cloud_config.toml

# ════════════════════════════════════════════════════════════════════════════
#  Cloud variant of the inference SSOT (see config.toml for the full schema).
#
#  Here the chat/vision endpoints are remote (backend = "openai") and therefore
#  NOT served locally — `pixi run inference` skips backend = "openai". Only the
#  RAG embedding/reranker still run locally on llama.cpp, exactly as in
#  config.toml.
#
#  To use it: everything (agents, `pixi run inference`, download-models) reads
#  config.toml, so swap this file in and provide the API key:
#      cp cloud_config.toml config.toml && export OPENAI_API_KEY=sk-...
#
#  Because cloud agents use several distinct remote models, endpoints are split
#  per model (chat_mini / vlm_mini / vlm_nano) and agents reference the right one.
# ════════════════════════════════════════════════════════════════════════════

# ─── Endpoints ──────────────────────────────────────────────────────────────

[endpoints.chat_mini]
type     = "llm"
backend  = "openai"
model    = "gpt-5-mini"
base_url = "https://api.openai.com/v1"

[endpoints.vlm_mini]
type     = "vlm"
backend  = "openai"
model    = "gpt-5-mini"
base_url = "https://api.openai.com/v1"

[endpoints.vlm_nano]
type     = "vlm"
backend  = "openai"
model    = "gpt-5-nano"
base_url = "https://api.openai.com/v1"

# RAG models are the only endpoints still served locally (backend = "gpu"):
# `pixi run inference` launches these two llama.cpp servers and skips the
# remote backend = "openai" endpoints above. Same specs as config.toml.
[endpoints.embeddings]
type       = "embedding"
backend    = "gpu"
model      = "qwen3-embedding:0.6b"
host       = "localhost"
port       = 8082
model_path = "${DEMO_ROOT}/models/Qwen3-Embedding-0.6B-Q8_0.gguf"
model_url  = "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B-GGUF/resolve/main/Qwen3-Embedding-0.6B-Q8_0.gguf?download=true"

# NOTE: The reranker and the embedding model are two separate models!
[endpoints.reranker]
type       = "reranker"
backend    = "gpu"
model      = "qwen3-reranker:0.6b"
host       = "localhost"
port       = 8083
model_path = "${DEMO_ROOT}/models/qwen3-reranker-0.6b-q8_0.gguf"
model_url  = "https://huggingface.co/ggml-org/Qwen3-Reranker-0.6B-Q8_0-GGUF/resolve/main/qwen3-reranker-0.6b-q8_0.gguf?download=true"

# ─── Agents ─────────────────────────────────────────────────────────────────

[general]
llm = "chat_mini"
vlm = "vlm_mini"
llm_reasoning = false
vlm_reasoning = false

[megamind_agent]
llm = "chat_mini"
vlm = "vlm_mini"
llm_reasoning = false
vlm_reasoning = false

[inspection_agent]
vlm = "vlm_nano"
vlm_reasoning = false
vlm_temperature = 0.0

[condition_agent]
vlm = "vlm_mini"
vlm_reasoning = false
vlm_temperature = 0.1

[safety_agent]
vlm = "vlm_nano"
vlm_reasoning = false
vlm_temperature = 0.0
embeddings = "embeddings"
reranker = "reranker"