Files
poimen-memory/crates/mem-cli/src/opensearch_client.rs
T
Story Crater Bot 56bee1915e chore: Archive completed task files (M0, M1, M3, M3.5, M4.1-2, M3.6.1)
Deleted 31 completed task files:
- M0.x: 8 tasks (cargo, domain types, recordsource, tokenizer, adapters, gate)
- M1.x: 8 tasks (llm-chat, standing-query, prompt template, parser, loop, log, e2e, gate)
- M3.x: 4 tasks (l2-synthesis, rerank, mem-query, gate)
- M3.5.x: 8 tasks (http-server, ingest, query, federation, skills, projects, rate-limiting, gate)
- M3.6.1: DocCorpusSource (heading-boundary chunking)
- M4.1-2: skill-draft, derived-filter

Updated INDEX.md:
- Removed M0 & M1 phase sections (archived in git history)
- Updated progress table: 65 active tasks (42 + 2🟡 + 21)
- Updated status: M0/M1 complete, M3/M3.5 gates passing, M4.1-2 done
- Noted M3.5.10 JWT auth implementation complete (awaiting image rollout)
- Cleaned up broken links to deleted task files

Total test count: 239 passing, 2 ignored (up from 196 at M3.4)
Ready for M4.3 gate composition, M5 post-training, M7 source connectors.
2026-08-27 20:25:05 -07:00

