LangGraph Builder - Utility and abstraction to quickly build graphs

[rvndbalaji]

Checked

• I searched existing ideas and did not find a similar one
• I added a very descriptive title
• I've clearly described the feature request and motivation for it

Feature request

In my org, I implemented a utility class to dynamically build LangGraph graphs
and abstracted away some of the common details

It is no means perfect, and is probably incomplete,
but is there a way for you guys to implement this in langchain-core?

I have this raw implementation here - https://gist.github.com/rvndbalaji/2f50bf3d2fc635bf2f36f71c724e3347

This can be used as a reference to implement a proper utility class

Motivation

• Found that it was difficult for new langgraph users to build agents using tutorials
• I found myself confused pretty often
• Eventually wrote this builder class so other devs in my org can use it and build graphs quickly

Proposal (If applicable)

I have this raw implementation here - https://gist.github.com/rvndbalaji/2f50bf3d2fc635bf2f36f71c724e3347

Usage Example

body = GraphConfig(
    graph_id=3,
    name="Graph",
    description="Graph",
    session_id=None,
    agents=[
        AgentConfig(
                    name="Researcher", 
                    prompt="You are a research assistant", 
                    llm="claude-sonnet-3.5", 
                    tools=[], 
                    color="#FF871F"
                   ),
        AgentConfig(
                    name="Writer", 
                    prompt="You are a great writer",
                    llm="claude-sonnet-3.5", 
                    tools=[], 
                    color="#FF871F"
                   ),
    ],
    edges=[
        GraphEdge(source="start", target="Researcher"),
         GraphEdge(source="Researcher", target="Writer"),
        GraphEdge(source="Writer", target="end")
    ]
)


graph = GraphBuilder(graph_config=body)
graph.build()
response = GraphResponse(
    config = graph.get_compiled_config(),
    base64 = graph.get_image(xray=True, mermaid=True)
)
response