Merge branch 'main' into eval_api_final

llama_stack/distribution/datatypes.py

@@ -125,6 +125,13 @@ class LoggingConfig(BaseModel):
     )
 
 
+class AuthenticationConfig(BaseModel):
+    endpoint: str = Field(
+        ...,
+        description="Endpoint URL to validate authentication tokens",
+    )
+
+
 class ServerConfig(BaseModel):
     port: int = Field(
         default=8321,
@@ -140,6 +147,10 @@ class ServerConfig(BaseModel):
         default=None,
         description="Path to TLS key file for HTTPS",
     )
+    auth: Optional[AuthenticationConfig] = Field(
+        default=None,
+        description="Authentication configuration for the server",
+    )
 
 
 class StackRunConfig(BaseModel):

llama_stack/distribution/server/auth.py

@@ -0,0 +1,69 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import json
+from urllib.parse import parse_qs
+
+import httpx
+
+from llama_stack.log import get_logger
+
+logger = get_logger(name=__name__, category="auth")
+
+
+class AuthenticationMiddleware:
+    def __init__(self, app, auth_endpoint):
+        self.app = app
+        self.auth_endpoint = auth_endpoint
+
+    async def __call__(self, scope, receive, send):
+        if scope["type"] == "http":
+            headers = dict(scope.get("headers", []))
+            auth_header = headers.get(b"authorization", b"").decode()
+
+            if not auth_header or not auth_header.startswith("Bearer "):
+                return await self._send_auth_error(send, "Missing or invalid Authorization header")
+
+            api_key = auth_header.split("Bearer ", 1)[1]
+
+            path = scope.get("path", "")
+            request_headers = {k.decode(): v.decode() for k, v in headers.items()}
+
+            query_string = scope.get("query_string", b"").decode()
+            params = parse_qs(query_string)
+
+            auth_data = {
+                "api_key": api_key,
+                "request": {
+                    "path": path,
+                    "headers": request_headers,
+                    "params": params,
+                },
+            }
+
+            # Validate with authentication endpoint
+            try:
+                async with httpx.AsyncClient() as client:
+                    response = await client.post(self.auth_endpoint, json=auth_data)
+                    if response.status_code != 200:
+                        logger.warning(f"Authentication failed: {response.status_code}")
+                        return await self._send_auth_error(send, "Authentication failed")
+            except Exception:
+                logger.exception("Error during authentication")
+                return await self._send_auth_error(send, "Authentication service error")
+
+        return await self.app(scope, receive, send)
+
+    async def _send_auth_error(self, send, message):
+        await send(
+            {
+                "type": "http.response.start",
+                "status": 401,
+                "headers": [[b"content-type", b"application/json"]],
+            }
+        )
+        error_msg = json.dumps({"error": {"message": message}}).encode()
+        await send({"type": "http.response.body", "body": error_msg})

llama_stack/distribution/server/server.py

@@ -52,6 +52,7 @@ from llama_stack.providers.utils.telemetry.tracing import (
     start_trace,
 )
 
+from .auth import AuthenticationMiddleware
 from .endpoints import get_all_api_endpoints
 
 REPO_ROOT = Path(__file__).parent.parent.parent.parent
@@ -351,6 +352,11 @@ def main():
     if not os.environ.get("LLAMA_STACK_DISABLE_VERSION_CHECK"):
         app.add_middleware(ClientVersionMiddleware)
 
+    # Add authentication middleware if configured
+    if config.server.auth and config.server.auth.endpoint:
+        logger.info(f"Enabling authentication with endpoint: {config.server.auth.endpoint}")
+        app.add_middleware(AuthenticationMiddleware, auth_endpoint=config.server.auth.endpoint)
+
     try:
         impls = asyncio.run(construct_stack(config))
     except InvalidProviderError as e:

llama_stack/distribution/ui/page/distribution/datasets.py

@@ -5,7 +5,8 @@
 # the root directory of this source tree.
 
 import streamlit as st
-from modules.api import llama_stack_api
+
+from llama_stack.distribution.ui.modules.api import llama_stack_api
 
 
 def datasets():

llama_stack/distribution/ui/page/distribution/eval_tasks.py

@@ -5,7 +5,8 @@
 # the root directory of this source tree.
 
