langchain-empiriolabs

This package contains the LangChain integration for EmpirioLabs AI.

EmpirioLabs AI is specialized AI model hosting for open, proprietary, and custom stacks. Every model it serves is listed, with its ID and price, in the live catalog at empiriolabs.ai/models.

Installation

pip install -U langchain-empiriolabs

Set your API key as an environment variable:

export EMPIRIOLABS_API_KEY="your-api-key"

You can create a key from the EmpirioLabs AI dashboard.

Chat models

ChatEmpirioLabs wraps the EmpirioLabs chat completions API.

from langchain_empiriolabs import ChatEmpirioLabs

llm = ChatEmpirioLabs(model="MODEL_ID")  # any chat model ID from empiriolabs.ai/models

response = llm.invoke("Explain backpropagation in one paragraph.")
print(response.content)

Streaming:

for chunk in llm.stream("Write a haiku about the sea."):
    print(chunk.content, end="", flush=True)

Tool calling:

from pydantic import BaseModel, Field

class GetWeather(BaseModel):
    """Get the current weather in a given location."""

    location: str = Field(..., description="The city and state, e.g. San Francisco, CA")

llm_with_tools = llm.bind_tools([GetWeather])
print(llm_with_tools.invoke("What is the weather in SF?").tool_calls)

Available models

Any chat model ID from the live catalog works: empiriolabs.ai/models, or GET https://api.empiriolabs.ai/v1/models from code. The catalog changes as models are added and retired, so this page names none.

Reasoning models place their chain-of-thought in response.additional_kwargs["reasoning_content"].

Embeddings

EmpirioLabsEmbeddings wraps the EmpirioLabs embeddings API.

from langchain_empiriolabs import EmpirioLabsEmbeddings

embeddings = EmpirioLabsEmbeddings(model="MODEL_ID")  # any embedding model ID from empiriolabs.ai/models

vector = embeddings.embed_query("Hello, world!")
print(len(vector))

A request takes up to 2,048 texts; embed_documents sends 1,000 per request by default (chunk_size).

Configuration

License

MIT