65583ed5d6
Removes module-level doc comments (//! lines) and excessive inline doc comments that were duplicating information already evident from: - Function/struct names (self-documenting code) - Type signatures (the what is clear from types) - Implementation context (the how is clear from code) Affected modules: - cli/* - Removed command descriptions duplicating clap help text - core/* - Removed module headers and obvious function docs - documents/* - Removed extractor/regenerator/truncation docs - embedding/* - Removed pipeline and chunking docs - gitlab/* - Removed client and transformer docs (kept type definitions) - ingestion/* - Removed orchestrator and ingestion docs - search/* - Removed FTS and vector search docs Philosophy: Code should be self-documenting. Comments should explain "why" (business decisions, non-obvious constraints) not "what" (which the code itself shows). This change reduces noise and maintenance burden while keeping the codebase just as understandable. Retains comments for: - Non-obvious business logic - Important safety invariants - Complex algorithm explanations - Public API boundaries where generated docs matter Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
85 lines
2.2 KiB
Rust
85 lines
2.2 KiB
Rust
use console::style;
|
|
use serde::Serialize;
|
|
|
|
use crate::Config;
|
|
use crate::core::db::create_connection;
|
|
use crate::core::error::Result;
|
|
use crate::core::paths::get_db_path;
|
|
use crate::embedding::ollama::{OllamaClient, OllamaConfig};
|
|
use crate::embedding::pipeline::embed_documents;
|
|
|
|
#[derive(Debug, Default, Serialize)]
|
|
pub struct EmbedCommandResult {
|
|
pub embedded: usize,
|
|
pub failed: usize,
|
|
pub skipped: usize,
|
|
}
|
|
|
|
pub async fn run_embed(
|
|
config: &Config,
|
|
full: bool,
|
|
retry_failed: bool,
|
|
progress_callback: Option<Box<dyn Fn(usize, usize)>>,
|
|
) -> Result<EmbedCommandResult> {
|
|
let db_path = get_db_path(config.storage.db_path.as_deref());
|
|
let conn = create_connection(&db_path)?;
|
|
|
|
let ollama_config = OllamaConfig {
|
|
base_url: config.embedding.base_url.clone(),
|
|
model: config.embedding.model.clone(),
|
|
..OllamaConfig::default()
|
|
};
|
|
let client = OllamaClient::new(ollama_config);
|
|
|
|
client.health_check().await?;
|
|
|
|
if full {
|
|
conn.execute_batch(
|
|
"BEGIN;
|
|
DELETE FROM embedding_metadata;
|
|
DELETE FROM embeddings;
|
|
COMMIT;",
|
|
)?;
|
|
} else if retry_failed {
|
|
conn.execute(
|
|
"UPDATE embedding_metadata SET last_error = NULL, attempt_count = 0
|
|
WHERE last_error IS NOT NULL",
|
|
[],
|
|
)?;
|
|
}
|
|
|
|
let model_name = &config.embedding.model;
|
|
let result = embed_documents(&conn, &client, model_name, progress_callback).await?;
|
|
|
|
Ok(EmbedCommandResult {
|
|
embedded: result.embedded,
|
|
failed: result.failed,
|
|
skipped: result.skipped,
|
|
})
|
|
}
|
|
|
|
pub fn print_embed(result: &EmbedCommandResult) {
|
|
println!("{} Embedding complete", style("done").green().bold(),);
|
|
println!(" Embedded: {}", result.embedded);
|
|
if result.failed > 0 {
|
|
println!(" Failed: {}", style(result.failed).red());
|
|
}
|
|
if result.skipped > 0 {
|
|
println!(" Skipped: {}", result.skipped);
|
|
}
|
|
}
|
|
|
|
#[derive(Serialize)]
|
|
struct EmbedJsonOutput<'a> {
|
|
ok: bool,
|
|
data: &'a EmbedCommandResult,
|
|
}
|
|
|
|
pub fn print_embed_json(result: &EmbedCommandResult) {
|
|
let output = EmbedJsonOutput {
|
|
ok: true,
|
|
data: result,
|
|
};
|
|
println!("{}", serde_json::to_string(&output).unwrap());
|
|
}
|