feat(bins): multi-library populate_knowledge + progress UX

populate_knowledge now loads real libraries from the DB instead of
fabricating a single library_id=1 row from BASE_PATH. Adds --library
<id|name> to restrict the walk and validates --path against the selected
library roots. The full library set is still passed to InsightGenerator so
resolve_full_path can probe every root when an insight resolves to a
different library than the one being walked.

Adds indicatif progress bars across the long-running utility binaries via
a shared src/bin_progress.rs helper (determinate bar + open-ended spinner
with consistent styling). Per-batch info! noise is replaced by the bar's
throughput/ETA; warnings and errors route through pb.println so they
scroll above the bar instead of fighting with it.

  populate_knowledge   spinner during scan, determinate bar over all libs
  backfill_hashes      spinner with running hashed/missing/errors counts
  import_calendar      determinate bar; embedding/store failures inline
  import_location_*    determinate bar advancing by chunk size
  import_search_*      determinate bar; pb cloned into the spawn task
  cleanup_files P1     determinate bar over DB paths
  cleanup_files P2     determinate bar; pb.suspend() around y/n/a/s prompt

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Cameron
2026-04-26 23:55:33 -04:00
parent d5f944c7b6
commit b9d5578653
11 changed files with 362 additions and 149 deletions

View File

@@ -2,10 +2,10 @@ use anyhow::{Context, Result};
use chrono::Utc;
use clap::Parser;
use image_api::ai::ollama::OllamaClient;
use image_api::bin_progress;
use image_api::database::calendar_dao::{InsertCalendarEvent, SqliteCalendarEventDao};
use image_api::parsers::ical_parser::parse_ics_file;
use log::{error, info};
use std::sync::{Arc, Mutex};
// Import the trait to use its methods
use image_api::database::CalendarEventDao;
@@ -64,9 +64,11 @@ async fn main() -> Result<()> {
None
};
let inserted_count = Arc::new(Mutex::new(0));
let skipped_count = Arc::new(Mutex::new(0));
let error_count = Arc::new(Mutex::new(0));
let mut inserted_count = 0usize;
let mut skipped_count = 0usize;
let mut error_count = 0usize;
let pb = bin_progress::determinate(events.len() as u64, "importing");
// Process events in batches
// Can't use rayon with async, so process sequentially
@@ -82,7 +84,8 @@ async fn main() -> Result<()> {
)
&& exists
{
*skipped_count.lock().unwrap() += 1;
skipped_count += 1;
pb.inc(1);
continue;
}
@@ -101,10 +104,7 @@ async fn main() -> Result<()> {
}) {
Ok(emb) => Some(emb),
Err(e) => {
error!(
"Failed to generate embedding for event '{}': {}",
event.summary, e
);
pb.println(format!("embedding failed for '{}': {}", event.summary, e));
None
}
}
@@ -133,28 +133,26 @@ async fn main() -> Result<()> {
};
match dao_instance.store_event(&context, insert_event) {
Ok(_) => {
*inserted_count.lock().unwrap() += 1;
if *inserted_count.lock().unwrap() % 100 == 0 {
info!("Imported {} events...", *inserted_count.lock().unwrap());
}
}
Ok(_) => inserted_count += 1,
Err(e) => {
error!("Failed to store event '{}': {:?}", event.summary, e);
*error_count.lock().unwrap() += 1;
pb.println(format!("store failed for '{}': {:?}", event.summary, e));
error_count += 1;
}
}
pb.set_message(format!(
"inserted={} skipped={} errors={}",
inserted_count, skipped_count, error_count
));
pb.inc(1);
}
let final_inserted = *inserted_count.lock().unwrap();
let final_skipped = *skipped_count.lock().unwrap();
let final_errors = *error_count.lock().unwrap();
pb.finish_and_clear();
info!("\n=== Import Summary ===");
info!("=== Import Summary ===");
info!("Total events found: {}", events.len());
info!("Successfully inserted: {}", final_inserted);
info!("Skipped (already exist): {}", final_skipped);
info!("Errors: {}", final_errors);
info!("Successfully inserted: {}", inserted_count);
info!("Skipped (already exist): {}", skipped_count);
info!("Errors: {}", error_count);
if args.generate_embeddings {
info!("Embeddings were generated for semantic search");
@@ -162,5 +160,12 @@ async fn main() -> Result<()> {
info!("No embeddings generated (use --generate-embeddings to enable semantic search)");
}
if error_count > 0 {
error!(
"Completed with {} errors — review log output above",
error_count
);
}
Ok(())
}