docs(llamaindex-sdk): add README for LlamaIndex SDK

DEVELOPER.md

@@ -105,6 +105,40 @@
     docker run -d toolbox:dev
     ```
 
+## Developing Toolbox SDKs
+
+Setting 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
+    ```
+
+    or
+
+    ```bash
+    cd genai-toolbox/sdks/llamaindex
+    ```
+
+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
+    ```
+
 ## CI/CD Details
 
 Cloud Build is used to run tests against Google Cloud resources in test project.

README.md

@@ -99,9 +99,30 @@ Once you've installed the Toolbox LangChain SDK, you can load tools:
 
 ```python
 from toolbox_langchain_sdk import ToolboxClient
+from aiohttp import ClientSession
 
 # update the url to point to your server
-client = ToolboxClient("http://127.0.0.1/")
+session = ClientSession()
+client = ToolboxClient("http://127.0.0.1:5000", session)
+
+# these tools can be passed to your application! 
+tools = await client.load_toolset()
+```
+
+</details>
+
+<details open>
+
+<summary>LlamaIndex</summary>
+Once you've installed the Toolbox LlamaIndex SDK, you can load tools: 
+
+```python
+from toolbox_llamaindex_sdk import ToolboxClient
+from aiohttp import ClientSession
+
+# update the url to point to your server
+session = ClientSession()
+client = ToolboxClient("http://127.0.0.1:5000", session)
 
 # these tools can be passed to your application! 
 tools = await client.load_toolset()

sdks/llamaindex/README.md

@@ -0,0 +1,76 @@
+# 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.
+
+<!-- TOC ignore:true -->
+## Table of Contents
+<!-- TOC -->
+
+- [Installation](#installation)
+- [Usage](#usage)
+- [Load a toolset](#load-a-toolset)
+- [Use with LlamaIndex](#use-with-llamaindex)
+- [Manual usage](#manual-usage)
+
+<!-- /TOC -->
+
+## Installation
+
+You can install the Toolbox SDK for LlamaIndex using `pip`.
+
+```bash
+pip install toolbox-llamaindex-sdk
+```
+
+> [!IMPORTANT]
+> This SDK is not yet available on PyPI. For now, install it from source by following these [instructions](/DEVELOPER.md#developing-toolbox-SDKs).
+
+## Usage
+
+Import and initialize the toolbox client.
+
+```python
+from toolbox_llamaindex_sdk import ToolboxClient
+from aiohttp import ClientSession
+
+session = ClientSession()
+# Replace with your Toolbox service's URL
+toolbox = ToolboxClient("http://127.0.0.1:5000", session)
+```
+
+## 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 LlamaIndex
+
+LlamaIndex 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 llama_index.llms.vertex import Vertex
+from llama_index.core.agent import ReActAgent
+
+model = Vertex(model="gemini-1.5-pro")
+
+# Initialize agent with tools
+agent = ReActAgent.from_tools(tools, llm=model, verbose=True)
+
+# Query the agent
+response = agent.query("Get some response from the agent.")
+```
+
+## Manual usage
+
+You can also execute a tool manually using the `acall` method.
+
+```python
+result = await tools[0].acall({"param1": "value1", "param2": "value2"})
+```

sdks/llamaindex/pyproject.toml

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