langgraph-docs▌

22:T48c,<h1>langgraph-docs</h1>

<h2>Workflow</h2> <h3>1. Fetch the Documentation Index</h3> <p>Use <code>fetch_url</code> to read: <a href="https://docs.langchain.com/llms.txt" target="_blank" rel="ugc nofollow noopener">https://docs.langchain.com/llms.txt</a></p> <p>This returns a structured list of all available documentation with descriptions.</p> <h3>2. Select Relevant Documentation</h3> <p>Identify 2-4 most relevant URLs from the index. Prioritize:</p> <ul> <li><strong>Implementation questions</strong> — specific how-to guides</li> <li><strong>Conceptual questions</strong> — core concept pages</li> <li><strong>End-to-end examples</strong> — tutorials</li> <li><strong>API details</strong> — reference docs</li> </ul> <h3>3. Fetch and Apply</h3> <p>Use <code>fetch_url</code> on the selected URLs, then complete the user's request using the documentation content.</p> <p>If <code>fetch_url</code> fails or returns empty content, retry once. If it fails again, inform the user and suggest checking <a href="https://langchain-ai.github.io/langgraph/" target="_blank" rel="ugc nofollow noopener">https://langchain-ai.github.io/langgraph/</a> directly.</p>1d:["$","div",null,{"className":"prose prose-invert max-w-none prose-headings:font-semibold prose-headings:tracking-tight prose-h1:text-4xl prose-h1:mb-2 prose-h2:text-2xl prose-h2:mb-2 prose-h3:text-lg prose-h3:mb-2 prose-p:text-muted-foreground prose-li:text-muted-foreground prose-code:bg-muted prose-code:text-foreground prose-code:px-1 prose-code:py-0.5 prose-code:rounded-sm prose-code:text-sm prose-code:before:content-none prose-code:after:content-none prose-pre:bg-muted prose-pre:text-foreground prose-pre:border prose-pre:border-border prose-pre:rounded-md [&_table]:!border-[color:var(--border)] [&_th]:!border-[color:var(--border)] [&_td]:!border-[color:var(--border)]","dangerouslySetInnerHTML":{"__html":"$22"}}] 18:[["$","meta","0",{"charSet":"utf-8"}],["$","meta","1",{"name":"viewport","content":"width=device-width, initial-scale=1"}]] 16:null