Files
librechat.ai/content/docs/configuration/pre_configured_ai/bedrock.mdx
Marco Beretta 4656b0116a feat: Migrate to Fumadocs, overhaul UI, and improve docs navigation (#500)
* feat: enhance accessibility and improve component structure across various files

* feat: enhance components with TypeScript typings and improve documentation

- Added TypeScript interface for Screenshot component props.
- Updated button component documentation for clarity.
- Removed unnecessary console log in ContainerScroll component.
- Added descriptive comments for FloatingDock and utility functions.
- Improved CSP headers in next.config.mjs for security.
- Cleaned up package.json by removing unused dependencies.
- Refactored _app.tsx to use AppProps for type safety.
- Updated meta configuration by removing hidden display property.
- Added API documentation comments for GitHub stats and subscription endpoints.
- Enhanced error handling in subscription API.
- Updated Tailwind CSS configuration with detailed comments.
- Cleaned up style.css by organizing and refining styles.
- Updated tsconfig.json to include TypeScript files for API routes.
- Added comments to Subscriber model and dbConnect utility for clarity.

* feat: add aria-labels to HeroLinks for improved accessibility

* feat: replace Twitter icon with X and add new X icon component

* chore: update code structure for better readability and maintenance

* chore: update .gitignore to include additional AI assistant files and Claude Flow generated files

* feat: replace sidebar emojis with Lucide icons, fix duplicate titles, and clean up codebase

- Add icon resolver (lib/icons.tsx) with 73 Lucide React icons mapped to string IDs
- Wire icon resolver into Fumadocs loader for automatic sidebar icon rendering
- Update all 19 meta.json files to use icon field instead of emoji prefixes
- Add icon frontmatter to all 162 MDX documentation pages
- Deduplicate adjacent sidebar icons (e.g. Search/ListFilter, Brain/Bookmark)
- Remove duplicate H1 headings from 154 MDX files (DocsTitle renders frontmatter)
- Add frontmatter to 33 files that were missing it
- Shorten overly long titles (agents, mcp, url_query)
- Rewrite /docs/local cards from old Nextra syntax to Fumadocs Card components
- Remove all emojis from Get Started and Features index pages
- Collapse sidebar folders by default (defaultOpenLevel: 0)
- Delete temporary debugging scripts, test specs, and screenshot artifacts
- Fix eslint errors in mdx-components, nextra-shims, tailwind config, and error page
- Update .gitignore to exclude test/debug artifacts

* feat: enhance accessibility and improve UI components

- Added aria-hidden attributes to social media icons in FooterMenu for better accessibility.
- Updated FooterMenu to use <footer> element for semantic HTML.
- Improved Carousel component by adding aria-labels to navigation buttons for better screen reader support.
- Modified OptionTable to use a unique key for each row to prevent rendering issues.
- Enhanced CredentialsGeneratorBox with aria-labels for input fields and buttons to improve accessibility.
- Updated documentation to remove unnecessary links and improve clarity in various sections.
- Fixed iframe attributes in documentation for better compatibility and accessibility.
- Adjusted CSS variable for muted foreground color to improve contrast.
- Updated package.json and pnpm-lock.yaml for dependency management and optimization.

* feat: update FileComponent and FolderComponent to include new props for enhanced functionality

* Add new AI provider icons and update documentation

- Introduced new SVG icons for AI providers: TogetherAI, TrueFoundry, VLLM, Vultr, and XAI.
- Updated existing AI endpoint documentation to reflect new icon names and improve clarity.
- Replaced generic \Plug\ icons with specific provider icons for Anyscale, APIpie, Cloudflare, Cohere, Databricks, DeepSeek, Fireworks, Groq, Helicone, HuggingFace, LiteLLM, Mistral, MLX, Moonshot, NeuroChain, Ollama, OpenRouter, Perplexity, Portkey, ShuttleAI, and TrueFoundry.
- Enhanced the icon resolution logic to include new icons in the icon registry.

* feat: add DocsHub and QuickStartHub components for enhanced documentation navigation

* feat: implement FeaturesHub component for enhanced feature navigation and update ViewOptions for improved links

* feat: add fresh-build script for streamlined project setup and development

* fix: update ESLint configuration and improve type handling in components

- Added 'next.config.mjs' to ESLint ignore list.
- Refactored version assignment in ChangelogPage for better type safety.
- Removed unnecessary type casting in Author components for cleaner code.
- Simplified BlogHeader component by removing redundant type assertions.
- Added eslint-disable comments for unused variables in CardCompat and Nextra shims.

* fix: update ViewOptions link for LibreChat to remove unnecessary submit parameter

* feat: enhance HomePage layout and improve GitHub star display

- Integrated HomeLayout component for better page structure.
- Updated HeroSection to improve the presentation of GitHub stars with a new layout and styling.
- Adjusted link attributes for better accessibility and user experience.

