🦜

LangChain

Use Promptly as your LLM backend in LangChain

Integrate Promptly with LangChain to automatically optimize costs on every LLM call. Smart routing, caching, and prompt compression work transparently.

Setup Guide

Install LangChain

Install the LangChain OpenAI integration package.

bash

pip install langchain-openai

Configure the Client

Point LangChain's OpenAI client to Promptly's endpoint. All chains, agents, and tools work automatically.

python

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-4o",
    api_key="sk-promptly-...",
    base_url="https://api.getpromptly.in/v1",
)

response = llm.invoke("Explain quantum computing simply.")
print(response.content)

Use with Chains & Agents

Every chain and agent call is automatically optimized - prompts are compressed, similar queries are cached, and simple requests route to cheaper models.

python

from langchain_core.prompts import PromptTemplate

prompt = PromptTemplate.from_template("Summarize: {text}")
chain = prompt | llm

result = chain.invoke({"text": "Your long document here..."})
print(result.content)