add brave tool provider (#653)

# What does this PR do?

Adds a new brave tool provider


## Test Plan

```
curl -X POST 'http://localhost:5000/alpha/toolgroups/register' \
-H 'Content-Type: application/json' \
-d '{
  "name": "search",
  "tool_group": {
    "type": "user_defined",
    "tools": [
      {
        "name": "brave_search",
        "description": "A web search tool",
        "parameters": [
          {
            "name": "query",
            "parameter_type": "string",
            "description": "The query to search"
          }
        ],
        "metadata": {},
        "tool_prompt_format": "json"
      }
    ]
  }
}'

curl -X POST 'http://localhost:5000/alpha/tool-runtime/invoke' \
-H 'Content-Type: application/json' \
-d '{
    "tool_id": "brave_search",
    "args": {
        "query": "who is meta ceo"
    }
}' | jq .content
  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
100  1973  100  1884  100    89  11288    533 --:--:-- --:--:-- --:--:-- 11885
"{'title': 'Mark Zuckerberg, Founder, Chairman and Chief Executive ...', 'url': 'https://about.meta.com/media-gallery/executives/mark-zuckerberg/', 'description': 'Not Logged In · Please log in to see this page', 'type': 'search_result'}\n{'title': 'Meta - Leadership & Governance', 'url': 'https://investor.fb.com/leadership-and-governance/', 'description': '<strong>Mark Zuckerberg</strong> is the founder, chairman and CEO of Meta, which he originally founded as Facebook in 2004. Mark is responsible for setting the overall direction and product strategy for the company. He leads the design of Meta&#x27;s services and development of its core technology and infrastructure.', 'type': 'search_result'}\n[{'type': 'video_result', 'url': '2372542949/', 'title': 'Mark Zuckerberg, the CEO of Meta, has officially joined the ...', 'description': \"Express Tribune, Karachi, Pakistan. 2,334,400 likes · 36,360 talking about this · 205 were here. The Express Tribune is Pakistan's #1 brand for breaking news in politics, sports, business, lifestyle\"}, {'type': 'video_result', 'url': 'https://www.youtube.com/watch?v=Y3oeQqtRvqk', 'title': \"Meta CEO: Mark Zuckerberg becomes World's Second Richest Person!\", 'description': 'Try VectorVest Risk-Free ➥➥➥ https://www.vectorvest.com/YTUse this link for a FREE Stock Analysis Report ➥➥➥ vectorvest.com/YTFSAVectorVest Merch Store ➥➥➥'}, {'type': 'video_result', 'url': '5348412224/', 'title': '#WATCH | Meta founder and CEO Mark Zuckerberg recently ...', 'description': 'See posts, photos and more on Facebook'}]"

curl -X POST 'http://localhost:5000/alpha/tool-runtime/invoke' \
-H 'Content-Type: application/json' -H 'X-LlamaStack-ProviderData: {"api_key": "<KEY>"}' \
-d '{
    "tool_id": "brave_search",
    "args": {
        "query": "who is meta ceo"
    }
}'
```

llama_stack/providers/inline/tool_runtime/brave_search/__init__.py

@@ -0,0 +1,20 @@
+# 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.
+
+from pydantic import BaseModel
+
+from .brave_search import BraveSearchToolRuntimeImpl
+from .config import BraveSearchToolConfig
+
+
+class BraveSearchToolProviderDataValidator(BaseModel):
+    api_key: str
+
+
+async def get_provider_impl(config: BraveSearchToolConfig, _deps):
+    impl = BraveSearchToolRuntimeImpl(config)
+    await impl.initialize()
+    return impl

