77 lines
4.2 KiB
TOML
77 lines
4.2 KiB
TOML
# ImageApi LLM configuration. Copy to `llm.toml` next to `.env` (or point
|
|
# LLM_CONFIG_PATH at it). Every key is optional: delete any line to get its
|
|
# default. The values below are an example llama-swap setup, not the
|
|
# defaults; each key's default is in its trailing `default:` comment.
|
|
#
|
|
# Secrets stay in env: OPENROUTER_API_KEY enables the hybrid backend.
|
|
#
|
|
# The local model catalog (which models exist, vision, context size) is NOT
|
|
# listed here. It is discovered from llama-swap's /v1/models, using each
|
|
# model's `metadata:` block in llama-swap/config.yaml (kind/vision/ctx/dim).
|
|
#
|
|
# The old env vars (LLAMA_SWAP_*, OLLAMA_*, OPENROUTER_* except the key,
|
|
# EMBED_*, EMBEDDING_DIM, AGENTIC_*, LLM_BACKEND, UNIFIED_SEARCH_MODEL) still
|
|
# work for now and OVERRIDE this file, with a deprecation warning at startup.
|
|
|
|
# Local stack for chat, vision describe and embeddings: "ollama" | "llamacpp".
|
|
# Global on purpose: don't flip it without re-embedding (mixed vector spaces
|
|
# break similarity search).
|
|
backend = "llamacpp" # default: "ollama"
|
|
|
|
# Small model pinned for /photos/search/unified query translation, so it can
|
|
# stay loaded alongside CLIP.
|
|
unified_search_model = "gemma4-e4b" # default: unset (the client's selected model)
|
|
|
|
[llamacpp]
|
|
url = "http://localhost:9292/v1" # default: unset (llama.cpp client + TTS disabled)
|
|
chat = "qwen3.8-27b-abliterated" # default: "chat"
|
|
vision = "qwen3.8-27b-code-vision" # default: unset (uses `chat`); describe_photo model
|
|
timeout_secs = 180 # default: 180
|
|
|
|
# The picker shows every llama-swap model with `kind: chat` metadata (param
|
|
# aliases like `:sub` / `:fast` are always hidden), minus `exclude`.
|
|
# `include`, if set, is a strict allowlist instead.
|
|
[llamacpp.picker]
|
|
exclude = ["nemotron3.5-lightning-30b-A3B"] # default: []
|
|
# include = ["qwen3.8-27b-code", "gemma4-31"] # default: unset (show everything)
|
|
|
|
[embedding]
|
|
# Must all agree with what the stored corpus was embedded with. Changing any
|
|
# of them means `cargo run --bin reembed_embeddings`.
|
|
model = "embed" # default: "embed" (llama-swap id; Ollama always uses nomic-embed-text:v1.5)
|
|
dim = 768 # default: 768 (nomic v1.5) | 1024 for Qwen3-Embedding-0.6B
|
|
# Set prefixes only together with a re-embed; a corpus embedded without them
|
|
# won't match queries embedded with them.
|
|
query_prefix = "" # default: "" | nomic v1.5: "search_query: " | Qwen3: "Instruct: <task>\nQuery: "
|
|
document_prefix = "" # default: "" | nomic v1.5: "search_document: " | Qwen3: ""
|
|
|
|
[tts]
|
|
# Chatterbox behind llama-swap; needs llamacpp.url but not backend = "llamacpp".
|
|
model = "chatterbox" # default: "chatterbox"
|
|
voice = "m" # default: unset (server default); used when a request omits one
|
|
ref_seconds = 30 # default: 30; max voice-clone reference clip length
|
|
timeout_secs = 600 # default: 600; long chunked text takes minutes
|
|
|
|
[ollama]
|
|
primary_url = "http://localhost:11434" # default: "http://localhost:11434"
|
|
primary_model = "nemotron-3-nano:30b" # default: "nemotron-3-nano:30b"
|
|
# Tried on connection failure.
|
|
# fallback_url = "http://server:11434" # default: unset (no fallback)
|
|
# fallback_model = "llama3.2:3b" # default: unset (reuse primary_model)
|
|
timeout_secs = 120 # default: 120
|
|
|
|
[openrouter]
|
|
default_model = "anthropic/claude-sonnet-4" # default: "anthropic/claude-sonnet-4"
|
|
allowed = ["openai/gpt-4o-mini", "anthropic/claude-haiku-4-5", "google/gemini-2.5-flash"] # default: []
|
|
max_tokens = 16384 # default: 16384; 0 = uncapped (OpenRouter reserves credit against it)
|
|
# base_url = "https://openrouter.ai/api/v1" # default: unset (OpenRouter's public API)
|
|
# embedding_model = "openai/text-embedding-3-small" # default: unset
|
|
# http_referer = "https://your-site.example" # default: unset
|
|
# app_title = "ImageApi" # default: unset
|
|
|
|
[agentic]
|
|
max_iterations = 12 # default: 12; tool-loop cap for agentic insight generation
|
|
chat_max_iterations = 6 # default: 6; per chat turn, per-request values are clamped to it
|
|
chat_default_num_ctx = 32768 # default: 32768; assumed window when neither request nor backend reports one
|
|
chat_turn_timeout_secs = 300 # default: 300; reconnectable chat turns are dropped after this
|