LangChain

Connect your LangChain model or chain to the Messaging API. Each incoming message starts a run, and Flow delivers its streamed answer as chat bubbles.

TypeScript

// npm install @flow-engineer/messaging @langchain/openai
import { ChatOpenAI } from "@langchain/openai";
import { FlowMessaging, contentText } from "@flow-engineer/messaging";

const flow = new FlowMessaging();
const model = new ChatOpenAI({ model: "gpt-4.1-mini" });

for await (const event of flow.events.stream({ types: ["message.received"] })) {
  const stream = await model.stream([
    ["system", "You are the assistant for Asha's Bakery. Answer in short messages."],
    ["human", contentText(event.data.message.content)],
  ]);
  await event.conversation.reply(stream); // reads each chunk's content
}

Python (webhook reply)

# pip install langchain-openai fastapi
# Plain HTTP, no Flow SDK; the Python SDK (pip install flow-messaging) wraps the same calls. This answers in the webhook response.
from fastapi import FastAPI, Request
from langchain_openai import ChatOpenAI

model = ChatOpenAI(model="gpt-4.1-mini")
app = FastAPI()

@app.post("/flow")
async def flow_webhook(request: Request):
    event = await request.json()  # verify Flow-Signature first: see Events and webhooks
    if event["type"] != "message.received":
        return {}
    text = event["data"]["message"]["content"].get("text", "")
    answer = await model.ainvoke([("system", "You are the assistant for Asha's Bakery."), ("human", text)])
    return {"reply": answer.content}  # a string is a basic message, sent exactly as written

How it fits

• Any runnable whose .stream() yields message chunks works with reply(): chat models, prompt.pipe(model) chains, and chains ending in a string output parser.
• The Python version answers in the webhook response (one round trip). Flow waits 10 seconds for the answer, so this suits fast chains; for slower ones answer {} at once and send later with POST /v0/conversations/{conversation_id}/basic. Flow sends the text exactly as written (it renders no markdown), so ask the model for plain text; the reply goes out as one message, so keep it within the channel’s text limit (4096 characters on Telegram). See Events and webhooks.
• Keep chat history per conversation.id, or read it from GET /v0/conversations/{conversation_id}/messages.
• To see each turn’s model and tool calls and get every reply graded, send this agent’s traces to Flow Observe: Traces from agent frameworks.

Full example

examples/langchain on GitHub.