docs(env): update Gemini example model to gemini-3.1-flash-lite-preview

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.env.example

@@ -9,7 +9,7 @@ LLM_MODEL_NAME=qwen-plus
 # Get a free API key at: https://aistudio.google.com/
 # LLM_PROVIDER=gemini
 # LLM_API_KEY=AIza...
-# LLM_MODEL_NAME=gemini-2.0-flash
+# LLM_MODEL_NAME=gemini-3.1-flash-lite-preview
 
 # ===== Graph Backend =====
 # GRAPH_BACKEND=zep      (default) — Zep Cloud managed memory graph
@@ -25,6 +25,21 @@ ZEP_API_KEY=your_zep_api_key_here
 # NEO4J_URI=bolt://localhost:7687
 # NEO4J_USER=neo4j
 # NEO4J_PASSWORD=your_neo4j_password_here
+# GRAPHITI_BATCH_SIZE=10  # chunks per bulk call; higher = faster but more LLM parallelism
+
+# --- Embedding LLM (used by Graphiti for vector indexing) ---
+# Falls back to LLM_API_KEY / LLM_BASE_URL if not set.
+# Use a dedicated embedding deployment when your LLM_BASE_URL points to a generative model.
+# LLM_EMBED_API_KEY=your_embed_api_key_here
+# LLM_EMBED_BASE_URL=https://<resource>.cognitiveservices.azure.com/openai/deployments/<embed-deployment>/embeddings?api-version=2024-05-01-preview
+# LLM_EMBED_MODEL_NAME=text-embedding-3-small
+
+# --- Small/fast LLM (used by Graphiti for reranking and lightweight tasks) ---
+# Falls back to LLM_API_KEY / LLM_BASE_URL / LLM_MODEL_NAME if not set.
+# Use a cheaper model (e.g. gpt-4o-mini, gpt-5-mini) to reduce costs.
+# LLM_SMALL_API_KEY=your_small_api_key_here
+# LLM_SMALL_BASE_URL=https://<resource>.cognitiveservices.azure.com/openai/deployments/<small-model>/chat/completions?api-version=2024-05-01-preview
+# LLM_SMALL_MODEL_NAME=gpt-4o-mini
 
 # ===== 加速 LLM 配置（可选）=====
 # 注意如果不使用加速配置，env文件中就不要出现下面的配置项