llamaindex-nativ

LlamaIndex integration for Nativ — AI-powered localization.

Give any LlamaIndex agent the ability to translate text, search translation memory, manage terminology, and more — all backed by your team's brand voice and style guides.

Installation

pip install llamaindex-nativ

Quick start

from llamaindex_nativ import NativToolSpec

spec = NativToolSpec()  # reads NATIV_API_KEY from env
tools = spec.to_tool_list()

# Use a single tool directly
result = spec.translate("Hello world", target_language="French")
print(result)
# Bonjour le monde
# Rationale: Standard greeting translated with neutral register.

Use with a LlamaIndex agent

from llamaindex_nativ import NativToolSpec
from llama_index.llms.openai import OpenAI
from llama_index.core.agent import ReActAgent

tools = NativToolSpec().to_tool_list()
llm = OpenAI(model="gpt-4o")
agent = ReActAgent.from_tools(tools, llm=llm, verbose=True)

response = agent.chat(
    "Translate 'Welcome back!' to French, German, and Japanese"
)

Available tools

Configuration

Pass api_key and base_url directly:

spec = NativToolSpec(api_key="nativ_...", base_url="https://api.usenativ.com")

Or set the environment variable:

export NATIV_API_KEY=nativ_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Use individual tools

from llamaindex_nativ import NativToolSpec

spec = NativToolSpec()

# Search translation memory
print(spec.search_translation_memory("Welcome"))
# Found 3 match(es):
# - [98% exact] "Welcome" -> "Bienvenue"
# - [85% fuzzy] "Welcome back" -> "Content de vous revoir"
# ...

# Get configured languages
print(spec.get_languages())
# Configured languages:
# - French (fr) -- formality: formal
# - German (de) -- formality: formal
# ...

License

MIT