# kebab config — `~/.config/kebab/config.toml`.
#
## `workspace.root` accepts:
#   • absolute paths       (`/home/me/KnowledgeBase`)
#   • tilde                (`~/KnowledgeBase`)         ← default
#   • env vars             (`${XDG_DATA_HOME}/kebab`)
#   • relative paths       (`./notes`, `notes`, `../shared/x`)
#     — relative paths resolve against the directory of THIS
#       config file, NOT the user's `cwd` at invocation time.
#
# 처리 가능한 형식 (extractor 가 자동 결정 — config 에 명시할 수 없음):
#   • Markdown: .md
#   • 이미지:   .png .jpg .jpeg  (OCR + caption)
#   • PDF:      .pdf
# 다른 확장자는 ingest 시 자동 skip + warning. 처리 대상 폴더의
# 일부만 ingest 하고 싶으면 `kebab ingest <path>` 로 root 명시
# 또는 `.kebabignore` 파일 / 본 `workspace.exclude` 로 denylist.
#
# Override individual keys at runtime with `KEBAB_*` env vars
# (e.g. `KEBAB_WORKSPACE_ROOT=/tmp/test kebab ingest`).
schema_version = 2

[workspace]
root = "/Users/user/Obsidian/Default"
exclude = [
    ".git/**",
    "node_modules/**",
    ".obsidian/**",
]

[storage]
data_dir = "${XDG_DATA_HOME:-~/.local/share}/kebab"
sqlite = "{data_dir}/kebab.sqlite"
vector_dir = "{data_dir}/lancedb"
asset_dir = "{data_dir}/assets"
artifact_dir = "{data_dir}/artifacts"
model_dir = "{data_dir}/models"
runs_dir = "{data_dir}/runs"
copy_threshold_mb = 100

[indexing]
max_parallel_extractors = 2
max_parallel_embeddings = 1
watch_filesystem = false

[chunking]
target_tokens = 500
overlap_tokens = 80
respect_markdown_headings = true
chunker_version = "md-heading-v1"

[models.embedding]
provider = "ollama"
endpoint = "http://127.0.0.1:11434"
# endpoint = "http://192.168.0.2:11943"
model = "snowflake-arctic-embed2"
# provider = "candle"
# model    = "snowflake-arctic-embed-l-v2.0"
version = "v1"
dimensions = 1024
batch_size = 64
num_threads = 0

[models.llm]
provider = "ollama"
model = "gemma4:e4b"
context_tokens = 32768
# endpoint = "http://127.0.0.1:11434"
endpoint = "http://192.168.0.2:11943"
temperature = 0.0
seed = 0
request_timeout_secs = 300

# NLI(groundedness) 모델.
[models.nli]
model = "Xenova/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7"
provider = "onnx"

[search]
default_k = 10
hybrid_fusion = "rrf"
rrf_k = 60
snippet_chars = 220
cache_capacity = 256
stale_threshold_days = 30

[rag]
prompt_template_version = "rag-v3"
score_gate = 0.30000001192092896
explain_default = false
max_context_tokens = 8000
multi_hop_max_depth = 3
multi_hop_max_sub_queries_per_iter = 5
multi_hop_max_pool_chunks = 15
nli_threshold = 0.0

[image.ocr]
enabled = true
engine = "paddle-onnx"
# engine = "ollama-vision"
model = "gemma4:e4b"
languages = [
    "eng",
    "kor",
]
max_pixels = 1600
request_timeout_secs = 300

[image.caption]
enabled = true
max_pixels = 768
prompt_template_version = "caption-v1"

[ui]
theme = "dark"

# code ingest skip 정책(.gitignore 자동 honor).
[ingest.code]
skip_generated_header = false
max_file_bytes = 262144
max_file_lines = 5000
extra_skip_globs = []
ast_chunk_max_lines = 200
fallback_lines_per_chunk = 80
fallback_lines_overlap = 20

# scanned PDF page-단위 OCR(기본 off).
[pdf.ocr]
enabled = false
always_on = false
engine = "paddle-onnx"
# engine = "ollama-vision"
model = "qwen2.5vl:3b"
languages = [
    "eng",
    "kor",
]
max_pixels = 2048
request_timeout_secs = 180
valid_ratio_threshold = 0.5
min_char_count = 20
lang_hint = "kor"

# ingest 로그(기본 on, ~/.local/state/kebab/logs).
[logging]
ingest_log_enabled = true
ingest_log_dir = "{state_dir}/logs"
keep_recent_runs = 100
retention_days = 30