Add hosted app reference to README

README.md

@@ -2,25 +2,24 @@
 
 This repository provides a blueprint and full toolkit for a LangGraph-based agent service architecture. It includes a [LangGraph](https://langchain-ai.github.io/langgraph/) agent, a [FastAPI](https://fastapi.tiangolo.com/) service to serve it, a client to interact with the service, and a [Streamlit](https://streamlit.io/) app that uses the client to provide a chat interface.
 
-## Purpose
+This project offers a template for you to easily build and run your own agents using the LangGraph framework. It demonstrates a complete setup from agent definition to user interface, making it easier to get started with LangGraph-based projects by providing a full, robust toolkit.
 
-The purpose of this project is to offer a template for developers to easily build and run their own agents using the LangGraph framework. It demonstrates a complete setup from agent definition to user interface, making it easier to get started with LangGraph-based projects by providing a full, robust kit.
+## Overview
 
-## Structure
+### [Try the app!](https://agent-service-toolkit.streamlit.app/)
+
+[![Streamlit App](https://static.streamlit.io/badges/streamlit_badge_black_white.svg)](https://agent-service-toolkit.streamlit.app/)
+
+
+<a href="https://agent-service-toolkit.streamlit.app/"><img src="media/app_screenshot.png" width="600"></a>
 
-The repository is structured as follows:
 
-- `agent/agent.py`: Defines the LangGraph agent
-- `schema/__init__.py`: Defines the service schema
-- `service/service.py`: FastAPI service to serve the agent
-- `client/__init__.py`: Client to interact with the agent service
-- `streamlit_app.py`: Streamlit app providing a chat interface
 
 ### Architecture Diagram
 
 <img src="media/agent_architecture.png" width="600">
 
-## Key Features
+### Key Features
 
 1. **LangGraph Agent**: A customizable agent built using the LangGraph framework.
 2. **FastAPI Service**: Serves the agent with both streaming and non-streaming endpoints.
@@ -31,6 +30,16 @@ The repository is structured as follows:
 7. **Feedback Mechanism**: Includes a star-based feedback system integrated with LangSmith.
 8. **Docker Support**: Includes Dockerfiles and a docker compose file for easy development and deployment.
 
+### Key Files
+
+The repository is structured as follows:
+
+- `agent/agent.py`: Defines the LangGraph agent
+- `schema/__init__.py`: Defines the service schema
+- `service/service.py`: FastAPI service to serve the agent
+- `client/__init__.py`: Client to interact with the agent service
+- `streamlit_app.py`: Streamlit app providing a chat interface
+
 ## Why LangGraph?
 
 AI agents are increasingly being built with more explicitly structured and tightly controlled [Compound AI Systems](https://bair.berkeley.edu/blog/2024/02/18/compound-ai-systems/), with careful attention to the [cognitive architecture](https://blog.langchain.dev/what-is-a-cognitive-architecture/). At the time of this repo's creation, LangGraph seems like the most advanced open source framework for building such systems, with a high degree of control as well as support for features like concurrent execution, cycles in the graph, streaming results, built-in observability, and the rich ecosystem around LangChain.

agent/tools.py

@@ -1,16 +1,16 @@
+import inspect
 import math
 import numexpr
 import re
-from langchain_core.tools import tool
+from langchain_core.tools import tool, BaseTool
 from langchain_community.tools import DuckDuckGoSearchResults, ArxivQueryRun
 
-web_search = DuckDuckGoSearchResults()
+web_search = DuckDuckGoSearchResults(name="WebSearch")
 
 # Kinda busted since it doesn't return links
-arxiv_search = ArxivQueryRun()
+arxiv_search = ArxivQueryRun(name="ArxivSearch")
 
-@tool
-def calculator(expression: str) -> str:
+def calculator_func(expression: str) -> str:
     """Calculates a math expression using numexpr.
     
     Useful for when you need to answer questions about math using numexpr.
@@ -39,3 +39,6 @@ def calculator(expression: str) -> str:
             f'calculator("{expression}") raised error: {e}.'
             " Please try again with a valid numerical expression"
         )
+
+calculator: BaseTool = tool(calculator_func)
+calculator.name = "Calculator"