* refactor: simplify title for Model Context Protocol (MCP) documentation

- Changed the title from "Model Context Protocol (MCP)" to "MCP" for brevity.
- Updated the description to clarify how LibreChat utilizes MCP for integration with external tools and services.

* feat: enhance navigation styling and update HomeLayout props

- Added a new background style for the navigation bar with a blur effect.
- Updated HomeLayout component to include a transparent navigation mode for improved visual integration.

* refactor: deprecate plugins in favor of agents and update related documentation

- Removed references to plugins across various files, including the FeaturesHub and documentation.
- Updated navigation redirects to point to agents instead of plugins.
- Deleted the plugins documentation file to streamline content and reduce confusion.

* feat: update demo images for improved visual representation

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2026-02-18 10:44:38 -05:00

96 lines
4.2 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
title: "AWS Bedrock"
icon: Bot
---
Head to the [AWS docs](https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html) to sign up for AWS and setup your credentials.
Youll also need to turn on model access for your account, which you can do by [following these instructions](https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html).
## Authentication
- You will need to set the following environment variables:
```bash filename=".env"
BEDROCK_AWS_DEFAULT_REGION=us-east-1
BEDROCK_AWS_ACCESS_KEY_ID=your_access_key_id
BEDROCK_AWS_SECRET_ACCESS_KEY=your_secret_access_key
```
**Note:** You can also omit the access keys in order to use the default AWS credentials chain but you must set the default region:
```bash filename=".env"
BEDROCK_AWS_DEFAULT_REGION=us-east-1
```
Doing so prompts the credential provider to find credentials from the following sources (listed in order of precedence):
- Environment variables exposed via process.env
- SSO credentials from token cache
- Web identity token credentials
- Shared credentials and config ini files
- The EC2/ECS Instance Metadata Service
The default credential provider will invoke one provider at a time and only continue to the next if no credentials have been located.
For example, if the process finds values defined via the `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY` environment variables, the files at ~/.aws/credentials and ~/.aws/config will not be read, nor will any messages be sent to the Instance Metadata Service.
## Configuring models
- You can optionally specify which models you want to make available with `BEDROCK_AWS_MODELS`:
```bash filename=".env"
BEDROCK_AWS_MODELS=anthropic.claude-3-5-sonnet-20240620-v1:0,meta.llama3-1-8b-instruct-v1:0
```
Note: If omitted, all known, supported model IDs will be included automatically.
- See all Bedrock model IDs here:
- **[https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns](https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns)**
## Additional Configuration
You can further configure the Bedrock endpoint in your [`librechat.yaml`](/docs/configuration/librechat_yaml/) file:
```yaml
endpoints:
bedrock:
availableRegions:
- "us-east-1"
- "us-west-2"
streamRate: 35
titleModel: 'anthropic.claude-3-haiku-20240307-v1:0'
guardrailConfig:
guardrailIdentifier: "abc123xyz"
guardrailVersion: "1"
trace: "enabled"
```
- `streamRate`: (Optional) Set the rate of processing each new token in milliseconds.
- This can help stabilize processing of concurrent requests and provide smoother frontend stream rendering.
- `titleModel`: (Optional) Specify the model to use for generating conversation titles.
- Recommended: `anthropic.claude-3-haiku-20240307-v1:0`.
- Omit or set as `current_model` to use the same model as the chat.
- `availableRegions`: (Optional) Specify the AWS regions you want to make available.
- If provided, users will see a dropdown to select the region. If not selected, the default region is used.
- ![image](https://github.com/user-attachments/assets/6f3c5e82-9c6b-4643-8487-07db1061ba49)
- `guardrailConfig`: (Optional) Configure AWS Bedrock Guardrails for content filtering.
- `guardrailIdentifier`: The guardrail ID or ARN from your AWS Bedrock Console.
- `guardrailVersion`: The guardrail version number (e.g., `"1"`) or `"DRAFT"`.
- `trace`: (Optional) Enable trace logging: `"enabled"`, `"disabled"`, or `"enabled_full"`.
- See [AWS Bedrock Guardrails documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-how.html) for creating and managing guardrails.
## Notes
- The following models are not supported due to lack of streaming capability:
- ai21.j2-mid-v1
- The following models are not supported due to lack of conversation history support:
- ai21.j2-ultra-v1
- cohere.command-text-v14
- cohere.command-light-text-v14
- AWS Bedrock endpoint supports all [Shared Endpoint Settings](/docs/configuration/librechat_yaml/object_structure/shared_endpoint_settings) via the `librechat.yaml` configuration file, including `streamRate`, `titleModel`, `titleMethod`, `titlePrompt`, `titlePromptTemplate`, and `titleEndpoint`