doc: Create a README file explaining the setup and sample usage with LangChain and LangGraph. (#45)

Author: anubhav756

DEVELOPER.md

@@ -0,0 +1,20 @@
+## Development
+
+Below are the details to set up a development environment:
+
+1. Clone the repository:
+    ```bash
+    git clone https://github.com/googleapis/genai-toolbox.git
+    ```
+1. Navigate to the SDK directory:
+    ```bash
+    cd genai-toolbox/sdks/langchain
+    ```
+1. Install the SDK and test dependencies:
+    ```bash
+    pip install -e .[test]
+    ```
+1. Run tests and/or contribute to the SDK's development.
+    ```bash
+    pytest
+    ```

README.md

@@ -0,0 +1,146 @@
+# GenAI Toolbox SDK
+
+This SDK allows you to seamlessly integrate the functionalities of
+[Toolbox](https://github.com/googleapis/genai-toolbox) into your LLM
+applications, enabling advanced orchestration and interaction with GenAI models.
+
+> [!NOTE] Currently the SDK only supports
+> [LangChain](https://python.langchain.com/docs/introduction/).
+
+<!-- TOC -->
+
+- [GenAI Toolbox SDK](#genai-toolbox-sdk)
+    - [Installation](#installation)
+    - [Usage](#usage)
+    - [Load a toolset](#load-a-toolset)
+    - [Use with LangChain](#use-with-langchain)
+    - [Use with LangGraph](#use-with-langgraph)
+        - [Represent Tools as Nodes](#represent-tools-as-nodes)
+        - [Connect Tools with LLM](#connect-tools-with-llm)
+    - [Manual usage](#manual-usage)
+
+<!-- /TOC -->
+
+
+## Installation
+
+You can install the Toolbox SDK for LangChain using `pip`.
+
+```bash
+pip install toolbox-langchain-sdk
+```
+
+> [!IMPORTANT] This SDK is not yet available on PyPI. For now, install it from
+> source by following these [installation instructions](#development) (up to
+> step 3).
+
+## Usage
+
+Import and initialize the toolbox client.
+
+```python
+from toolbox_langchain_sdk import ToolboxClient
+
+# Replace with your Toolbox service's URL
+toolbox = ToolboxClient("http://localhost:5000")
+```
+
+## Load a toolset
+
+You can load a toolsets, that are collections of related tools.
+
+```python
+# Load all tools
+tools = await toolbox.load_toolset()
+
+# Load a specific toolset
+tools = await toolbox.load_toolset("my-toolset")
+```
+
+## Use with LangChain
+
+LangChain's agents can dynamically choose and execute tools based on the user
+input. The user can include the tools loaded from the Toolbox SDK in the agent's
+toolkit.
+
+```python
+from langchain_google_vertexai import ChatVertexAI
+from langchain.agents import initialize_agent
+
+model = ChatVertexAI()
+
+# Initialize agent with tools
+agent = initialize_agent(tools, model)
+
+# Run the agent
+agent.run("Do something with the tools")
+```
+
+## Use with LangGraph
+
+The Toolbox SDK can be seamlessly integrated with LangGraph to enable the use of
+Toolbox service tools within a graph-based workflow. Using this SDK, we can
+follow the [official guide](https://langchain-ai.github.io/langgraph/) with
+minimal changes.
+
+### Represent Tools as Nodes
+Each tool generated by the SDK can be represented as a LangGraph node. The
+node's functionality would encapsulate the execution of the corresponding tool.
+
+```python
+from toolbox_sdk import ToolboxClient
+from langgraph.graph import StateGraph, MessagesState
+from langgraph.prebuilt import ToolNode
+
+# Define the function that calls the model
+def call_model(state: MessagesState):
+    messages = state['messages']
+    response = model.invoke(messages)
+    # We return a list, because this will get added to the existing list
+    return {"messages": [response]}
+
+model = ChatVertexAI()
+builder = StateGraph()
+tool_node = ToolNode(tools)
+
+builder.add_node("agent", call_model)
+builder.add_node("tools", tool_node)
+```
+
+### Connect Tools with LLM
+
+Now we can connect the tool nodes with LLM nodes. The LLM can decide which tool
+to use based on the user input or the context of the conversation. The output
+from a tool can then be fed back into the LLM for further processing or
+decision-making.
+
+```python
+from langgraph.graph import END, START
+
+# Define the function that determines whether to continue or not
+def should_continue(state: MessagesState) -> Literal["tools", END]:
+    messages = state['messages']
+    last_message = messages[-1]
+    # If the LLM makes a tool call, then we route to the "tools" node
+    if last_message.tool_calls:
+        return "tools"
+    # Otherwise, we stop (reply to the user)
+    return END
+
+builder.add_edge(START, "agent")
+builder.add_conditional_edges(
+    "agent",
+    should_continue,
+)
+builder.add_edge("tools", 'agent')
+
+graph = builder.compile()
+```
+
+## Manual usage
+
+You can also execute a tool manually using the `arun` method.
+
+```python
+result = await tools[0].arun({ "name": "Alice", "age": 30 })
+```

pyproject.toml

@@ -1,5 +1,5 @@
 [project]
-name = "toolbox_langchain_sdk"
+name = "toolbox-langchain-sdk"
 version="0.0.1"
 description = "Python SDK for interacting with the Toolbox service with LangChain"
 license = {file = "LICENSE"}