper Initial commit: Erowid conversational bot 2026-02-17 01:19:49 +00:00
static Initial commit: Erowid conversational bot 2026-02-17 01:19:49 +00:00
__init__.py Initial commit: Erowid conversational bot 2026-02-17 01:19:49 +00:00
config.py Drastically reduce prompt size for CPU inference speed 2026-02-17 01:47:06 -07:00
database.py Initial commit: Erowid conversational bot 2026-02-17 01:19:49 +00:00
embeddings.py Aggressively optimize Ollama CPU inference speed 2026-02-17 01:12:04 -07:00
llm.py Drastically reduce prompt size for CPU inference speed 2026-02-17 01:47:06 -07:00
main.py Aggressively optimize Ollama CPU inference speed 2026-02-17 01:12:04 -07:00
models.py Initial commit: Erowid conversational bot 2026-02-17 01:19:49 +00:00
rag.py Drastically reduce prompt size for CPU inference speed 2026-02-17 01:47:06 -07:00