vexor 0.19.0a1__py3-none-any.whl → 0.21.0__py3-none-any.whl

vexor/__init__.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from .api import VexorError, clear_index, index, search
+from .api import VexorError, clear_index, index, search, set_config_json, set_data_dir
 
 __all__ = [
     "__version__",
@@ -11,9 +11,11 @@ __all__ = [
     "get_version",
     "index",
     "search",
+    "set_config_json",
+    "set_data_dir",
 ]
 
-__version__ = "0.19.0a1"
+__version__ = "0.21.0"
 
 
 def get_version() -> str:

vexor/_bundled_skills/vexor-cli/SKILL.md

@@ -31,6 +31,7 @@ vexor "<QUERY>" [--path <ROOT>] [--mode <MODE>] [--ext .py,.md] [--exclude-patte
 - `--no-respect-gitignore`: include ignored files
 - `--no-recursive`: only the top directory
 - `--format`: `rich` (default) or `porcelain`/`porcelain-z` for scripts
+- `--no-cache`: in-memory only, do not read/write index cache
 
 ## Modes (pick the cheapest that works)
 

vexor/api.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 from dataclasses import dataclass
 from pathlib import Path
+from collections.abc import Mapping
 from typing import Sequence
 
 from .config import (
@@ -13,9 +14,12 @@ from .config import (
     Config,
     RemoteRerankConfig,
     SUPPORTED_RERANKERS,
+    config_from_json,
     load_config,
     resolve_default_model,
+    set_config_dir,
 )
+from .cache import set_cache_dir
 from .modes import available_modes, get_strategy
 from .services.index_service import IndexResult, build_index, clear_index_entries
 from .services.search_service import SearchRequest, SearchResponse, perform_search
@@ -38,6 +42,8 @@ class RuntimeSettings:
     model_name: str
     batch_size: int
     embed_concurrency: int
+    extract_concurrency: int
+    extract_backend: str
     base_url: str | None
     api_key: str | None
     local_cuda: bool
@@ -47,6 +53,30 @@ class RuntimeSettings:
     remote_rerank: RemoteRerankConfig | None
 
 
+_RUNTIME_CONFIG: Config | None = None
+
+
+def set_data_dir(path: Path | str | None) -> None:
+    """Set the base directory for config and cache data."""
+    set_config_dir(path)
+    set_cache_dir(path)
+
+
+def set_config_json(
+    payload: Mapping[str, object] | str | None, *, replace: bool = False
+) -> None:
+    """Set in-memory config for API calls from a JSON string or mapping."""
+    global _RUNTIME_CONFIG
+    if payload is None:
+        _RUNTIME_CONFIG = None
+        return
+    base = None if replace else (_RUNTIME_CONFIG or load_config())
+    try:
+        _RUNTIME_CONFIG = config_from_json(payload, base=base)
+    except ValueError as exc:
+        raise VexorError(str(exc)) from exc
+
+
 def search(
     query: str,
     *,
@@ -62,11 +92,16 @@ def search(
     model: str | None = None,
     batch_size: int | None = None,
     embed_concurrency: int | None = None,
+    extract_concurrency: int | None = None,
+    extract_backend: str | None = None,
     base_url: str | None = None,
     api_key: str | None = None,
     local_cuda: bool | None = None,
     auto_index: bool | None = None,
     use_config: bool = True,
+    config: Config | Mapping[str, object] | str | None = None,
+    temporary_index: bool = False,
+    no_cache: bool = False,
 ) -> SearchResponse:
     """Run a semantic search and return ranked results."""
 
@@ -90,11 +125,15 @@ def search(
         model=model,
         batch_size=batch_size,
         embed_concurrency=embed_concurrency,
+        extract_concurrency=extract_concurrency,
+        extract_backend=extract_backend,
         base_url=base_url,
         api_key=api_key,
         local_cuda=local_cuda,
         auto_index=auto_index,
         use_config=use_config,
+        runtime_config=_RUNTIME_CONFIG,
+        config_override=config,
     )
 
