Get Started with LangChain

from langchain_cerebras import ChatCerebras
import os

# Use Llama 3.3 70B for complex reasoning tasks
llama_70b = ChatCerebras(
    model="llama-3.3-70b",
    api_key=os.getenv("CEREBRAS_API_KEY"),
)

# Use Llama 3.1 8B for faster, lighter tasks
llama_8b = ChatCerebras(
    model="llama3.1-8b",
    api_key=os.getenv("CEREBRAS_API_KEY"),
)

# Use Qwen 3 32B for balanced performance
qwen_32b = ChatCerebras(
    model="qwen-3-32b",
    api_key=os.getenv("CEREBRAS_API_KEY"),
)

# Use GPT-OSS 120B for large-scale tasks
gpt_oss = ChatCerebras(
    model="gpt-oss-120b",
    api_key=os.getenv("CEREBRAS_API_KEY"),
)

from langchain_cerebras import ChatCerebras
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
import os

# Initialize the model
llm = ChatCerebras(
    model="llama-3.3-70b",
    api_key=os.getenv("CEREBRAS_API_KEY"),
)

# Create a RAG prompt template
template = """Answer the question based only on the following context:
{context}

Question: {question}

Answer:"""

prompt = ChatPromptTemplate.from_template(template)

# Create the RAG chain
rag_chain = (
    {"context": RunnablePassthrough(), "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

# Use the chain
context = "Cerebras has developed the world's largest and fastest AI processor, the Wafer-Scale Engine-3 (WSE-3)."
question = "What has Cerebras developed?"

answer = rag_chain.invoke({"context": context, "question": question})
print(answer)

import asyncio
from langchain_cerebras import ChatCerebras
from langchain_core.messages import HumanMessage
import os

async def get_response():
    llm = ChatCerebras(
        model="llama-3.3-70b",
        api_key=os.getenv("CEREBRAS_API_KEY"),
    )
    
    response = await llm.ainvoke([HumanMessage(content="Hello!")])
    return response.content

# Run async function
result = asyncio.run(get_response())
print(result)

from langchain_cerebras import ChatCerebras
from langchain.agents import AgentExecutor, create_react_agent
from langchain_core.tools import Tool
from langchain_core.prompts import PromptTemplate
import os

# Initialize the model
llm = ChatCerebras(
    model="llama-3.3-70b",
    api_key=os.getenv("CEREBRAS_API_KEY"),
)

# Define tools
def get_word_length(word: str) -> int:
    """Returns the length of a word."""
    return len(word)

tools = [
    Tool(
        name="GetWordLength",
        func=get_word_length,
        description="Returns the length of a word"
    )
]

# Define ReAct prompt directly (no hub needed)
react_prompt = PromptTemplate.from_template("""Answer the following questions as best you can. You have access to the following tools:

{tools}

Use the following format:

Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question

Begin!

Question: {input}
Thought: {agent_scratchpad}""")

# Create agent
agent = create_react_agent(llm, tools, react_prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

# Run agent
result = agent_executor.invoke({"input": "How many letters are in the word 'Cerebras'?"})
print(result)