LangChain + Gonka AI - AI applications for pennies

A minimal example — connecting LangChain to Gonka:

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://gate.joingonka.ai/v1",
    api_key="jg-your-key",
    model="MiniMaxAI/MiniMax-M2.7",
)

response = llm.invoke("Explain what RAG is")
print(response.content)

That's it. Three lines — and your LangChain project runs through the decentralized Gonka network for pennies.

Installing dependencies:

pip install langchain langchain-openai

Recommendation: explicitly set max_tokens=8192 — this is the output cap through JoinGonka Gateway for MiniMax M2.7 and GLM-5.3 Flash (DeepSeek V4 Flash goes up to 32768). The context window is 200K tokens for MiniMax M2.7 (380K for DeepSeek V4 Flash, 390K for GLM-5.3 Flash) — keep this in mind when setting chunk_size in RAG pipelines.

RAG (Retrieval-Augmented Generation) is the most popular pattern for AI applications. You load documents, split them into chunks, create embeddings, retrieve relevant fragments, and generate an answer with context.

from langchain_openai import ChatOpenAI
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.chains import RetrievalQA
from langchain_community.vectorstores import FAISS
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.document_loaders import TextLoader

# 1. LLM via Gonka
llm = ChatOpenAI(
    base_url="https://gate.joingonka.ai/v1",
    api_key="jg-your-key",
    model="MiniMaxAI/MiniMax-M2.7",
    streaming=True,
)

# 2. Load and index documents
loader = TextLoader("docs/my_document.txt")
docs = loader.load()
splitter = RecursiveCharacterTextSplitter(chunk_size=1000)
chunks = splitter.split_documents(docs)

# 3. Vector store (local, free)
embeddings = HuggingFaceEmbeddings()
vectorstore = FAISS.from_documents(chunks, embeddings)

# 4. RAG chain
qa = RetrievalQA.from_chain_type(
    llm=llm,
    retriever=vectorstore.as_retriever(),
)

# 5. Query
result = qa.invoke("What is this document about?")
print(result["result"])

Cost: a single RAG pipeline request (retrieval + generation) uses ~2-5K LLM tokens. Through Gonka that's $0.00001-0.000024. Through OpenAI — $0.005-0.05. The difference — 1,300x.

For production systems handling thousands of requests a day, the savings add up to tens of thousands of dollars a month.

LangChain lets you build agents with tools. The network's models support native tool calling — agents work reliably, without parsing text responses.

from langchain_openai import ChatOpenAI
from langchain.agents import create_openai_tools_agent, AgentExecutor
from langchain.tools import tool
from langchain.prompts import ChatPromptTemplate

llm = ChatOpenAI(
    base_url="https://gate.joingonka.ai/v1",
    api_key="jg-your-key",
    model="MiniMaxAI/MiniMax-M2.7",
)

@tool
def calculator(expression: str) -> str:
    """Evaluates a math expression."""
    return str(eval(expression))

@tool
def search_web(query: str) -> str:
    """Searches the web for information."""
    return f"Search results for: {query}"

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant."),
    ("human", "{input}"),
    ("placeholder", "{agent_scratchpad}"),
])

agent = create_openai_tools_agent(llm, [calculator, search_web], prompt)
executor = AgentExecutor(agent=agent, tools=[calculator, search_web])

result = executor.invoke({"input": "What is 2**10 * 3.14?"})
print(result["output"])

The agent calls calculator, gets the result, and forms an answer. The whole cycle costs ~$0.00005 through Gonka. Through OpenAI — $0.01-0.05. For systems with thousands of users, that's a difference of tens of thousands of dollars.