release(core): 0.3.62

Author: hntrl

docs/core_docs/docs/integrations/tools/tavily_crawl.mdx

@@ -0,0 +1,221 @@
+---
+sidebar_label: Tavily Crawl
+title: TavilyCrawl
+---
+
+export const quartoRawHtml = [
+  `
+<table>
+<colgroup>
+<col style="width: 22%" />
+<col style="width: 22%" />
+<col style="width: 27%" />
+<col style="width: 27%" />
+</colgroup>
+<thead>
+<tr>
+<th style="text-align: left;">Class</th>
+<th style="text-align: left;">Package</th>
+<th style="text-align: center;"><a href="https://python.langchain.com/docs/integrations/tools/tavily_search/">PY support</a></th>
+<th style="text-align: center;">Package latest</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td style="text-align: left;"><a href="https://api.js.langchain.com/classes/_langchain_tavily.TavilyCrawl.html">TavilyMap</a></td>
+<td style="text-align: left;"><a href="https://www.npmjs.com/package/@langchain/tavily"><code>@langchain/tavily</code></a></td>
+<td style="text-align: center;">✅</td>
+<td style="text-align: center;"><img src="https://img.shields.io/npm/v/@langchain/tavily?style=flat-square&amp;label=%20&amp;.png" alt="NPM - Version" /></td>
+</tr>
+</tbody>
+</table>
+`,
+];
+
+[Tavily](https://tavily.com/) is a search engine built specifically for
+AI agents (LLMs), delivering real-time, accurate, and factual results at
+speed. Tavily offers four key endpoints, one of which being Crawl, which
+provides a graph-based website traversal tool that can explore hundreds
+of paths in parallel with built-in extraction and intelligent discovery.
+
+This guide provides a quick overview for getting started with the Tavily
+[tool](../../../docs/integrations/tools/). For a complete breakdown of
+the Tavily tool, you can find more detailed documentation in the [API
+reference](https://v03.api.js.langchain.com/modules/_langchain_tavily.html).
+
+## Overview
+
+### Integration details
+
+<div dangerouslySetInnerHTML={{ __html: quartoRawHtml[0] }} />
+
+## Setup
+
+The integration lives in the `@langchain/tavily` package, which you can
+install as shown below:
+
+```mdx-code-block
+import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
+import Npm2Yarn from "@theme/Npm2Yarn";
+
+<IntegrationInstallTooltip></IntegrationInstallTooltip>
+
+<Npm2Yarn>
+  @langchain/tavily @langchain/core
+</Npm2Yarn>
+```
+
+### Credentials
+
+Set up an API key [here](https://app.tavily.com) and set it as an
+environment variable named `TAVILY_API_KEY`.
+
+```typescript
+process.env.TAVILY_API_KEY = "YOUR_API_KEY";
+```
+
+It’s also helpful (but not needed) to set up
+[LangSmith](https://smith.langchain.com/) for best-in-class
+observability:
+
+```typescript
+process.env.LANGSMITH_TRACING = "true";
+process.env.LANGSMITH_API_KEY = "your-api-key";
+```
+
+## Instantiation
+
+You can import and instantiate an instance of the `TavilyCrawl` tool
+like this:
+
+```typescript
+import { TavilyCrawl } from "@langchain/tavily";
+
+const tool = new TavilyCrawl({
+  maxDepth: 3,
+  maxBreadth: 50,
+  // extractDepth: "basic",
+  // format: "markdown",
+  // limit: 100,
+  // includeImages: false,
+  // allowExternal: false,
+});
+```
+
+## Invocation
+
+### [Invoke directly with args](../../../docs/concepts/tools)
+
+The Tavily crawl tool accepts the following arguments during invocation:
+
+- `url` (required): A natural language search query
+
+- The following arguments can also be set during invocation :
+  `instructions`, `selectPaths` , `selectDomains`, `excludePaths`,
+  `excludeDomains`, `allowExternal`, `categories`.
+
+```typescript
+await tool.invoke({
+  url: "https://docs.tavily.com",
+});
+```
+
+### [Invoke with ToolCall](../../../docs/concepts/tools)
+
+We can also invoke the tool with a model-generated `ToolCall`, in which
+case a `ToolMessage` will be returned:
+
+```typescript
+// This is usually generated by a model, but we'll create a tool call directly for demo purposes.
+const modelGeneratedToolCall = {
+  args: {
+    url: "https://docs.tavily.com",
+  },
+  id: "1",
+  name: tool.name,
+  type: "tool_call",
+};
+
+await tool.invoke(modelGeneratedToolCall);
+```
+
+## Chaining
+
+We can use our tool in a chain by first binding it to a [tool-calling
+model](../../../docs/how_to/tool_calling/) and then calling it:
+
+```mdx-code-block
+import ChatModelTabs from "@theme/ChatModelTabs";
+
+<ChatModelTabs customVarName="llm" />
+```
+
+```typescript
+import { HumanMessage } from "@langchain/core/messages";
+import { ChatPromptTemplate } from "@langchain/core/prompts";
+import { RunnableLambda } from "@langchain/core/runnables";
+
+const prompt = ChatPromptTemplate.fromMessages([
+  ["system", "You are a helpful assistant."],
+  ["placeholder", "{messages}"],
+]);
+
+const llmWithTools = llm.bindTools([tool]);
+
+const chain = prompt.pipe(llmWithTools);
+
+const toolChain = RunnableLambda.from(async (userInput: string, config) => {
+  const humanMessage = new HumanMessage(userInput);
+  const aiMsg = await chain.invoke(
+    {
+      messages: [new HumanMessage(userInput)],
+    },
+    config
+  );
+  const toolMsgs = await tool.batch(aiMsg.tool_calls, config);
+  return chain.invoke(
+    {
+      messages: [humanMessage, aiMsg, ...toolMsgs],
+    },
+    config
+  );
+});
+
+const toolChainResult = await toolChain.invoke("https://docs.tavily.com");
+```
+
+```typescript
+const { tool_calls, content } = toolChainResult;
+
+console.log(
+  "AIMessage",
+  JSON.stringify(
+    {
+      tool_calls,
+      content,
+    },
+    null,
+    2
+  )
+);
+```
+
+## Agents
+
+For guides on how to use LangChain tools in agents, see the
+[LangGraph.js](https://langchain-ai.github.io/langgraphjs/how-tos/#tool-calling)
+docs.
+
+## API reference
+
+For detailed documentation of all Tavily Crawl API features and
+configurations head to the API reference:
+
+https://docs.tavily.com/documentation/api-reference/endpoint/crawl
+
+## Related
+
+- Tool [conceptual
+  guide](https://js.langchain.com/docs/concepts/tools/)
+
+- Tool [how-to guides](https://js.langchain.com/docs/how_to/#tools)