feat: fix Chinese text search and duplicate chunk_id bug

- Add helper functions to extract text from nested content structure
- Update SearchResult to include uuid field
- Add PostgreSQL function get_chunk_by_chunk_id_and_uuid to handle duplicate chunk_ids
- Update Qdrant search functions to extract uuid from payload
- Change embedding model to nomic-embed-text-v2-moe:latest
- Update Qdrant collection name to momentry_rule1
- Fix MongoDB authentication and disable cache for development
- Improve error handling in processor.rs
- Update documentation with new embedding model

src/playground.rs

@@ -2235,7 +2235,7 @@ async fn main() -> Result<()> {
                 .await
                 .context("Failed to init PostgreSQL")?;
             let qdrant = QdrantDb::init().await.context("Failed to init Qdrant")?;
-            let embedder = Embedder::new("nomic-embed-text:v1.5".to_string());
+            let embedder = Embedder::new("nomic-embed-text-v2-moe:latest".to_string());
 
             let target_uuid = if uuid == "all" {
                 None
@@ -2261,7 +2261,8 @@ async fn main() -> Result<()> {
                 for chunk in sentence_chunks {
                     let text = chunk
                         .content
-                        .get("text")
+                        .get("data")
+                        .and_then(|data| data.get("text"))
                         .and_then(|v| v.as_str())
                         .unwrap_or("");