llama: update llama.cpp to latest version

.github/workflows/cicd.yaml

@@ -36,10 +36,12 @@ jobs:
 
   build_and_test:
     strategy:
+      fail-fast: false
       matrix:
         os: [ubuntu-latest, macos-13, windows-latest]
         rust-version: [stable]
     runs-on: ${{ matrix.os }}
+    timeout-minutes: 30
     steps:
       - name: Checkout repository
         uses: actions/checkout@v3

crates/llm-chain-hnsw/Cargo.toml

@@ -14,7 +14,7 @@ repository = "https://github.com/sobelio/llm-chain/"
 
 [dependencies]
 async-trait.workspace = true
-hnsw_rs = "0.1.19"
+hnsw_rs = "0.2"
 llm-chain = { path = "../llm-chain", version = "0.13.0", default-features = false }
 serde.workspace = true
 serde_json.workspace = true

crates/llm-chain-hnsw/examples/dump_load.rs

@@ -1,3 +1,5 @@
+use hnsw_rs::{hnswio::*, prelude::*};
+use std::path::PathBuf;
 use std::sync::Arc;
 
 use llm_chain::{
@@ -16,7 +18,7 @@ async fn main() {
     let hnsw_index_fn = "hnsw_index".to_string();
     let mut embeddings = llm_chain_openai::embeddings::Embeddings::default();
     let document_store = Arc::new(Mutex::new(InMemoryDocumentStore::<EmptyMetadata>::new()));
-    let mut hnsw_vs = HnswVectorStore::new(
+    let hnsw_vs = HnswVectorStore::new(
         HnswArgs::default(),
         Arc::new(embeddings),
         document_store.clone(),
@@ -56,12 +58,13 @@ async fn main() {
     // Load
     println!("Loading hnsw index from file");
     embeddings = llm_chain_openai::embeddings::Embeddings::default();
-    hnsw_vs = HnswVectorStore::load_from_file(
-        hnsw_index_fn,
-        Arc::new(embeddings),
-        document_store.clone(),
-    )
-    .unwrap();
+
+    let mut hnswio = HnswIo::new(PathBuf::from("."), hnsw_index_fn);
+    let hnsw_loaded = hnswio.load_hnsw::<f32, DistCosine>().unwrap();
+    let hnsw_vs =
+        HnswVectorStore::load_from_file(hnsw_loaded, Arc::new(embeddings), document_store.clone())
+            .unwrap();
+
     println!("Loaded!");
 
     let response = hnsw_vs