From 02560ab8f7fb2f95162c72c228bfcfe32c60382e Mon Sep 17 00:00:00 2001 From: Willy Douhard Date: Fri, 29 Mar 2024 20:28:54 +0100 Subject: [PATCH] fix llama index example (#97) - also fix infinite rendering in the custom frontend example --- llama-index/app.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/llama-index/app.py b/llama-index/app.py index 7223a43e..e82addfe 100644 --- a/llama-index/app.py +++ b/llama-index/app.py @@ -11,6 +11,9 @@ ) from llama_index.llms.openai import OpenAI from llama_index.embeddings.openai import OpenAIEmbedding +from llama_index.core.query_engine.retriever_query_engine import RetrieverQueryEngine +from llama_index.core.callbacks import CallbackManager +from llama_index.core.service_context import ServiceContext openai.api_key = os.environ.get("OPENAI_API_KEY") @@ -33,7 +36,8 @@ async def start(): Settings.embed_model = OpenAIEmbedding(model="text-embedding-3-small") Settings.context_window = 4096 - query_engine = index.as_query_engine(streaming=True, similarity_top_k=2) + service_context = ServiceContext.from_defaults(callback_manager=CallbackManager([cl.LlamaIndexCallbackHandler()])) + query_engine = index.as_query_engine(streaming=True, similarity_top_k=2, service_context=service_context) cl.user_session.set("query_engine", query_engine) await cl.Message(