chore: made inbuilt tools blocking calls into async non blocking calls (#1509)

# What does this PR do?
This PR converts blocking calls for in built tools like wolfram, brave,
tavily and bing into non blocking async calls
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
[Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.*]
pytest -s -v tool_runtime/test_builtin_tools.py --stack-config=together
--text-model=meta-llama/Llama-3.1-8B-Instruct
Used the command above to get the below results
<img width="1710" alt="image"
src="https://github.com/user-attachments/assets/76b0ca06-f6e4-45fa-a114-0449bef2325b"
/>


<img width="1389" alt="image"
src="https://github.com/user-attachments/assets/5220ccbb-7882-4240-b17e-f362ad46d25b"
/>

<img width="1432" alt="image"
src="https://github.com/user-attachments/assets/bb93a41e-e82a-4c98-a22d-6b0e320aa974"
/>

[//]: # (## Documentation)

---------

Co-authored-by: sarthakdeshpande <sarthak.deshpande@engati.com>

llama_stack/providers/remote/tool_runtime/bing_search/bing_search.py

@@ -7,7 +7,7 @@
 import json
 from typing import Any, Dict, List, Optional
 
-import requests
+import httpx
 
 from llama_stack.apis.common.content_types import URL
 from llama_stack.apis.tools import (
@@ -31,7 +31,7 @@ class BingSearchToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, NeedsRequestP
     async def initialize(self):
         pass
 
-    async def register_tool(self, tool: Tool):
+    async def register_tool(self, tool: Tool) -> None:
         pass
 
     async def unregister_tool(self, tool_id: str) -> None:
@@ -77,12 +77,13 @@ class BingSearchToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, NeedsRequestP
             "q": kwargs["query"],
         }
 
-        response = requests.get(
-            url=self.url,
-            params=params,
-            headers=headers,
-        )
-        response.raise_for_status()
+        async with httpx.AsyncClient() as client:
+            response = await client.get(
+                url=self.url,
+                params=params,
+                headers=headers,
+            )
+            response.raise_for_status()
 
         return ToolInvocationResult(content=json.dumps(self._clean_response(response.json())))
 

llama_stack/providers/remote/tool_runtime/brave_search/brave_search.py

@@ -6,7 +6,7 @@
 
 from typing import Any, Dict, List, Optional
 
-import requests
+import httpx
 
 from llama_stack.apis.common.content_types import URL
 from llama_stack.apis.tools import (
@@ -30,7 +30,7 @@ class BraveSearchToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, NeedsRequest
     async def initialize(self):
         pass
 
-    async def register_tool(self, tool: Tool):
+    async def register_tool(self, tool: Tool) -> None:
         pass
 
     async def unregister_tool(self, tool_id: str) -> None:
@@ -74,8 +74,13 @@ class BraveSearchToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, NeedsRequest
             "Accept": "application/json",
         }
         payload = {"q": kwargs["query"]}
-        response = requests.get(url=url, params=payload, headers=headers)
-        response.raise_for_status()
+        async with httpx.AsyncClient() as client:
+            response = await client.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(

llama_stack/providers/remote/tool_runtime/tavily_search/tavily_search.py

@@ -7,7 +7,7 @@
 import json
 from typing import Any, Dict, List, Optional
 
-import requests
+import httpx
 
 from llama_stack.apis.common.content_types import URL
 from llama_stack.apis.tools import (
@@ -30,7 +30,7 @@ class TavilySearchToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, NeedsReques
     async def initialize(self):
         pass
 
-    async def register_tool(self, tool: Tool):
+    async def register_tool(self, tool: Tool) -> None:
         pass
 
     async def unregister_tool(self, tool_id: str) -> None:
@@ -66,10 +66,12 @@ class TavilySearchToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, NeedsReques
 
     async def invoke_tool(self, tool_name: str, kwargs: Dict[str, Any]) -> ToolInvocationResult:
         api_key = self._get_api_key()
-        response = requests.post(
-            "https://api.tavily.com/search",
-            json={"api_key": api_key, "query": kwargs["query"]},
-        )
+        async with httpx.AsyncClient() as client:
+            response = await client.post(
+                "https://api.tavily.com/search",
+                json={"api_key": api_key, "query": kwargs["query"]},
+            )
+            response.raise_for_status()
 
         return ToolInvocationResult(content=json.dumps(self._clean_tavily_response(response.json())))
 

llama_stack/providers/remote/tool_runtime/wolfram_alpha/wolfram_alpha.py

@@ -7,7 +7,7 @@
 import json
 from typing import Any, Dict, List, Optional
 
-import requests
+import httpx
 
 from llama_stack.apis.common.content_types import URL
 from llama_stack.apis.tools import (
@@ -31,7 +31,7 @@ class WolframAlphaToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, NeedsReques
     async def initialize(self):
         pass
 
-    async def register_tool(self, tool: Tool):
+    async def register_tool(self, tool: Tool) -> None:
         pass
 
     async def unregister_tool(self, tool_id: str) -> None:
@@ -73,11 +73,9 @@ class WolframAlphaToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, NeedsReques
             "format": "plaintext",
             "output": "json",
         }
-        response = requests.get(
-            self.url,
-            params=params,
-        )
-
+        async with httpx.AsyncClient() as client:
+            response = await client.get(params=params, url=self.url)
+            response.raise_for_status()
         return ToolInvocationResult(content=json.dumps(self._clean_wolfram_alpha_response(response.json())))
 
     def _clean_wolfram_alpha_response(self, wa_response):