 import streamlit as st
-from modules.api import llama_stack_api
+
+from llama_stack.distribution.ui.modules.api import llama_stack_api
 
 
 def benchmarks():

llama_stack/distribution/ui/page/distribution/models.py

@@ -5,7 +5,8 @@
 # the root directory of this source tree.
 
 import streamlit as st
-from modules.api import llama_stack_api
+
+from llama_stack.distribution.ui.modules.api import llama_stack_api
 
 
 def models():

llama_stack/distribution/ui/page/distribution/providers.py

@@ -5,7 +5,8 @@
 # the root directory of this source tree.
 
 import streamlit as st
-from modules.api import llama_stack_api
+
+from llama_stack.distribution.ui.modules.api import llama_stack_api
 
 
 def providers():

llama_stack/distribution/ui/page/distribution/resources.py

@@ -4,14 +4,15 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from page.distribution.benchmarks import benchmarks
-from page.distribution.datasets import datasets
-from page.distribution.models import models
-from page.distribution.scoring_functions import scoring_functions
-from page.distribution.shields import shields
-from page.distribution.vector_dbs import vector_dbs
 from streamlit_option_menu import option_menu
 
+from llama_stack.distribution.ui.page.distribution.datasets import datasets
+from llama_stack.distribution.ui.page.distribution.eval_tasks import benchmarks
+from llama_stack.distribution.ui.page.distribution.models import models
+from llama_stack.distribution.ui.page.distribution.scoring_functions import scoring_functions
+from llama_stack.distribution.ui.page.distribution.shields import shields
+from llama_stack.distribution.ui.page.distribution.vector_dbs import vector_dbs
+
 
 def resources_page():
     options = [

llama_stack/distribution/ui/page/distribution/scoring_functions.py

@@ -5,7 +5,8 @@
 # the root directory of this source tree.
 
 import streamlit as st
-from modules.api import llama_stack_api
+
+from llama_stack.distribution.ui.modules.api import llama_stack_api
 
 
 def scoring_functions():

llama_stack/distribution/ui/page/distribution/shields.py

@@ -5,7 +5,8 @@
 # the root directory of this source tree.
 
 import streamlit as st
-from modules.api import llama_stack_api
+
+from llama_stack.distribution.ui.modules.api import llama_stack_api
 
 
 def shields():

llama_stack/distribution/ui/page/distribution/vector_dbs.py

@@ -5,7 +5,8 @@
 # the root directory of this source tree.
 
 import streamlit as st
-from modules.api import llama_stack_api
+
+from llama_stack.distribution.ui.modules.api import llama_stack_api
 
 
 def vector_dbs():

llama_stack/distribution/ui/page/evaluations/app_eval.py

@@ -8,8 +8,9 @@ import json
 
 import pandas as pd
 import streamlit as st
-from modules.api import llama_stack_api
-from modules.utils import process_dataset
+
+from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.utils import process_dataset
 
 
 def application_evaluation_page():

llama_stack/distribution/ui/page/evaluations/native_eval.py

@@ -8,7 +8,8 @@ import json
 
 import pandas as pd
 import streamlit as st
-from modules.api import llama_stack_api
+
+from llama_stack.distribution.ui.modules.api import llama_stack_api
 
 
 def select_benchmark_1():

llama_stack/distribution/ui/page/playground/chat.py

@@ -5,7 +5,8 @@
 # the root directory of this source tree.
 
 import streamlit as st
-from modules.api import llama_stack_api
+
+from llama_stack.distribution.ui.modules.api import llama_stack_api
 
 # Sidebar configurations
 with st.sidebar:

llama_stack/distribution/ui/page/playground/rag.py

@@ -7,9 +7,10 @@
 import streamlit as st
 from llama_stack_client.lib.agents.agent import Agent
 from llama_stack_client.lib.agents.event_logger import EventLogger
-from llama_stack_client.types.memory_insert_params import Document
-from modules.api import llama_stack_api
-from modules.utils import data_url_from_file
+from llama_stack_client.types.shared.document import Document
+
+from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.utils import data_url_from_file
 
 
 def rag_chat_page():