feat: add multimodal search and granular performance diagnostics
Core CI / core (ubuntu-latest) (push) Failing after 3m31s
Core CI / core (macos-latest) (push) Canceled after 0s
Core CI / core (windows-latest) (push) Canceled after 0s
Core CI / desktop (ubuntu-latest) (push) Successful in 5m39s
Core CI / desktop (macos-latest) (push) Canceled after 0s
Core CI / desktop (windows-latest) (push) Canceled after 0s

This commit is contained in:
karl committed 2026-10-12 19:16:23 +02:00
1 parent d3bb8c7618
commit b8400c4fbf
110 files changed
+79395 -250

No files matched your search

+134 -4
View File
@@ -1,5 +1,6 @@
//! Desktop-owned orchestration: managed model setup and persistent hybrid queries.
use crate::{model_download, AppState, Filters};
use crate::{measured_outcome, model_download, AppState, Filters, MeasuredFailure};
use searchi_core::metrics::{MetricsMode, SearchResponse, TraceCollector};
use searchi_core::SearchResult;
use searchi_service::{EmbeddingReport, HybridSearch};
use serde::Serialize;
@@ -24,10 +25,20 @@ pub struct SemanticState {
downloaded_bytes: AtomicU64,
error: Mutex<Option<String>>,
service: Mutex<Option<HybridSearch>>,
media_tools: Option<searchi_media::FfmpegTools>,
media_setup_error: Option<String>,
}
impl SemanticState {
pub fn new(model_directory: PathBuf, worker: PathBuf) -> Self {
pub fn new(
model_directory: PathBuf,
worker: PathBuf,
media_tools: Result<searchi_media::FfmpegTools, String>,
) -> Self {
let (media_tools, media_setup_error) = match media_tools {
Ok(tools) => (Some(tools), None),
Err(error) => (None, Some(error)),
};
Self {
model_directory,
worker,
@@ -40,6 +51,8 @@ impl SemanticState {
downloaded_bytes: AtomicU64::new(0),
error: Mutex::new(None),
service: Mutex::new(None),
media_tools,
media_setup_error,
}
}
@@ -118,6 +131,9 @@ pub struct SemanticStatus {
pending: usize,
warming: bool,
worker_info: Option<searchi_service::WorkerInfo>,
media_tools_ready: bool,
media_setup_error: Option<String>,
media_failures: Vec<searchi_service::MediaFailure>,
}
struct WorkGuard<'a>(&'a AtomicBool);
@@ -158,6 +174,9 @@ pub fn semantic_status(state: State<'_, AppState>) -> Result<SemanticStatus, Str
.try_lock()
.ok()
.and_then(|service| service.as_ref().and_then(HybridSearch::worker_info)),
media_tools_ready: semantic.media_tools.is_some(),
media_setup_error: semantic.media_setup_error.clone(),
media_failures: index.failures,
})
}
@@ -217,13 +236,42 @@ pub async fn index_embeddings(state: State<'_, AppState>) -> Result<EmbeddingRep
semantic.record_error(None);
// Indexing uses its own isolated worker; interactive queries keep their own session.
let result = HybridSearch::open(
database,
&database,
&semantic.model_directory,
&semantic.worker,
threads,
)
.and_then(|mut service| service.index_embeddings())
.and_then(|mut service| {
let tools = semantic.media_tools.as_ref().ok_or_else(|| {
anyhow::anyhow!("The media decoder is missing from this installation. Repair or reinstall searchi.")
})?;
service.index_embeddings_with_media(tools, &searchi_media::MediaLimits::default())
})
.map_err(|error| error.to_string());
// Prepare the newly activated graph before advertising semantic readiness.
// Keyword search stays available while the cached query session catches up.
if result.is_ok() {
semantic.warmed.store(false, Ordering::Release);
semantic.warming.store(true, Ordering::Release);
let _warming_guard = WorkGuard(&semantic.warming);
let preparation = (|| {
let mut cached = semantic
.service
.lock()
.map_err(|_| "Semantic session is unavailable.".to_string())?;
let service = cached
.as_mut()
.ok_or_else(|| "Semantic query session has not been prepared.".to_string())?;
service.warmup().map_err(|error| error.to_string())
})();
semantic.warmed.store(preparation.is_ok(), Ordering::Release);
if let Err(error) = preparation {
semantic.record_error(Some(format!(
"The index was saved, but search preparation failed: {error}"
)));
return result;
}
}
semantic.record_error(result.as_ref().err().cloned());
result
})
@@ -283,3 +331,85 @@ pub async fn hybrid_search(
.await
.map_err(|error| error.to_string())?
}
#[tauri::command]
pub async fn hybrid_search_measured(
query: String,
filters: Option<Filters>,
debug_performance: bool,
state: State<'_, AppState>,
) -> Result<SearchResponse<SearchResult>, MeasuredFailure> {
let started = std::time::Instant::now();
let mut trace = TraceCollector::new(if debug_performance {
MetricsMode::Debug
} else {
MetricsMode::Basic
});
let semantic = state.semantic.clone();
if !semantic.warmed.load(Ordering::Acquire) {
return Err(MeasuredFailure::new(
"Semantic search is preparing in the background; keyword results are available.",
trace,
));
}
let threads = trace.timed("desktop.settings_lock", None, |_, _| {
state
.settings
.lock()
.map(|settings| settings.value.cpu_threads)
.map_err(|_| "Settings are unavailable.")
});
let threads = match threads {
Ok(threads) => threads,
Err(error) => return Err(MeasuredFailure::new(error, trace)),
};
if semantic
.querying
.compare_exchange(false, true, Ordering::AcqRel, Ordering::Acquire)
.is_err()
{
return Err(MeasuredFailure::new(
"Semantic worker is busy; keyword results remain available.",
trace,
));
}
let database = state.database.clone();
let queue = trace.begin("desktop.worker_queue", None);
tauri::async_runtime::spawn_blocking(move || {
let _guard = WorkGuard(&semantic.querying);
trace.end(queue, Default::default());
let result = (|| {
let mut cached = trace.timed("desktop.semantic_lock", None, |_, _| {
semantic
.service
.lock()
.map_err(|_| "Semantic session is unavailable.")
})?;
if cached.is_none() {
*cached = Some(trace.timed("desktop.session_initialize", None, |_, _| {
HybridSearch::open(
database,
&semantic.model_directory,
&semantic.worker,
threads,
)
.map_err(|error| error.to_string())
})?);
}
cached
.as_mut()
.ok_or("Semantic session is unavailable.")?
.search_traced(
&query,
50,
&filters.unwrap_or_default().into(),
&mut trace,
None,
)
.map_err(|error| error.to_string())
})();
measured_outcome(result, trace)
})
.await
.map_err(|error| MeasuredFailure::task(error.to_string(), started))?
}