Protocol Compatibility

LangChain with DEVUP AI

Build production-grade AI applications and autonomous agents with LangChain and DEVUP AI. Because DEVUP AI exposes a fully OpenAI-compatible REST API, you can use standard langchain-openai to access 200+ catalog models with LCEL chains, streaming, and tool calling without proprietary wrappers.

Get API Key LangChain Documentation

Under the hood: LangChain's ChatOpenAI class communicates directly with DEVUP AI's verified OpenAI-compatible endpoint at https://api.devupai.com/v1.

OpenAI Gateway Specs

Architecture Flow

How LangChain Integrates with DEVUP AI

Setting openai_api_base to https://api.devupai.com/v1directs all prompt executions, structured outputs, and streaming iterations to DEVUP AI's high-throughput inference cluster.

1. App Layer

LangChain LCEL

Prompts, Chains & Agents

2. Adapter

ChatOpenAI

langchain_openai client

3. Gateway

DEVUP AI /v1

https://api.devupai.com/v1

4. Execution

Target Model

DeepSeek-V4-Pro, Qwen, etc.

Installation

Install Packages

Install the standard langchain-openai package using pip:

bash

pip install langchain-openai

Configuration

Initialize ChatOpenAI Client

Configure ChatOpenAI with your DEVUP AI API key and point openai_api_base to the platform gateway:

python

import os
from langchain_openai import ChatOpenAI

# Initialize ChatOpenAI pointing to the DEVUP AI gateway
chat = ChatOpenAI(
    openai_api_key=os.environ["DEVUP_API_KEY"],
    openai_api_base="https://api.devupai.com/v1",
    model_name="deepseek-ai/DeepSeek-V4-Pro",
)

Tip: You can also set OPENAI_API_BASE="https://api.devupai.com/v1" and OPENAI_API_KEY directly in your environment to run standard LangChain code without specifying parameters.

Text Generation

One-Shot Generation with invoke

Execute standard chat completion calls using the unified invoke method:

python

from langchain_openai import ChatOpenAI

# Initialize the DEVUP AI endpoint
chat = ChatOpenAI(
    openai_api_key="your-devup-api-key",
    openai_api_base="https://api.devupai.com/v1",
    model_name="deepseek-ai/DeepSeek-V4-Pro",
)

response = chat.invoke("Hello, DEVUP AI!")
print(response.content)

Real-Time Streaming

Token Streaming with stream

Stream response tokens in real-time by setting streaming=True and iterating over response chunks:

python

from langchain_openai import ChatOpenAI

chat = ChatOpenAI(
    openai_api_key="your-devup-api-key",
    openai_api_base="https://api.devupai.com/v1",
    model_name="deepseek-ai/DeepSeek-V4-Pro",
    streaming=True,
)

for chunk in chat.stream("Explain quantum computing in 3 sentences."):
    print(chunk.content, end="", flush=True)

LCEL Composition

Building Pipelines with LCEL

Compose prompts, models, and parsers into production pipelines using the pipe (|) operator:

python

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

chat = ChatOpenAI(
    openai_api_key="your-devup-api-key",
    openai_api_base="https://api.devupai.com/v1",
    model_name="deepseek-ai/DeepSeek-V4-Pro",
)

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a senior {language} developer."),
    ("human", "{question}"),
])

chain = prompt | chat

response = chain.invoke({
    "language": "Python",
    "question": "What is the best way to handle async in Python 3.12?",
})

print(response.content)

Capabilities Matrix

Verified LangChain Features

ChatOpenAI & Invocation

Full compatibility with LangChain's standard OpenAI chat model integration.

Compatible with chat.invoke() and batching
Token-by-token streaming via chat.stream()
Async execution with ainvoke() and astream()

LCEL & Advanced Workflows

Composable pipeline orchestration with output parsing and tool calling.

Compatible with LangChain Expression Language (| operator)
Structured outputs with Pydantic via with_structured_output
Tool and function binding via bind_tools

Configuration Parameters

Parameter	Type	Default	Description
openai_api_base	str	"https://api.devupai.com/v1"	DEVUP AI OpenAI-compatible endpoint URL
openai_api_key	str	os.environ["DEVUP_API_KEY"]	Your DEVUP AI API key from dashboard
model_name	str	"deepseek-ai/DeepSeek-V4-Pro"	Any active model identifier from the DEVUP AI catalog
temperature	float	0.7	Sampling temperature between 0.0 and 2.0
streaming	bool	False	Enable real-time token streaming

Build AI Applications with LangChain Today

Get your API key, configure ChatOpenAI with our base URL, and build production chains with Algerian Dinar billing.

Get API Key View Documentation