Code-Inc/intelligence-terminal
2
0
Fork 0
Code Issues 10 Pull Requests Actions Packages Projects Releases Wiki Activity

Add Ollama provider for self-hosted LLM inference

Browse Source 
Adds LLM_PROVIDER=ollama for fully local, zero-cost inference
via Ollama's OpenAI-compatible API. No API key required.
Configurable base URL via OLLAMA_BASE_URL env var.
This commit is contained in:
R4V3N
2026-03-18 17:13:16 +01:00
parent a8682c50d0
commit 06514fb5e4
6 changed files with 266 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
.env.example
View File

@@ -31,13 +31,15 @@ REFRESH_INTERVAL_MINUTES=15
# === LLM Layer (optional) ===
# Enables AI-enhanced trade ideas and breaking news Telegram alerts.
# Provider options: anthropic | openai | gemini | codex | openrouter | minimax
# Provider options: anthropic | openai | gemini | codex | openrouter | minimax | ollama
LLM_PROVIDER=
# Not needed for codex (uses ~/.codex/auth.json)
# Not needed for codex (uses ~/.codex/auth.json) or ollama (local)
LLM_API_KEY=
# Optional override. Each provider has a sensible default:
# anthropic: claude-sonnet-4-6 | openai: gpt-5.4 | gemini: gemini-3.1-pro | codex: gpt-5.3-codex | openrouter: openrouter/auto | minimax: MiniMax-M2.5
# anthropic: claude-sonnet-4-6 | openai: gpt-5.4 | gemini: gemini-3.1-pro | codex: gpt-5.3-codex | openrouter: openrouter/auto | minimax: MiniMax-M2.5 | ollama: llama3.1:8b
LLM_MODEL=
# Ollama base URL (only needed if not using default http://localhost:11434)
OLLAMA_BASE_URL=
# === Telegram Alerts (optional, requires LLM) ===
# Create a bot via @BotFather, get chat ID via @userinfobot