Connect LangChain to Gonka Broker

LangChain is a framework for building applications on top of language models. Its OpenAI chat-model integration accepts a custom base URL, so you can point it at Gonka Broker and build on open-source models: the only change from a standard OpenAI setup is the base URL, the key, and the model id.

The integration is the same in Python and JavaScript/TypeScript; only the package name and the constructor differ. Pick your language below.

Prerequisites

• A Gonka API key (starts with gnk-prx-). See Create a Gonka API Key.
• Python 3.9+ or Node.js 18+, depending on your stack.

Install and configure

Python

Install the OpenAI integration package:

pip install langchain-openai

Point ChatOpenAI at Gonka Broker:

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="moonshotai/Kimi-K2.6",
    base_url="https://proxy.gonkabroker.com/v1",
    api_key="gnk-prx-your-api-key",
)

response = llm.invoke("Say hello from Gonka Broker.")
print(response.content)

JavaScript / TypeScript

Install the OpenAI integration package:

npm install @langchain/openai

Point ChatOpenAI at Gonka Broker:

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

const llm = new ChatOpenAI({
  model: "moonshotai/Kimi-K2.6",
  apiKey: "gnk-prx-your-api-key",
  configuration: {
    baseURL: "https://proxy.gonkabroker.com/v1",
  },
});

const response = await llm.invoke("Say hello from Gonka Broker.");
console.log(response.content);

The model must match a Gonka-supported id exactly, for example moonshotai/Kimi-K2.6 or MiniMaxAI/MiniMax-M2.7 (see Supported Models). Once the model is configured, use it anywhere a LangChain chat model goes: chains, agents, and LCEL pipelines all work unchanged.

Embeddings for RAG

LangChain’s OpenAIEmbeddings works with Gonka Broker the same way: same base URL and key, with BAAI/bge-m3 as the model (see Embeddings & RAG). The embeddings drop into any LangChain vector store.

Python

from langchain_openai import OpenAIEmbeddings
from langchain_core.vectorstores import InMemoryVectorStore

embeddings = OpenAIEmbeddings(
    model="BAAI/bge-m3",
    base_url="https://proxy.gonkabroker.com/v1",
    api_key="gnk-prx-your-api-key",
    check_embedding_ctx_length=False,
)

store = InMemoryVectorStore(embeddings)
store.add_texts([
    "Gonka Broker bills in USD per token.",
    "The Eiffel Tower is in Paris.",
])
print(store.similarity_search("How am I charged?", k=1)[0].page_content)

check_embedding_ctx_length=False is required: without it, LangChain pre-tokenizes your text with tiktoken and sends token arrays instead of strings, which the API rejects with a 400.

JavaScript / TypeScript

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

const embeddings = new OpenAIEmbeddings({
  model: "BAAI/bge-m3",
  apiKey: "gnk-prx-your-api-key",
  configuration: {
    baseURL: "https://proxy.gonkabroker.com/v1",
  },
});

const vector = await embeddings.embedQuery("How am I charged?");
console.log(vector.length); // 1024

No extra flags needed; the JS client sends plain strings. Pass the embeddings object to any LangChain vector store (MemoryVectorStore, Chroma, pgvector, …) to build retrieval.

Verify

Run the snippet above. A printed reply confirms LangChain is reaching Gonka Broker through your key.

Troubleshooting

• 401 / invalid API key: wrong or paused key. Create a fresh one from Create a Gonka API Key.
• Model not found / unsupported: the model must match a model Gonka Broker serves exactly (see Supported Models).
• Connection errors: confirm the base URL is exactly https://proxy.gonkabroker.com/v1.
• 400 “input must be a string or a non-empty array of strings” on embeddings: Python’s OpenAIEmbeddings sent tiktoken token arrays instead of text. Set check_embedding_ctx_length=False (see the embeddings section above).
• Looking for the model’s thinking: reasoning models return their thinking in a separate reasoning response field, never inside content — the text LangChain returns is clean answer text. To skip thinking entirely (shorter, cheaper responses), see reasoning control.