383 lines
11 KiB
Rust

use anyhow::{anyhow, Result};
use serde_json::{json, Value};
use std::sync::Arc;
use tokio::sync::RwLock;
/// OpenSearch client for hybrid search (semantic + lexical)
pub struct OpenSearchClient {
hosts: Vec<String>,
client: reqwest::Client,
cache: Arc<RwLock<SearchCache>>,
}
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
pub struct SearchResult {
pub id: String,
pub chunk: String,
pub score: f32,
pub source: String,
pub level: String,
pub breadcrumb: Vec<String>,
pub method: String, // "semantic", "lexical", or "hybrid"
}
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
pub struct HybridSearchResult {
pub results: Vec<SearchResult>,
pub total: usize,
pub query: String,
pub search_method: String,
}
struct SearchCache {
queries: std::collections::HashMap<String, (HybridSearchResult, std::time::Instant)>,
ttl_secs: u64,
}
impl OpenSearchClient {
/// Create new OpenSearch client
pub fn new(hosts: Vec<String>) -> Self {
let client = reqwest::Client::builder()
.timeout(std::time::Duration::from_secs(30))
.build()
.expect("Failed to create HTTP client");
Self {
hosts,
client,
cache: Arc::new(RwLock::new(SearchCache {
queries: std::collections::HashMap::new(),
ttl_secs: 300, // 5 minute cache
})),
}
}
/// Get the primary host
fn primary_host(&self) -> &str {
&self.hosts[0]
}
/// Index a document (called on vault changes)
pub async fn index_document(
&self,
doc_id: &str,
content: &str,
source: &str,
level: &str,
breadcrumb: Vec<String>,
jwt_token: &str,
) -> Result<()> {
let url = format!(
"https://{}/vault-*/_doc/{}",
self.primary_host(),
doc_id
);
let body = json!({
"content": content,
"source": source,
"level": level,
"breadcrumb": breadcrumb,
"indexed_at": chrono::Utc::now().to_rfc3339(),
});
let response = self
.client
.put(&url)
.header("Authorization", format!("Bearer {}", jwt_token))
.json(&body)
.send()
.await?;
if !response.status().is_success() {
return Err(anyhow!(
"OpenSearch index failed: {} {}",
response.status(),
response.text().await.unwrap_or_default()
));
}
// Invalidate cache after indexing
self.cache.write().await.queries.clear();
Ok(())
}
/// BM25 lexical search via OpenSearch
async fn lexical_search(
&self,
query: &str,
limit: usize,
jwt_token: &str,
) -> Result<Vec<(String, f32, String, String, Vec<String>)>> {
let url = format!("https://{}/vault-*/_search", self.primary_host());
let search_body = json!({
"size": limit * 2,
"query": {
"multi_match": {
"query": query,
"fields": ["content^2", "source", "breadcrumb"],
"fuzziness": "AUTO",
"operator": "or"
}
},
"_source": ["content", "source", "level", "breadcrumb"]
});
let response = self
.client
.get(&url)
.header("Authorization", format!("Bearer {}", jwt_token))
.header("Content-Type", "application/json")
.json(&search_body)
.send()
.await?;
if !response.status().is_success() {
return Err(anyhow!(
"OpenSearch search failed: {} {}",
response.status(),
response.text().await.unwrap_or_default()
));
}
let result: Value = response.json().await?;
let mut results = Vec::new();
if let Some(hits) = result["hits"]["hits"].as_array() {
for hit in hits {
let score = hit["_score"].as_f64().unwrap_or(0.0) as f32;
let source = &hit["_source"];
let id = hit["_id"].as_str().unwrap_or("").to_string();
let chunk = source["content"].as_str().unwrap_or("").to_string();
let src = source["source"].as_str().unwrap_or("").to_string();
let level = source["level"].as_str().unwrap_or("L0").to_string();
let breadcrumb: Vec<String> = source["breadcrumb"]
.as_array()
.map(|arr| {
arr.iter()
.filter_map(|v| v.as_str().map(|s| s.to_string()))
.collect()
})
.unwrap_or_default();
results.push((id, score, chunk, src, breadcrumb));
}
}
Ok(results)
}
/// Semantic search via pgvector (called from memory service)
/// This is separate - pgvector search happens in PostgreSQL
pub async fn semantic_search(
&self,
embedding: &[f32],
limit: usize,
jwt_token: &str,
) -> Result<Vec<(String, f32, String, String, Vec<String>)>> {
// NOTE: This is actually handled by pgvector in PostgreSQL
// This method is a placeholder for consistency
// The actual semantic search happens in crates/mem-cli/src/http_server.rs
Err(anyhow!(
"Semantic search must be done via pgvector in PostgreSQL, not OpenSearch"
))
}
/// Hybrid search: combine lexical (OpenSearch) + semantic (pgvector)
pub async fn hybrid_search(
&self,
query: &str,
semantic_results: Vec<(String, f32, String, String, Vec<String>)>,
jwt_token: &str,
limit: usize,
weights: &HybridWeights,
) -> Result<HybridSearchResult> {
// Check cache
{
let cache = self.cache.read().await;
if let Some((cached, timestamp)) = cache.queries.get(query) {
if timestamp.elapsed().as_secs() < cache.ttl_secs {
return Ok(cached.clone());
}
}
}
// Perform lexical search
let lexical_results = self
.lexical_search(query, limit, jwt_token)
.await
.unwrap_or_default();
// Combine results
let combined = self.combine_results(
semantic_results,
lexical_results,
limit,
weights,
);
let result = HybridSearchResult {
results: combined,
total: limit,
query: query.to_string(),
search_method: "hybrid".to_string(),
};
// Cache result
{
let mut cache = self.cache.write().await;
cache.queries.insert(query.to_string(), (result.clone(), std::time::Instant::now()));
}
Ok(result)
}
/// Combine semantic and lexical results with reranking
fn combine_results(
&self,
semantic: Vec<(String, f32, String, String, Vec<String>)>,
lexical: Vec<(String, f32, String, String, Vec<String>)>,
limit: usize,
weights: &HybridWeights,
) -> Vec<SearchResult> {
use std::collections::HashMap;
// Normalize scores to 0-1
let sem_max = semantic.iter().map(|(_, s, _, _, _)| s).cloned().fold(f32::NEG_INFINITY, f32::max);
let lex_max = lexical.iter().map(|(_, s, _, _, _)| s).cloned().fold(f32::NEG_INFINITY, f32::max);
let sem_norm = semantic.into_iter().map(|(id, s, chunk, src, bc)| {
let normalized = if sem_max > 0.0 { s / sem_max } else { 0.0 };
(id, normalized, chunk, src, bc)
}).collect::<Vec<_>>();
let lex_norm = lexical.into_iter().map(|(id, s, chunk, src, bc)| {
let normalized = if lex_max > 0.0 { s / lex_max } else { 0.0 };
(id, normalized, chunk, src, bc)
}).collect::<Vec<_>>();
// Combine with weighted average
let mut combined: HashMap<String, (f32, String, String, Vec<String>)> = HashMap::new();
for (id, sem_score, chunk, src, bc) in sem_norm {
let lex_score = lex_norm
.iter()
.find(|(lid, _, _, _, _)| lid == &id)
.map(|(_, s, _, _, _)| *s)
.unwrap_or(0.0);
let final_score = weights.semantic * sem_score + weights.lexical * lex_score;
combined.insert(id, (final_score, chunk, src, bc));
}
// Add lexical-only results
for (id, lex_score, chunk, src, bc) in lex_norm {
if !combined.contains_key(&id) {
let final_score = weights.lexical * lex_score;
combined.insert(id, (final_score, chunk, src, bc));
}
}
// Sort and take top-k
let mut results: Vec<_> = combined
.into_iter()
.map(|(id, (score, chunk, src, bc))| SearchResult {
id,
chunk,
score,
source: src,
level: "L1".to_string(),
breadcrumb: bc,
method: "hybrid".to_string(),
})
.collect();
results.sort_by(|a, b| b.score.partial_cmp(&a.score).unwrap());
results.truncate(limit);
results
}
/// Health check
pub async fn health(&self, jwt_token: &str) -> Result<bool> {
let url = format!("https://{}/_cluster/health", self.primary_host());
let response = self
.client
.get(&url)
.header("Authorization", format!("Bearer {}", jwt_token))
.send()
.await?;
Ok(response.status().is_success())
}
}
#[derive(Clone, Debug)]
pub struct HybridWeights {
pub semantic: f32, // 0.6 = 60%
pub lexical: f32, // 0.4 = 40%
}
impl Default for HybridWeights {
fn default() -> Self {
Self {
semantic: 0.6,
lexical: 0.4,
}
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_hybrid_weights_sum() {
let weights = HybridWeights::default();
assert!((weights.semantic + weights.lexical - 1.0).abs() < 0.01);
}
#[test]
fn test_combine_results_ranking() {
let client = OpenSearchClient::new(vec!["localhost:9200".to_string()]);
let semantic = vec![
(
"doc1".to_string(),
0.9,
"deployment content".to_string(),
"deploy.md".to_string(),
vec!["runbooks".to_string()],
),
(
"doc2".to_string(),
0.7,
"networking content".to_string(),
"network.md".to_string(),
vec!["docs".to_string()],
),
];
let lexical = vec![
(
"doc1".to_string(),
0.95,
"deployment content".to_string(),
"deploy.md".to_string(),
vec!["runbooks".to_string()],
),
];
let weights = HybridWeights::default();
let results = client.combine_results(semantic, lexical, 10, &weights);
assert_eq!(results.len(), 2);
assert_eq!(results[0].id, "doc1"); // doc1 has both semantic and lexical scores
assert!(results[0].score > results[1].score);
}
}