Merge branch 'meta-llama:main' into main

docs/source/distributions/index.md

@@ -1,5 +1,4 @@
-# Llama Stack Distributions
-
+# Building Llama Stacks
 
 ```{toctree}
 :maxdepth: 2
@@ -12,6 +11,7 @@ ondevice_distro/index
 ## Introduction
 
 Llama Stack Distributions are pre-built Docker containers/Conda environments that assemble APIs and Providers to provide a consistent whole to the end application developer.
+
 These distributions allow you to mix-and-match providers - some could be backed by local code and some could be remote. This flexibility enables you to choose the optimal setup for your use case, such as serving a small model locally while using a cloud provider for larger models, all while maintaining a consistent API interface for your application.
 
 

docs/source/getting_started/index.md

@@ -149,7 +149,6 @@ if __name__ == "__main__":
 
 ## Next Steps
 
-- You can mix and match different providers for inference, memory, agents, evals etc. See [Building custom distributions](../distributions/index.md)
-- [Developer Cookbook](developer_cookbook.md)
+You can mix and match different providers for inference, memory, agents, evals etc. See [Building Llama Stacks](../distributions/index.md)
 
 For example applications and more detailed tutorials, visit our [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main/examples) repository.

llama_stack/providers/inline/agents/meta_reference/agent_instance.py

@@ -396,12 +396,6 @@ class ChatAgent(ShieldRunnerMixin):
         n_iter = 0
         while True:
             msg = input_messages[-1]
-            if msg.role == Role.user.value:
-                color = "blue"
-            elif msg.role == Role.ipython.value:
-                color = "yellow"
-            else:
-                color = None
             if len(str(msg)) > 1000:
                 msg_str = f"{str(msg)[:500]}...<more>...{str(msg)[-500:]}"
             else:

llama_stack/providers/inline/meta_reference/telemetry/config.py

@@ -18,4 +18,4 @@ class LogFormat(Enum):
 
 @json_schema_type
 class ConsoleConfig(BaseModel):
-    log_format: LogFormat = LogFormat.JSON
+    log_format: LogFormat = LogFormat.TEXT

requirements.txt

@@ -2,8 +2,8 @@ blobfile
 fire
 httpx
 huggingface-hub
-llama-models>=0.0.53
-llama-stack-client>=0.0.53
+llama-models>=0.0.54
+llama-stack-client>=0.0.54
 prompt-toolkit
 python-dotenv
 pydantic>=2

setup.py

@@ -16,7 +16,7 @@ def read_requirements():
 
 setup(
     name="llama_stack",
-    version="0.0.53",
+    version="0.0.54",
     author="Meta Llama",
     author_email="llama-oss@meta.com",
     description="Llama Stack",