diff --git a/templates/types/streaming/fastapi/README-template.md b/templates/types/streaming/fastapi/README-template.md
index 77fa879319be255a6cb422b65c0b9602e7125076..a91b9f15a4d1d359934c2987702f883514927b8a 100644
--- a/templates/types/streaming/fastapi/README-template.md
+++ b/templates/types/streaming/fastapi/README-template.md
@@ -11,13 +11,19 @@ poetry shell
 
 By default, we use the OpenAI LLM (though you can customize, see `app/context.py`). As a result you need to specify an `OPENAI_API_KEY` in an .env file in this directory.
 
-Example `backend/.env` file:
+Example `.env` file:
 
 ```
 OPENAI_API_KEY=<openai_api_key>
 ```
 
-Second, run the development server:
+Second, generate the embeddings of the documents in the `./data` directory:
+
+```
+python app/engine/generate.py 
+```
+
+Third, run the development server:
 
 ```
 python main.py
diff --git a/templates/types/streaming/fastapi/app/engine/constants.py b/templates/types/streaming/fastapi/app/engine/constants.py
index 6dba7d2e0b870bfbec91f19e054d775ab25ceb23..4180edc4b440cafc26aef00530dc3ba2af3cbdf6 100644
--- a/templates/types/streaming/fastapi/app/engine/constants.py
+++ b/templates/types/streaming/fastapi/app/engine/constants.py
@@ -1,4 +1,4 @@
-STORAGE_DIR = "./storage"  # directory to cache the generated index
-DATA_DIR = "./data"  # directory containing the documents to index
+STORAGE_DIR = "storage"  # directory to cache the generated index
+DATA_DIR = "data"  # directory containing the documents to index
 CHUNK_SIZE = 1024
 CHUNK_OVERLAP = 20
diff --git a/templates/types/streaming/fastapi/app/engine/generate.py b/templates/types/streaming/fastapi/app/engine/generate.py
index 3abb7491abe405d9d5377e37f78604ee1f9bd2b1..3c4cd6a9e310f3f2e2f7e4709e94b9073282f151 100644
--- a/templates/types/streaming/fastapi/app/engine/generate.py
+++ b/templates/types/streaming/fastapi/app/engine/generate.py
@@ -12,7 +12,8 @@ from llama_index import (
     VectorStoreIndex,
 )
 
-logger = logging.getLogger("uvicorn")
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger()
 
 
 def generate_datasource(service_context):