docs: add guide for choosing between Graph and Functional APIs #1225
Conversation
|
Mintlify preview ID generated: preview-mdrxyl-1761933163-3caa308 |
|
Mintlify preview ID generated: preview-mdrxyl-1761935042-5451e86 |
There was a problem hiding this comment.
Pull Request Overview
This PR introduces a new conceptual guide comparing LangGraph's Graph API and Functional API to help users choose the appropriate approach for their use case.
Key Changes
- Adds comprehensive guide explaining when to use Graph API vs Functional API
- Includes practical code examples demonstrating different use cases for each API
- Provides migration guidance between the two approaches
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| src/oss/langgraph/choosing-apis.mdx | New conceptual guide with decision criteria, detailed comparisons, code examples, and migration strategies for choosing between LangGraph's Graph and Functional APIs |
| src/docs.json | Adds new guide to both Python and JavaScript navigation under "LangGraph APIs" section |
| # Graph API: Clear visualization of decision paths | ||
| from langgraph.graph import StateGraph | ||
| from typing import TypedDict | ||
|
|
||
| class AgentState(TypedDict): | ||
| messages: list | ||
| current_tool: str | ||
| retry_count: int | ||
|
|
||
| def should_continue(state): | ||
| if state["retry_count"] > 3: | ||
| return "end" | ||
| elif state["current_tool"] == "search": | ||
| return "process_search" | ||
| else: | ||
| return "call_llm" | ||
|
|
||
| workflow = StateGraph(AgentState) | ||
| workflow.add_node("call_llm", call_llm_node) | ||
| workflow.add_node("process_search", search_node) | ||
| workflow.add_conditional_edges("call_llm", should_continue) |
There was a problem hiding this comment.
This document contains only Python code examples but is referenced in both Python and JavaScript navigation paths. According to the custom coding guidelines (CodingGuidelineID: 1000000), files in /oss/ that contain language-specific content should use custom language fences (:::python and :::js) to generate language-specific outputs. All code blocks should be wrapped with :::python and ::: fences, and corresponding JavaScript/TypeScript examples should be added within :::js and ::: fences. This will ensure the build pipeline creates appropriate versions for both languages.
| { | ||
| "group": "LangGraph APIs", | ||
| "pages": [ | ||
| "oss/python/langgraph/choosing-apis", |
There was a problem hiding this comment.
The file path references a language-specific directory (oss/python/langgraph/choosing-apis) but the actual file is located at src/oss/langgraph/choosing-apis.mdx without language-specific subdirectories. According to the build pipeline, files in /oss/langgraph/ with custom language fences are automatically processed to create language-specific outputs at paths like /oss/python/langgraph/ and /oss/javascript/langgraph/. Ensure the source file uses the custom language fences so the build pipeline can generate the correct language-specific versions.
| { | ||
| "group": "LangGraph APIs", | ||
| "pages": [ | ||
| "oss/javascript/langgraph/choosing-apis", |
There was a problem hiding this comment.
The file path references a language-specific directory (oss/javascript/langgraph/choosing-apis) but the actual file is located at src/oss/langgraph/choosing-apis.mdx without language-specific subdirectories. According to the build pipeline, files in /oss/langgraph/ with custom language fences are automatically processed to create language-specific outputs at paths like /oss/python/langgraph/ and /oss/javascript/langgraph/. Ensure the source file uses the custom language fences so the build pipeline can generate the correct language-specific versions.
Closes #915