     request = SearchRequest(
@@ -108,6 +147,8 @@ def search(
         model_name=settings.model_name,
         batch_size=settings.batch_size,
         embed_concurrency=settings.embed_concurrency,
+        extract_concurrency=settings.extract_concurrency,
+        extract_backend=settings.extract_backend,
         provider=settings.provider,
         base_url=settings.base_url,
         api_key=settings.api_key,
@@ -115,6 +156,8 @@ def search(
         exclude_patterns=normalized_excludes,
         extensions=normalized_exts,
         auto_index=settings.auto_index,
+        temporary_index=temporary_index,
+        no_cache=no_cache,
         rerank=settings.rerank,
         flashrank_model=settings.flashrank_model,
         remote_rerank=settings.remote_rerank,
@@ -135,10 +178,13 @@ def index(
     model: str | None = None,
     batch_size: int | None = None,
     embed_concurrency: int | None = None,
+    extract_concurrency: int | None = None,
+    extract_backend: str | None = None,
     base_url: str | None = None,
     api_key: str | None = None,
     local_cuda: bool | None = None,
     use_config: bool = True,
+    config: Config | Mapping[str, object] | str | None = None,
 ) -> IndexResult:
     """Build or refresh the index for the given directory."""
 
@@ -154,11 +200,15 @@ def index(
         model=model,
         batch_size=batch_size,
         embed_concurrency=embed_concurrency,
+        extract_concurrency=extract_concurrency,
+        extract_backend=extract_backend,
         base_url=base_url,
         api_key=api_key,
         local_cuda=local_cuda,
         auto_index=None,
         use_config=use_config,
+        runtime_config=_RUNTIME_CONFIG,
+        config_override=config,
     )
 
     return build_index(
@@ -170,6 +220,8 @@ def index(
         model_name=settings.model_name,
         batch_size=settings.batch_size,
         embed_concurrency=settings.embed_concurrency,
+        extract_concurrency=settings.extract_concurrency,
+        extract_backend=settings.extract_backend,
         provider=settings.provider,
         base_url=settings.base_url,
         api_key=settings.api_key,
@@ -220,6 +272,8 @@ def _validate_mode(mode: str) -> str:
     return mode
 
 
+
+
 def _normalize_extensions(values: Sequence[str] | str | None) -> tuple[str, ...]:
     return normalize_extensions(_coerce_iterable(values))
 
@@ -242,13 +296,23 @@ def _resolve_settings(
     model: str | None,
     batch_size: int | None,
     embed_concurrency: int | None,
+    extract_concurrency: int | None,
+    extract_backend: str | None,
     base_url: str | None,
     api_key: str | None,
     local_cuda: bool | None,
     auto_index: bool | None,
     use_config: bool,
+    runtime_config: Config | None = None,
+    config_override: Config | Mapping[str, object] | str | None = None,
 ) -> RuntimeSettings:
-    config = load_config() if use_config else Config()
+    config = (
+        runtime_config if (use_config and runtime_config is not None) else None
+    )
+    if config is None:
+        config = load_config() if use_config else Config()
+    if config_override is not None:
+        config = _apply_config_override(config, config_override)
     provider_value = (provider or config.provider or DEFAULT_PROVIDER).lower()
     rerank_value = (config.rerank or DEFAULT_RERANK).strip().lower()
     if rerank_value not in SUPPORTED_RERANKERS:
@@ -265,11 +329,21 @@ def _resolve_settings(
     embed_value = (
         embed_concurrency if embed_concurrency is not None else config.embed_concurrency
     )
+    extract_value = (
+        extract_concurrency
+        if extract_concurrency is not None
+        else config.extract_concurrency
+    )
+    extract_backend_value = (
+        extract_backend if extract_backend is not None else config.extract_backend
+    )
     return RuntimeSettings(
         provider=provider_value,
         model_name=model_name,
         batch_size=batch_value,
         embed_concurrency=embed_value,
+        extract_concurrency=extract_value,
+        extract_backend=extract_backend_value,
         base_url=base_url if base_url is not None else config.base_url,
         api_key=api_key if api_key is not None else config.api_key,
         local_cuda=bool(local_cuda if local_cuda is not None else config.local_cuda),
@@ -278,3 +352,15 @@ def _resolve_settings(
         flashrank_model=config.flashrank_model,
         remote_rerank=config.remote_rerank,
     )
+
+
+def _apply_config_override(
+    base: Config,
+    override: Config | Mapping[str, object] | str,
+) -> Config:
+    if isinstance(override, Config):
+        return override
+    try:
+        return config_from_json(override, base=base)
+    except ValueError as exc:
+        raise VexorError(str(exc)) from exc