langchain-amazon-nova
Official LangChain integration for Amazon Nova models.
Amazon Nova is a family of state-of-the-art foundation models from Amazon that includes text, multimodal, and image generation capabilities. This integration provides access to Nova models through LangChain's standardized chat model interface.
Installation
pip install -U langchain-amazon-nova
Or using uv:
uv add langchain-amazon-nova
Quick Start
from langchain_amazon_nova import ChatAmazonNova
# Initialize the model
model = ChatAmazonNova(
model="nova-pro-v1",
temperature=0.7,
)
# Use it like any LangChain chat model
response = model.invoke("What is the capital of France?")
print(response.content)
Environment Setup
Set your Nova API credentials:
export NOVA_API_KEY="your-api-key"
export NOVA_BASE_URL="https://api.nova.amazon.com/v1"
Documentation
For detailed API documentation and additional parameters, see: https://nova.amazon.com/dev/documentation
Supported Models
Amazon Nova offers several model variants:
- nova-micro-v1: Fast, efficient text model (128K context)
- nova-lite-v1: Lightweight multimodal model (300K context)
- nova-pro-v1: Balanced multimodal model (300K context)
- nova-premier-v1: Most capable multimodal model (300K context)
Features
- Text Generation: All models support text completion
- Streaming: Token-by-token streaming responses
- Async Support: Native async/await support
- Tool Calling: Function calling capabilities (most models)
- Multimodal Input: Image and video understanding (lite, pro, premier)
Example Usage
Basic Chat
from langchain_amazon_nova import ChatAmazonNova
model = ChatAmazonNova(model="nova-pro-v1")
messages = [
("system", "You are a helpful assistant."),
("human", "Explain quantum computing in simple terms."),
]
response = model.invoke(messages)
print(response.content)
Streaming
for chunk in model.stream(messages):
print(chunk.content, end="", flush=True)
Tool Calling
from pydantic import BaseModel, Field
class GetWeather(BaseModel):
'''Get weather for a location.'''
location: str = Field(description="City name")
model_with_tools = model.bind_tools([GetWeather])
response = model_with_tools.invoke("What's the weather in Tokyo?")
print(response.tool_calls)
Async
import asyncio
async def main():
response = await model.ainvoke(messages)
print(response.content)
asyncio.run(main())
📖 Documentation
- Integration Guide - Complete usage guide
- API Reference - Detailed API documentation
- Amazon Nova Docs - Official Nova documentation
📕 Releases & Versioning
See our Releases and Versioning policies.
💁 Contributing
As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
For detailed information on how to contribute, see the Contributing Guide.
Metadata
Release files for langchain-amazon-nova 1.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| langchain_amazon_nova-1.0.1.tar.gz | 91.3 kB | Without provenance | Details for langchain_amazon_nova-1.0.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| langchain_amazon_nova-1.0.1-py3-none-any.whl | Python 3 | none | any | Details for langchain_amazon_nova-1.0.1-py3-none-any.whl |
Total release size: 105.2 kB
Release files / langchain_amazon_nova-1.0.1.tar.gz
| Download URL | langchain_amazon_nova-1.0.1.tar.gz |
|---|---|
| Size | 91.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a283bfadbae8f688c33bb841493f312167561f16f303e307f4d87a1813c5f54c
|
|
BLAKE2b-256 checksum How to use checksums |
f61ae1a6a7d196bbaffc4e62ba25228973aa6a9ff07ed132731c576527641589
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Release files / langchain_amazon_nova-1.0.1-py3-none-any.whl
| Download URL | langchain_amazon_nova-1.0.1-py3-none-any.whl |
|---|---|
| Size | 14.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2e9e5dbcb5e748bc056519b6a331c89ebb764d7ea37f09886144b61727e99f0e
|
|
BLAKE2b-256 checksum How to use checksums |
42f934ef5ec38eb1520b890fa382e418a8937d0198e3612e0e2b997594736ac2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Security for langchain-amazon-nova 1.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.