feat(cl): Use condense plus context chat engine for FastAPI as default

.changeset/tasty-buckets-design.md

+---
+"create-llama": patch
+---
+
+Use condense plus context chat engine for FastAPI as default

packages/create-llama/templates/components/vectordbs/python/mongo/index.py

@@ -20,4 +20,4 @@ def get_chat_engine():
     )
     index = VectorStoreIndex.from_vector_store(store, service_context)
     logger.info("Finished connecting to index from MongoDB.")
-    return index.as_chat_engine(similarity_top_k=5)
+    return index.as_chat_engine(similarity_top_k=5, chat_mode="condense_plus_context")

packages/create-llama/templates/components/vectordbs/python/none/index.py

@@ -22,4 +22,4 @@ def get_chat_engine():
     storage_context = StorageContext.from_defaults(persist_dir=STORAGE_DIR)
     index = load_index_from_storage(storage_context, service_context=service_context)
     logger.info(f"Finished loading index from {STORAGE_DIR}")
-    return index.as_chat_engine()
+    return index.as_chat_engine(similarity_top_k=5, chat_mode="condense_plus_context")

packages/create-llama/templates/components/vectordbs/python/pg/index.py

@@ -13,4 +13,4 @@ def get_chat_engine():
     store = init_pg_vector_store_from_env()
     index = VectorStoreIndex.from_vector_store(store, service_context)
     logger.info("Finished connecting to index from PGVector.")
-    return index.as_chat_engine(similarity_top_k=5)
+    return index.as_chat_engine(similarity_top_k=5, chat_mode="condense_plus_context")