feat(core): implement full memory pipeline (#11)

crates/mem-llm/src/embeddings.rs

@@ -0,0 +1,64 @@
+use anyhow::{anyhow, Result};
+use pgvector::Vector;
+use reqwest::Client;
+use serde::{Deserialize, Serialize};
+use std::env;
+
+/// Embeddings client for Ollama
+#[derive(Clone)]
+pub struct EmbeddingsClient {
+    base_url: String,
+    model: String,
+    #[allow(dead_code)]
+    http: Client,
+}
+
+#[derive(Debug, Serialize)]
+struct EmbeddingRequest {
+    model: String,
+    input: Vec<String>,
+}
+
+#[derive(Debug, Deserialize)]
+struct EmbeddingResponse {
+    embeddings: Vec<Vec<f32>>,
+    model: String,
+}
+
+impl EmbeddingsClient {
+    /// Create from environment
+    /// Uses api.riotpiao.com gateway (nomic-ai/nomic-embed-text-v2-moe model)
+    pub fn from_env() -> Result<Self> {
+        let base_url = env::var("LLM_API_BASE").unwrap_or_else(|_| "https://api.riotpiao.com".to_string());
+        let model = "nomic-ai/nomic-embed-text-v2-moe".to_string();
+
+        Ok(Self {
+            base_url,
+            model,
+            http: Client::new(),
+        })
+    }
+
+    /// Embed a single text string
+    pub async fn embed(&self, text: &str) -> Result<Vector> {
+        let embeddings = self.embed_batch(&[text.to_string()]).await?;
+        Ok(embeddings.into_iter().next().ok_or_else(|| anyhow::anyhow!("empty embedding response"))?)
+    }
+
+    /// Embed multiple texts in a batch using api.riotpiao.com gateway
+    pub async fn embed_batch(&self, texts: &[String]) -> Result<Vec<Vector>> {
+        let req = EmbeddingRequest {
+            model: self.model.clone(),
+            input: texts.to_vec(),
+        };
+
+        let url = format!("{}/v1/embeddings", self.base_url);
+        let resp: EmbeddingResponse = self.http.post(&url).json(&req).send().await?.json().await?;
+
+        Ok(resp
+            .embeddings
+            .into_iter()
+            .map(Vector::from)
+            .collect())
+    }
+}