Perplexity with LangChain

import os

os.environ["PERPLEXITY_API_KEY"] = "your_api_key_here"

from langchain_perplexity import ChatPerplexity

chat = ChatPerplexity(model="sonar")

response = chat.invoke("What breakthroughs in fusion energy have been announced this year?")
print(response.content)

from langchain_perplexity import ChatPerplexity, WebSearchOptions

chat = ChatPerplexity(
    model="sonar-pro",
    web_search_options=WebSearchOptions(search_type="pro")
)

response = chat.invoke("How does the electoral college work?")

# Access reasoning steps
if reasoning := response.additional_kwargs.get("reasoning_steps"):
    for step in reasoning:
        print(f"Thought: {step['thought']}")

chat = ChatPerplexity(
    model="sonar",
    search_domain_filter=["wikipedia.org", "nature.com"],
    search_recency_filter="month",
    return_images=True
)

response = chat.invoke("Solar system planets")

# Access citations and images
print("Citations:", response.additional_kwargs.get("citations", []))
print("Images:", response.additional_kwargs.get("images", []))

for chunk in chat.stream("Explain quantum computing"):
    print(chunk.content, end="", flush=True)

from langchain_perplexity import PerplexitySearchRetriever

retriever = PerplexitySearchRetriever(k=5)

docs = retriever.invoke("What is nuclear fusion?")

for doc in docs:
    print(f"Title: {doc.metadata['title']}")
    print(f"URL: {doc.metadata['url']}")
    print(f"Content: {doc.page_content[:200]}...")
    print("---")

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser
from langchain_perplexity import ChatPerplexity, PerplexitySearchRetriever

llm = ChatPerplexity(model="sonar")
retriever = PerplexitySearchRetriever(k=3)

template = """Answer based on the following context:
{context}

Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)

def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)

rag_chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

answer = rag_chain.invoke("What is the current status of ITER?")
print(answer)

from langchain_perplexity import PerplexitySearchResults

tool = PerplexitySearchResults()

results = tool.invoke("LangChain framework")

for result in results:
    print(f"Title: {result['title']}")
    print(f"URL: {result['url']}")
    print(f"Snippet: {result['snippet'][:100]}...")
    print("---")

from langchain.chat_models import init_chat_model
from langchain_perplexity import PerplexitySearchResults
from langgraph.prebuilt import create_react_agent

model = init_chat_model(model="gpt-4o", model_provider="openai")
search_tool = PerplexitySearchResults()

agent = create_react_agent(model, [search_tool])

for step in agent.stream(
    {"messages": [("user", "What are the latest LangChain releases?")]},
    stream_mode="values",
):
    step["messages"][-1].pretty_print()