llama_stack/providers/inline/tool_runtime/brave_search/brave_search.py

@@ -0,0 +1,123 @@
+# 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.
+
+from typing import Any, Dict, List
+
+import requests
+
+from llama_stack.apis.tools import Tool, ToolGroup, ToolInvocationResult, ToolRuntime
+from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.providers.datatypes import ToolsProtocolPrivate
+
+from .config import BraveSearchToolConfig
+
+
+class BraveSearchToolRuntimeImpl(
+    ToolsProtocolPrivate, ToolRuntime, NeedsRequestProviderData
+):
+    def __init__(self, config: BraveSearchToolConfig):
+        self.config = config
+
+    async def initialize(self):
+        pass
+
+    async def register_tool(self, tool: Tool):
+        if tool.identifier != "brave_search":
+            raise ValueError(f"Tool identifier {tool.identifier} is not supported")
+
+    async def unregister_tool(self, tool_id: str) -> None:
+        return
+
+    def _get_api_key(self) -> str:
+        if self.config.api_key:
+            return self.config.api_key
+
+        provider_data = self.get_request_provider_data()
+        if provider_data is None or not provider_data.api_key:
+            raise ValueError(
+                'Pass Search provider\'s API Key in the header X-LlamaStack-ProviderData as { "api_key": <your api key>}'
+            )
+        return provider_data.api_key
+
+    async def discover_tools(self, tool_group: ToolGroup) -> List[Tool]:
+        raise NotImplementedError("Brave search tool group not supported")
+
+    async def invoke_tool(
+        self, tool_id: str, args: Dict[str, Any]
+    ) -> ToolInvocationResult:
+        api_key = self._get_api_key()
+        url = "https://api.search.brave.com/res/v1/web/search"
+        headers = {
+            "X-Subscription-Token": api_key,
+            "Accept-Encoding": "gzip",
+            "Accept": "application/json",
+        }
+        payload = {"q": args["query"]}
+        response = requests.get(url=url, params=payload, headers=headers)
+        response.raise_for_status()
+        results = self._clean_brave_response(response.json())
+        content_items = "\n".join([str(result) for result in results])
+        return ToolInvocationResult(
+            content=content_items,
+        )
+
+    def _clean_brave_response(self, search_response):
+        clean_response = []
+        if "mixed" in search_response:
+            mixed_results = search_response["mixed"]
+            for m in mixed_results["main"][: self.config.max_results]:
+                r_type = m["type"]
+                results = search_response[r_type]["results"]
+                cleaned = self._clean_result_by_type(r_type, results, m.get("index"))
+                clean_response.append(cleaned)
+
+        return clean_response
+
+    def _clean_result_by_type(self, r_type, results, idx=None):
+        type_cleaners = {
+            "web": (
+                ["type", "title", "url", "description", "date", "extra_snippets"],
+                lambda x: x[idx],
+            ),
+            "faq": (["type", "question", "answer", "title", "url"], lambda x: x),
+            "infobox": (
+                ["type", "title", "url", "description", "long_desc"],
+                lambda x: x[idx],
+            ),
+            "videos": (["type", "url", "title", "description", "date"], lambda x: x),
+            "locations": (
+                [
+                    "type",
+                    "title",
+                    "url",
+                    "description",
+                    "coordinates",
+                    "postal_address",
+                    "contact",
+                    "rating",
+                    "distance",
+                    "zoom_level",
+                ],
+                lambda x: x,
+            ),
+            "news": (["type", "title", "url", "description"], lambda x: x),
+        }
+
+        if r_type not in type_cleaners:
+            return ""
+
+        selected_keys, result_selector = type_cleaners[r_type]
+        results = result_selector(results)
+
+        if isinstance(results, list):
+            cleaned = [
+                {k: v for k, v in item.items() if k in selected_keys}
+                for item in results
+            ]
+        else:
+            cleaned = {k: v for k, v in results.items() if k in selected_keys}
+
+        return str(cleaned)

llama_stack/providers/inline/tool_runtime/brave_search/config.py

@@ -0,0 +1,20 @@
+# 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.
+
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class BraveSearchToolConfig(BaseModel):
+    api_key: Optional[str] = Field(
+        default=None,
+        description="The Brave Search API Key",
+    )
+    max_results: int = Field(
+        default=3,
+        description="The maximum number of results to return",
+    )