Skip to content

Conversation

@5herlocked
Copy link
Contributor

Overview

Documentation for Amazon Nova Provider

Type of change

Type: New Documentation Page

  • Linear issue:
  • Slack thread:

Checklist

  • I have read the contributing guidelines
  • I have tested my changes locally using docs dev
  • All code examples have been tested and work correctly
  • I have used root relative paths for internal links
  • I have updated navigation in src/docs.json if needed

(Internal team members only / optional): Create a preview deployment as necessary using the Create Preview Branch workflow

Additional notes

@ccurme -- thank you so much for your support.

@github-actions github-actions bot added langchain For docs changes to LangChain python For content related to the Python version of LangChain projects oss docs-infra labels Dec 2, 2025
@5herlocked 5herlocked changed the title Added Amazon Nova provider documentation docs: Added Amazon Nova provider documentation Dec 2, 2025
@github-actions
Copy link
Contributor

github-actions bot commented Dec 2, 2025

❌ Import check failed

This PR contains imports from langchain_core that should be imported from langchain instead.

Detailed issues
Analyzing diff for import issues...
 Found 1 import issues:

File: src/oss/python/integrations/chat/amazon_nova.mdx
Line: 200
Issue: Import from langchain.tools instead of langchain_core.tools
Current:   from langchain_core.tools import tool
Suggested: from langchain.tools import tool
--------------------------------------------------------------------------------

 Found 1 import issues that need to be fixed.

Why this is a problem

The langchain package re-exports many modules and classes from langchain_core. When possible, imports should use langchain instead of langchain_core for:

  • Better user experience (single import source)
  • Consistency across documentation
  • Reduced cognitive load for users

How to fix

Replace the imports as suggested above. For example:

  • from langchain_core.messages import HumanMessage
  • from langchain.messages import HumanMessage

🤖 Automated check

This check is based on the latest analysis of langchain re-exports from langchain_core.

Copy link
Contributor

@ccurme ccurme left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Might be worth adding an entry to this page for discoverability (possibly re-naming it Amazon from AWS, I'm not very clear about the relation between the Amazon Nova and AWS).

Left some questions / nits that can be done in follow-up PRs if desired!

| Model | [Tool calling](/oss/langchain/tools) | [Structured output](/oss/langchain/structured-output/) | JSON mode | Local | [Multimodal](/oss/langchain/messages#multimodal) |
|-|-|-|-|-|-|
| [`ChatAnthropic`](/oss/integrations/chat/anthropic) ||||||
| [`ChatAmazonNova`](/oss/integrations/chat/amazon_nova) ||||| Model-dependent |
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
| [`ChatAmazonNova`](/oss/integrations/chat/amazon_nova) ||||| Model-dependent |
| [`ChatAmazonNova`](/oss/integrations/chat/amazon_nova) ||||| |

(I think we tend to say it's supported if the chat model supports it generally)

By default, @[`BaseChatModel.bind_tools`] validates that the model supports tool calling. To disable this validation:

```python
model_with_tools = model.bind_tools([GetWeather], strict=False)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

From what I see in the implementation, strict is propagated as a kwarg, so it ends up in invocation params. Is it true that it validates model support for tool calling? If strict is False and the model does not support tool calling, do we get a different error than we otherwise would?

Typically strict in bind_tools engages schema adherence for tool calls (see docs here).

| [`ChatGoogleGenerativeAI`](/oss/integrations/chat/google_generative_ai) ||||||
| [`ChatGroq`](/oss/integrations/chat/groq) ||||||
| [`ChatBedrock`](/oss/integrations/chat/bedrock) ||||||
| [`ChatAmazonNova`](/oss/integrations/chat/amazon_nova) ||||||
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

structured output may be supported already with the base implementation if you support the tool_choice param, might be worth a try.

@ccurme ccurme merged commit 194cd09 into langchain-ai:main Dec 2, 2025
9 of 10 checks passed
@5herlocked
Copy link
Contributor Author

@ccurme -- Thanks for the inputs. Already working on v1.1.0 of the provider -- structured output mode is definitely on the table, I also need to clean up / modify some of the tool use functionality because it's a little different because of it's dependency on Bedrock.

Will also likely have JS supported in due time.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

docs-infra langchain For docs changes to LangChain oss python For content related to the Python version of LangChain projects

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants