Skip to main content


Anyscale is a fully-managed Ray platform, on which you can build, deploy, and manage scalable AI and Python applications

This example goes over how to use LangChain to interact with Anyscale Endpoint.

##Installing the langchain packages needed to use the integration
%pip install -qU langchain-community
import os

from langchain.chains import LLMChain
from langchain_community.llms import Anyscale
from langchain_core.prompts import PromptTemplate
API Reference:LLMChain | Anyscale | PromptTemplate
template = """Question: {question}

Answer: Let's think step by step."""

prompt = PromptTemplate.from_template(template)
llm = Anyscale(model_name=ANYSCALE_MODEL_NAME)
llm_chain = prompt | llm
question = "When was George Washington president?"

llm_chain.invoke({"question": question})

With Ray, we can distribute the queries without asynchronized implementation. This not only applies to Anyscale LLM model, but to any other Langchain LLM models which do not have _acall or _agenerate implemented

prompt_list = [
"When was George Washington president?",
"Explain to me the difference between nuclear fission and fusion.",
"Give me a list of 5 science fiction books I should read next.",
"Explain the difference between Spark and Ray.",
"Suggest some fun holiday ideas.",
"Tell a joke.",
"What is 2+2?",
"Explain what is machine learning like I am five years old.",
"Explain what is artifical intelligence.",
import ray

def send_query(llm, prompt):
resp = llm.invoke(prompt)
return resp

futures = [send_query.remote(llm, prompt) for prompt in prompt_list]
results = ray.get(futures)

Was this page helpful?

You can leave detailed feedback on GitHub.