How to create Agent with ability to generate Image

[krisnagita]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

Here is my script:

def generator_image(query: str):
    model_image = VertexAIImageGeneratorChat(...)
    messages = [HumanMessage(content=[query])]
    response = model_image.invoke(messages)
    
    return response

@tool
def generator_image_tool(query: str) -> str:
    """
    Generate an image based on a text query using Vertex AI's Imagen model.
    """
    
    print("Triggering image generator! Loading...")
    result = generator_image(query=query)
    
    return result 

system_prompt = (
    "You are a supervisor tasked with managing a conversation between the"
    f" following workers: {members}. Given the following user request,"
    " respond with the worker to act next. Each worker will perform a"
    " task and respond with their results and status. When finished,"
    " respond with FINISH."
)

class Router(TypedDict):
    """Worker to route to next. If no workers needed, route to FINISH."""
    next: Literal["researcher", "image_generator", "FINISH"]

class State(MessagesState):
    next: str
    
model = AzureChatOpenAI(...)

def supervisor_node(state: State) -> Command[Literal["researcher", "image_generator", "__end__"]]:
    messages = [{"role": "system", "content": system_prompt},] + state["messages"]
    response = model.with_structured_output(Router).invoke(messages)
    goto = response["next"]
    
    if goto == "FINISH":
        goto = END

    return Command(goto=goto, update={"next": goto})

image_generator_agent = create_react_agent(
    model, tools=[generator_image_tool]
)

def image_generator_node(state: State) -> Command[Literal["supervisor"]]:
    result = image_generator_agent.invoke(state)
    
    return Command(
        update={
            "messages": [
                HumanMessage(content=result["messages"][-1].content, name="coder")
            ]
        },
        goto="supervisor",
    )

builder = StateGraph(State)

builder.add_node("supervisor", supervisor_node)
builder.add_node("researcher", research_node)
builder.add_node("image_generator", image_generator_node)

builder.add_edge(START, "supervisor")
builder.add_edge("supervisor", END)

graph = builder.compile()

for state in graph.stream({"messages": [("user", "Generate 1 soccer jersey")]}, subgraphs=True):
    print(state)
    print("----")

#p.s. I do not provide the script about research_node and other related
`

Description

Hi I'm developing an AI Agent that can research from RAG and generating Image. I develop it with langgraph, I got issue when trying to generate Image, the problem I'm facing is "This model's maximum context length is" due to Image Generation, is there any way or articles hat I could learn from to handle this issue?

Here is my error

System Info

langchain
langchain-community
langchain-google-vertexai
langchain-google-genai
langchain-openai
langchain-google-community
langgraph