serversdown
f3530cf4ae
Mid-size models (gpt-4o-mini, qwen2.5-14b) resist persona instructions — help-desk closers and feelings-disclaimers leak through regardless. Route live chat to a stronger model while keeping bulk consolidation cheap: - config: CHAT_MODEL (default gpt-4o), distinct from CLOUD_MODEL (gpt-4o-mini) - llm.complete gains a `model` override; chat.respond uses chat_model on cloud, consolidation paths keep cloud_model - persona: reword the "no sign-off" rule so genuine questions are welcome and only reflexive customer-service closers are discouraged Verified: on gpt-4o she owns her mood without disclaimers and drops most help-desk tails — clearly more in-character than mini/qwen. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
25 lines
970 B
Bash
25 lines
970 B
Bash
# Local backend (Ollama) — free, private. Point this at your home-lab Ollama.
|
|
LOCAL_BASE_URL=http://localhost:11434
|
|
LOCAL_MODEL=qwen2.5:7b-instruct
|
|
|
|
# MI50 backend — OpenAI-compatible llama.cpp server on the home-lab GPU box (CT202).
|
|
MI50_BASE_URL=http://10.0.0.42:8080/v1
|
|
MI50_MODEL=local-gpu
|
|
|
|
# Cloud backend (OpenAI) — higher quality, costs money.
|
|
OPENAI_API_KEY=
|
|
CLOUD_MODEL=gpt-4o-mini # cheap model for bulk consolidation (summaries/profile/etc.)
|
|
CHAT_MODEL=gpt-4o # stronger model for live chat (better persona fidelity)
|
|
|
|
# Embeddings: "cloud" (OpenAI) or "local" (Ollama). A database is tied to whichever
|
|
# backend created it — don't switch this against an existing DB (vector spaces differ).
|
|
EMBED_BACKEND=cloud
|
|
EMBED_MODEL=text-embedding-3-small
|
|
LOCAL_EMBED_MODEL=nomic-embed-text
|
|
|
|
# Backend used to compact old sessions into summaries ("local" keeps it free).
|
|
SUMMARY_BACKEND=local
|
|
|
|
# Where Lyra stores her memory.
|
|
LYRA_DB_PATH=data/lyra.db
|