add langchain agent sample

Author: commit111

samples/agentic-langgraph/.devcontainer/Dockerfile

@@ -0,0 +1 @@
+FROM mcr.microsoft.com/devcontainers/typescript-node:22-bookworm

samples/agentic-langgraph/.devcontainer/devcontainer.json

@@ -0,0 +1,11 @@
+{
+  "build": {
+    "dockerfile": "Dockerfile",
+    "context": ".."
+  },
+  "features": {
+    "ghcr.io/defanglabs/devcontainer-feature/defang-cli:1.0.4": {},
+    "ghcr.io/devcontainers/features/docker-in-docker:2": {},
+    "ghcr.io/devcontainers/features/aws-cli:1": {}
+  }
+}

samples/agentic-langgraph/.github/workflows/deploy.yaml

@@ -0,0 +1,25 @@
+name: Deploy
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  deploy:
+    environment: playground
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      id-token: write
+
+    steps:
+    - name: Checkout Repo
+      uses: actions/checkout@v4
+
+    - name: Deploy
+      uses: DefangLabs/[email protected]
+      with:
+        config-env-vars: TAVILY_API_KEY
+      env:
+        TAVILY_API_KEY: ${{ secrets.TAVILY_API_KEY }}

samples/agentic-langgraph/README.md

@@ -0,0 +1,57 @@
+# Agentic LangGraph
+
+[![1-click-deploy](https://raw.githubusercontent.com/DefangLabs/defang-assets/main/Logos/Buttons/SVG/deploy-with-defang.svg)](https://portal.defang.dev/redirect?url=https%3A%2F%2Fgithub.com%2Fnew%3Ftemplate_name%3Dsample-agentic-langgraph-template%26template_owner%3DDefangSamples)
+
+This sample demonstrates a LangGraph Agent application deployed with Defang. You can customize the agent's tools as needed. For example, it includes a Tavily Search tool for performing search queries, which requires a `TAVILY_API_KEY` (see [Configuration](#configuration) for setup details).
+
+## Prerequisites
+
+1. Download [Defang CLI](https://github.com/DefangLabs/defang)
+2. (Optional) If you are using [Defang BYOC](https://docs.defang.io/docs/concepts/defang-byoc) authenticate with your cloud provider account
+3. (Optional for local development) [Docker CLI](https://docs.docker.com/engine/install/)
+
+## Development
+
+To run the application locally, you can use the following command:
+
+```bash
+docker compose -f compose.dev.yaml up --build
+```
+
+## Configuration
+
+For this sample, you will need to provide the following [configuration](https://docs.defang.io/docs/concepts/configuration): 
+
+> Note that if you are using the 1-click deploy option, you can set these values as secrets in your GitHub repository and the action will automatically deploy them for you.
+
+### `TAVILY_API_KEY`
+A Tavily API key for accessing Tavily Search. 
+```bash
+defang config set TAVILY_API_KEY
+```
+
+## Deployment
+
+> [!NOTE]
+> Download [Defang CLI](https://github.com/DefangLabs/defang)
+
+### Defang Playground
+
+Deploy your application to the Defang Playground by opening up your terminal and typing:
+```bash
+defang compose up
+```
+
+### BYOC
+
+If you want to deploy to your own cloud account, you can [use Defang BYOC](https://docs.defang.io/docs/tutorials/deploy-to-your-cloud).
+
+---
+
+Title: Agentic LangGraph
+
+Short Description: A LangGraph Agent application that can use tools, deployed with Defang. 
+
+Tags: Agent, LangGraph, LangChain, AI, OpenAI, Tavily
+
+Languages: TypeScript

samples/agentic-langgraph/app/.dockerignore

@@ -0,0 +1,2 @@
+node_modules
+npm-debug.log

samples/agentic-langgraph/app/.gitignore

@@ -0,0 +1,2 @@
+node_modules
+.env

samples/agentic-langgraph/app/Dockerfile

@@ -0,0 +1,19 @@
+
+FROM node:22-bookworm-slim
+
+RUN apt-get update -qq \ 
+    && apt-get install -y curl \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY package*.json ./
+
+RUN npm install --omit=dev
+
+COPY . .
+
+EXPOSE 3000
+
+CMD ["npm", "start"]

samples/agentic-langgraph/app/agent.mts

@@ -0,0 +1,83 @@
+
+import { TavilySearch } from "@langchain/tavily";
+import { ChatOpenAI } from "@langchain/openai";
+import { HumanMessage, AIMessage } from "@langchain/core/messages";
+import { ToolNode } from "@langchain/langgraph/prebuilt";
+import { StateGraph, MessagesAnnotation } from "@langchain/langgraph";
+import { get } from "http";
+
+// Define the tools for the agent to use
+const tools = [new TavilySearch({ maxResults: 3 })];
+const toolNode = new ToolNode(tools);
+
+const baseUrl = process.env.LLM_URL || "https://api.openai.com/v1/";
+const baseModel =  process.env.LLM_MODEL || "gpt-4o-mini";
+
+// Create a model and give it access to the tools
+const model = new ChatOpenAI({
+  model: baseModel,
+  temperature: 0.7,
+  configuration: {
+    baseURL: baseUrl,
+  },
+}).bindTools(tools);
+
+// Define the function that determines whether to continue or not
+function shouldContinue({ messages }: typeof MessagesAnnotation.State) {
+  const lastMessage = messages[messages.length - 1] as AIMessage;
+
+  // If the LLM makes a tool call, then we route to the "tools" node
+  if (lastMessage.tool_calls?.length) {
+    return "tools";
+  }
+  // Otherwise, we stop (reply to the user) using the special "__end__" node
+  return "__end__";
+}
+
+// Define the function that calls the model
+async function callModel(state: typeof MessagesAnnotation.State) {
+  const response = await model.invoke(state.messages);
+  // console.log("Model response:", response);
+
+  // We return a list, because this will get added to the existing list
+  return { messages: [response] };
+}
+
+// Define a new graph
+const workflow = new StateGraph(MessagesAnnotation)
+  .addNode("agent", callModel)
+  .addEdge("__start__", "agent") // __start__ is a special name for the entrypoint
+  .addNode("tools", toolNode)
+  .addEdge("tools", "agent")
+  .addConditionalEdges("agent", shouldContinue);
+
+// Finally, we compile it into a LangChain Runnable.
+const app = workflow.compile();
+
+// Helper function to get agent output for a given input and optional previous messages
+const getAgentOutput = async (input: string, previousMessages: (HumanMessage | AIMessage)[] = []) => {
+  const initialState = {
+    messages: [...previousMessages, new HumanMessage(input)],
+  };
+  const finalState = await app.invoke(initialState);
+  return {
+    content: finalState.messages[finalState.messages.length - 1].content,
+    messages: finalState.messages,
+  };
+};
+
+// Helper function to get agent output as a readablestring
+export const getAgentOutputAsString = async (input: string, previousMessages: (HumanMessage | AIMessage)[] = []) => {
+  return getAgentOutput(input, previousMessages).then(result => result.content);
+};
+
+// // Example usage:
+// (async () => {
+//   // First query
+//   const firstResult = await getAgentOutput("what is the weather in sf");
+//   console.log(firstResult.content);
+
+//   // Follow-up query with context
+//   const secondResult = await getAgentOutput("what about ny", firstResult.messages);
+//   console.log(secondResult.content);
+// })();