diff --git a/llama_toolchain/distribution/registry.py b/llama_toolchain/distribution/registry.py
index ceb101cd4..48124c7d1 100644
--- a/llama_toolchain/distribution/registry.py
+++ b/llama_toolchain/distribution/registry.py
@@ -33,6 +33,7 @@ COMMON_DEPENDENCIES = [
     "Pillow",
     "pydantic==1.10.13",
     "pydantic_core==2.18.2",
+    "python-dotenv",
     "python-openapi",
     "requests",
     "tiktoken",
diff --git a/llama_toolchain/inference/client.py b/llama_toolchain/inference/client.py
index 4e9dd5ee2..331580190 100644
--- a/llama_toolchain/inference/client.py
+++ b/llama_toolchain/inference/client.py
@@ -66,7 +66,7 @@ async def run_main(host: str, port: int, stream: bool):
     cprint(f"User>{message.content}", "green")
     iterator = client.chat_completion(
         ChatCompletionRequest(
-            model="Meta-Llama-3.1-8B-Instruct",
+            model="Meta-Llama3.1-8B-Instruct",
             messages=[message],
             stream=stream,
         )