openai: add AI stack (litellm + langfuse + pipecat + silero-tts) and oO aliases

- LiteLLM proxy with langfuse callbacks, postgres backends, and OpenRouter fallbacks. - Langfuse observability UI. - Pipecat voice pipeline (LiveKit + STT + TTS + LLM) and Silero TTS build contexts. - Ollama tuned for GPU (OLLAMA_NUM_GPU=999, mem_limit=4g, max 2 loaded models). - open-webui wired to litellm + faster-whisper + silero for voice. - litellm-config.yaml publishes oO's model aliases (tip-generator, embedder, judge) pointing at the host ollama on :11434 so ml/serving can call them via LiteLLM. .env skipped (secrets). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-20 14:28:24 +00:00
parent 52190b63b8
commit 85033136d8
8 changed files with 1020 additions and 7 deletions
--- a/openai/litellm-config.yaml
+++ b/openai/litellm-config.yaml
@@ -0,0 +1,120 @@
+model_list:
+  # ── oO aliases (used by ml/serving; see oO/CLAUDE.md AI stack) ──────────
+  - model_name: tip-generator
+    litellm_params:
+      model: ollama/qwen2.5:1.5b
+      api_base: http://host.docker.internal:11434
+
+  - model_name: embedder
+    litellm_params:
+      model: ollama/nomic-embed-text
+      api_base: http://host.docker.internal:11434
+
+  - model_name: judge
+    litellm_params:
+      model: anthropic/claude-haiku-4-5-20251001
+      api_key: os.environ/ANTHROPIC_API_KEY
+
+  # ── raw model exposure ─────────────────────────────────────────────────
+  - model_name: ollama/qwen3.5:4b
+    litellm_params:
+      model: ollama/qwen3.5:4b
+      api_base: http://host.docker.internal:11436
+
+  - model_name: ollama/qwen3:8b
+    litellm_params:
+      model: ollama/qwen3:8b
+      api_base: http://host.docker.internal:11436
+
+  - model_name: ollama/qwen2.5:1.5b
+    litellm_params:
+      model: ollama/qwen2.5:1.5b
+      api_base: http://host.docker.internal:11436
+
+  - model_name: ollama/qwen2.5:0.5b
+    litellm_params:
+      model: ollama/qwen2.5:0.5b
+      api_base: http://host.docker.internal:11436
+
+  - model_name: ollama/gemma3:4b
+    litellm_params:
+      model: ollama/gemma3:4b
+      api_base: http://host.docker.internal:11436
+
+  - model_name: ollama/gemma3:1b
+    litellm_params:
+      model: ollama/gemma3:1b
+      api_base: http://host.docker.internal:11435
+
+  - model_name: ollama/nomic-embed-text
+    litellm_params:
+      model: ollama/nomic-embed-text
+      api_base: http://host.docker.internal:11435
+
+  # OpenRouter free-tier models
+  - model_name: meta-llama/llama-3.3-70b-instruct:free
+    litellm_params:
+      model: openrouter/meta-llama/llama-3.3-70b-instruct:free
+      api_key: os.environ/OPENROUTER_API_KEY
+
+  - model_name: meta-llama/llama-3.2-3b-instruct:free
+    litellm_params:
+      model: openrouter/meta-llama/llama-3.2-3b-instruct:free
+      api_key: os.environ/OPENROUTER_API_KEY
+
+  - model_name: deepseek/deepseek-r1:free
+    litellm_params:
+      model: openrouter/deepseek/deepseek-r1:free
+      api_key: os.environ/OPENROUTER_API_KEY
+
+  - model_name: qwen/qwen3-4b:free
+    litellm_params:
+      model: openrouter/qwen/qwen3-4b:free
+      api_key: os.environ/OPENROUTER_API_KEY
+
+  - model_name: qwen/qwen3-coder:free
+    litellm_params:
+      model: openrouter/qwen/qwen3-coder:free
+      api_key: os.environ/OPENROUTER_API_KEY
+
+  - model_name: google/gemma-3-27b-it:free
+    litellm_params:
+      model: openrouter/google/gemma-3-27b-it:free
+      api_key: os.environ/OPENROUTER_API_KEY
+
+  - model_name: google/gemma-3-12b-it:free
+    litellm_params:
+      model: openrouter/google/gemma-3-12b-it:free
+      api_key: os.environ/OPENROUTER_API_KEY
+
+  - model_name: mistralai/mistral-small-3.1-24b-instruct:free
+    litellm_params:
+      model: openrouter/mistralai/mistral-small-3.1-24b-instruct:free
+      api_key: os.environ/OPENROUTER_API_KEY
+
+  - model_name: nvidia/nemotron-3-super-120b-a12b:free
+    litellm_params:
+      model: openrouter/nvidia/nemotron-3-super-120b-a12b:free
+      api_key: os.environ/OPENROUTER_API_KEY
+
+  - model_name: openai/gpt-oss-120b:free
+    litellm_params:
+      model: openrouter/openai/gpt-oss-120b:free
+      api_key: os.environ/OPENROUTER_API_KEY
+
+  - model_name: minimax/minimax-m2.5:free
+    litellm_params:
+      model: openrouter/minimax/minimax-m2.5:free
+      api_key: os.environ/OPENROUTER_API_KEY
+
+  - model_name: nousresearch/hermes-3-llama-3.1-405b:free
+    litellm_params:
+      model: openrouter/nousresearch/hermes-3-llama-3.1-405b:free
+      api_key: os.environ/OPENROUTER_API_KEY
+
+litellm_settings:
+  success_callback: ["langfuse"]
+  failure_callback: ["langfuse"]
+  drop_params: true
+  fallbacks:
+    - deepseek/deepseek-r1:free: ["ollama/qwen3.5:4b"]