LangChain

With langchain-exa

typesearch speaks Exa’s API, and LangChain’s Exa integration lets you set the base URL. Point it at typesearch, use a typesearch key, and every Exa tool and retriever searches our news index:

pip install langchain-exa

A search tool

import os
from langchain_exa import ExaSearchResults

search = ExaSearchResults(
    exa_api_key=os.environ["TYPESEARCH_API_KEY"],
    exa_base_url="https://api.typesearch.ai/compat/exa",
)

search.invoke({"query": "EU AI Act enforcement", "num_results": 5})

In an agent

from langchain.agents import create_agent

agent = create_agent(
    model="anthropic:claude-sonnet-4-5",
    tools=[search],
    system_prompt="Answer with recent news. Cite the source and link of every fact.",
)

agent.invoke({"messages": [{"role": "user", "content": "What changed in EU AI Act enforcement this week?"}]})

A retriever

from langchain_exa import ExaSearchRetriever

retriever = ExaSearchRetriever(
    exa_api_key=os.environ["TYPESEARCH_API_KEY"],
    exa_base_url="https://api.typesearch.ai/compat/exa",
    k=5,
    type="fast",
)

docs = retriever.invoke("EU AI Act enforcement")

ExaFindSimilarResults works the same way, with our similar endpoint behind it.

What to know

• Modes. type maps to our modes: fast, auto, neural and keyword run as fast, deep as deep.
• Page text costs extra. The Exa tools ask for the text of each result by default. On typesearch that’s a short excerpt, never the full page, billed per page ($0.20 per 1,000 pages) on top of the search ($1.40 per 1,000 in fast).
• What isn’t supported is accepted and reported in the X-Compat-Warnings header instead of failing: see Migrate from Exa for every parameter.
• Tone, essentials and structured answers are in the native API: see the API reference.