Skip to main content

LangChain Integration

LangChain supports custom OpenAI-compatible endpoints. You can use Vexrail as the LLM provider in your LangChain application by configuring the base URL and custom headers.

JavaScript / TypeScript​

Installation​

npm install @langchain/openai

Setup​

import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({
  configuration: {
    baseURL: "https://api.vexrail.com/v1",
    defaultHeaders: {
      "x-publishable-key": process.env.VEXRAIL_PUBLISHABLE_KEY,
      "x-secret-key": process.env.VEXRAIL_SECRET_KEY,
      "x-conversation-id": "your-conversation-id",
    },
  },
  modelName: "gpt-4o-mini",
});

Usage​

const response = await model.invoke("What tools can help me manage a remote team?");
console.log(response.content);

Streaming​

const stream = await model.stream("Recommend a good project management tool.");

for await (const chunk of stream) {
  process.stdout.write(chunk.content.toString());
}

Python​

Installation​

pip install langchain-openai

Setup​

from langchain_openai import ChatOpenAI

model = ChatOpenAI(
    base_url="https://api.vexrail.com/v1",
    api_key="unused",
    model="gpt-4o-mini",
    default_headers={
        "x-publishable-key": "pk_live_your_publishable_key",
        "x-secret-key": "sk_live_your_secret_key",
        "x-conversation-id": "your-conversation-id",
    },
)

Usage​

response = model.invoke("What tools can help me manage a remote team?")
print(response.content)

Streaming​

for chunk in model.stream("Recommend a good project management tool."):
    print(chunk.content, end="")

Using with Chains​

Vexrail works with standard LangChain chains and agents. Any chain that uses a ChatOpenAI model can use Vexrail as its provider without modification to the chain logic.

import { ChatOpenAI } from "@langchain/openai";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { StringOutputParser } from "@langchain/core/output_parsers";

const model = new ChatOpenAI({
  configuration: {
    baseURL: "https://api.vexrail.com/v1",
    defaultHeaders: {
      "x-publishable-key": process.env.VEXRAIL_PUBLISHABLE_KEY,
      "x-secret-key": process.env.VEXRAIL_SECRET_KEY,
      "x-conversation-id": "your-conversation-id",
    },
  },
  modelName: "gpt-4o-mini",
});

const prompt = ChatPromptTemplate.fromMessages([
  ["system", "You are a helpful assistant."],
  ["human", "{input}"],
]);

const chain = prompt.pipe(model).pipe(new StringOutputParser());

const result = await chain.invoke({ input: "What is the best CRM for startups?" });
console.log(result);

Next Steps​