How to pass API response to prompt

[ayushk-singh]

Hi, I am new to langflow I want to pass the response from my API to prompt component
API response format: [ { "type": "reel", "avg_likes": 350, "avg_shares": 65, "avg_comments": 90 }, { "type": "carousel", "avg_likes": 185, "avg_shares": 45, "avg_comments": 32.5 }, { "type": "static", "avg_likes": 120, "avg_shares": 17.5, "avg_comments": 12.5 } ]

[dosubot[bot]]

Hey @ayushk-singh! I'm here to help you with any questions or issues you have. Let's tackle this together!

To pass the response from your API to a prompt component in Langflow, you can use the ChatInput component to receive the API response and then set it as the user_input for the PromptComponent. Here's a basic example of how you can achieve this:

from langflow.components.inputs import ChatInput
from langflow.components.models import OpenAIModelComponent
from langflow.components.outputs import ChatOutput
from langflow.components.prompts import PromptComponent
from langflow.graph import Graph

def basic_prompting_graph(api_response: str, template: str | None = None):
    if template is None:
        template = """Answer the user as if you were a pirate.

User: {user_input}

Answer:
"""
    chat_input = ChatInput()
    chat_input.message_response = api_response  # Set the API response here

    prompt_component = PromptComponent()
    prompt_component.set(
        template=template,
        user_input=chat_input.message_response,
    )

    openai_component = OpenAIModelComponent()
    openai_component.set(input_value=prompt_component.build_prompt)

    chat_output = ChatOutput()
    chat_output.set(input_value=openai_component.text_response)

    return Graph(start=chat_input, end=chat_output)

In this setup, api_response is the response from your API that you want to pass to the prompt component. You assign it to chat_input.message_response, which is then used as the user_input for the PromptComponent ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}