mirror of
https://github.com/katanemo/plano.git
synced 2026-06-23 15:38:07 +02:00
78f761ef75
Phase 1 - Remove dead/duplicate content:
- Delete demos/samples_java/ (incomplete Java demo)
- Delete demos/shared/chatbot_ui/ (replaced by AnythingLLM)
- Delete demos/shared/grafana/, prometheus/, logfire/, honeycomb/, signoz/
(legacy observability stacks; only jaeger is retained)
- Delete variant docker-compose files (honeycomb, logfire, signoz, jaeger)
- Delete demos/use_cases/spotify_bearer_auth/run_demo.sh (stale script)
Phase 2 - Restructure into semantic categories:
- getting_started/ : weather_forecast, llm_gateway
- agent_orchestration/ : travel_agents, multi_agent_crewai_langchain
- llm_routing/ : model_alias_routing, preference_based_routing, claude_code_router
- filter_chains/ : http_filter, mcp_filter
- integrations/ : ollama, spotify_bearer_auth
- advanced/ : model_choice_test_harness, multi_turn_rag,
currency_exchange, stock_quote
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| config.yaml | ||
| docker-compose.yaml | ||
| README.md | ||
| run_demo.sh | ||
This demo shows how you can use ollama as upstream LLM.
Before you can start the demo please make sure you have ollama up and running. You can use command ollama run llama3.2 to start llama 3.2 (3b) model locally at port 11434.