Skip to content

Commit

Permalink
chore: amazon bedrock instead of aws bedrock
Browse files Browse the repository at this point in the history
  • Loading branch information
marcklingen committed Oct 10, 2024
1 parent 89fcad9 commit 7e0d746
Show file tree
Hide file tree
Showing 4 changed files with 21 additions and 18 deletions.
1 change: 1 addition & 0 deletions next.config.mjs
Original file line number Diff line number Diff line change
Expand Up @@ -181,6 +181,7 @@ const nonPermanentRedirects = [
["/docs/integrations/openai/python", "/docs/integrations/openai/python/get-started"],
["/docs/integrations/openai/js", "/docs/integrations/openai/js/get-started"],
["/docs/integrations/mirascope", "/docs/integrations/mirascope/tracing"],
["/docs/integrations/aws-bedrock", "/docs/integrations/amazon-bedrock"],
["/docs/flowise", "/docs/integrations/flowise"],
["/docs/litellm", "/docs/integrations/litellm/tracing"],
["/docs/integrations/litellm", "/docs/integrations/litellm/tracing"],
Expand Down
2 changes: 1 addition & 1 deletion pages/docs/integrations/_meta.tsx
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,6 @@ export default {
mirascope: "Mirascope",
flowise: "Flowise",
langflow: "Langflow",
"aws-bedrock": "AWS Bedrock",
"amazon-bedrock": "Amazon Bedrock",
"mistral-sdk": "Mistral SDK",
};
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
---
title: Observability and Metrics for AWS Bedrock
description: Open source observability for AWS Bedrock applications and the Bedrock SDK.
title: Observability and Metrics for Amazon Bedrock
description: Open source observability for Amazon Bedrock applications and the Bedrock SDK.
---

# AWS Bedrock Integration
# Amazon Bedrock Integration

**AWS Bedrock** ([AWS](https://aws.amazon.com/bedrock/)) is a fully managed AWS service that lets you use foundation models and custom models to generate text, images, and audio.
[**Amazon Bedrock**](https://aws.amazon.com/bedrock/) is a fully managed AWS service that lets you use foundation models and custom models to generate text, images, and audio.

When **using Langfuse with AWS Bedrock**, you can easily capture [detailed traces](/docs/tracing) and metrics for every request, giving you insights into the performance and behavior of your application.
When **using Langfuse with Amazon Bedrock**, you can easily capture [detailed traces](/docs/tracing) and metrics for every request, giving you insights into the performance and behavior of your application.

## Integration Options

There are a few ways through which you can capture traces and metrics for AWS Bedrock:
There are a few ways through which you can capture traces and metrics for Amazon Bedrock:

1. via an application framework that is integrated with Langfuse:

Expand All @@ -23,14 +23,15 @@ There are a few ways through which you can capture traces and metrics for AWS Be
3. via wrapping the Bedrock SDK with the [Langfuse Decorator](/docs/sdk/python/decorators) (_We are currently working on adding more documentation and a cookbook for this._)
4. via the [low-level Python SDK](/docs/sdk/python/low-level-sdk) to have full control over what is captured

## Can I monitor AWS Bedrock cost and token usage in Langfuse?
## Can I monitor Amazon Bedrock cost and token usage in Langfuse?

Yes, you can monitor cost and token usage of your Bedrock calls in Langfuse. The native integrations with LLM application frameworks and the LiteLLM proxy will automatically report token usage to Langfuse.

If you use the Langfuse decorator or the low-level Python SDK, you can [report](/docs/model-usage-and-cost) token usage and (optionally) also cost information directly.

You can define custom price information via the Langfuse dashboard or UI ([see docs](/docs/model-usage-and-cost)) to adjust to the exact pricing of your models on AWS Bedrock.
You can define custom price information via the Langfuse dashboard or UI ([see docs](/docs/model-usage-and-cost)) to adjust to the exact pricing of your models on Amazon Bedrock.

## Resources

- Metadocs, [Monitoring your Langchain app's cost using Bedrock with Langfuse](https://www.metadocs.co/2024/07/03/monitor-your-langchain-app-cost-using-bedrock-with-langfuse/), featuring Langchain integration and custom model price definitions for Bedrock models.
- [Self-hosting guide](/docs/deployment/self-host) to deploy Langfuse on AWS.
19 changes: 10 additions & 9 deletions pages/docs/integrations/overview.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -27,15 +27,16 @@ Objective:

## Packages integrated with Langfuse

| Name | Description |
| ------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
| [Instructor](/docs/integrations/instructor) | Library to get structured LLM outputs (JSON, Pydantic) |
| [DSPy](/docs/integrations/dspy) | Framework that systematically optimizes language model prompts and weights |
| [Dify](/docs/integrations/dify) | Open source LLM app development platform with no-code builder. |
| [Ollama](/docs/integrations/ollama) | Easily run open source LLMs on your own machine. |
| [Mirascope](/docs/integrations/mirascope) | Python toolkit for building LLM applications. |
| [Flowise](/docs/integrations/flowise) | JS/TS no-code builder for customized LLM flows. |
| [Langflow](/docs/integrations/langflow) | Python-based UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows. |
| Name | Description |
| --------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
| [Instructor](/docs/integrations/instructor) | Library to get structured LLM outputs (JSON, Pydantic) |
| [DSPy](/docs/integrations/dspy) | Framework that systematically optimizes language model prompts and weights |
| [Dify](/docs/integrations/dify) | Open source LLM app development platform with no-code builder. |
| [Ollama](/docs/integrations/ollama) | Easily run open source LLMs on your own machine. |
| [Amazon Bedrock](/docs/integrations/amazon-bedrock) | Run foundation and fine-tuned models on AWS. |
| [Mirascope](/docs/integrations/mirascope) | Python toolkit for building LLM applications. |
| [Flowise](/docs/integrations/flowise) | JS/TS no-code builder for customized LLM flows. |
| [Langflow](/docs/integrations/langflow) | Python-based UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows. |

Unsure which integration to choose? Ask us on [Discord](/discord) or in the chat.

Expand Down

0 comments on commit 7e0d746

Please sign in to comment.