centdix 79ac6312e8 feat(ai): handle aws bedrock as provider (#7155)
* backend draft

* fix for tool and streaming

* do frontend side

* working

* working tools

* rm

* handle list endpoint

* handle for ai agents

* fix for models requiring inference id

* cleaning

* fix desc issue

* fix tool usage

* fix structured output

* cleaning

* fix for api

* rm

* fix input images

* cleaning

* chore: use aws sdk (#7156)

* feat(ai): Add AWS SDK dependencies for Bedrock integration

- Add aws-sdk-bedrockruntime v1.113.0
- Add aws-credential-types for bearer token authentication
- Update rustls to v0.23.35 for compatibility
- Dependencies added to windmill-common for AI features

* feat(ai): Add bearer token provider for Bedrock authentication

- Implement BearerTokenProvider using aws_credential_types
- Simple token-based auth using API keys from Windmill resources
- Add basic unit tests for provider creation
- Export bedrock_auth module in lib.rs

* feat(ai): Add Bedrock client wrapper with region extraction

- Implement BedrockClient wrapper around AWS SDK client
- Bearer token authentication integration
- Extract AWS region from Bedrock base URL automatically
- Comprehensive unit tests for region extraction
- Make aws-config non-optional dependency for AI features
- Update feature flags to reflect new dependency structure

* cargo

* feat(ai): Implement non-streaming Bedrock via AWS SDK

Use official AWS SDK instead of manual HTTP requests for better type safety and maintainability. Implements the Bedrock converse() API for non-streaming requests with proper bearer token authentication and message format conversion between OpenAI and Bedrock formats.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* refactor(ai): Eliminate Simple* conversion types for Bedrock SDK

- Move AI types to windmill-common/src/ai_types.rs for shared access
- Update bedrock_converters to work directly with OpenAI types
- Remove ~200 lines of conversion boilerplate from ai_executor.rs and bedrock.rs
- Remove unused imports to clean compilation warnings
- Benefits: 50% fewer conversion steps, no information loss, easier maintenance

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* feat(ai): Add streaming support for AWS Bedrock SDK

- Implement converse_stream() for Bedrock streaming responses
- Use EventReceiver.recv() to process stream events
- Extract text deltas using bedrock_stream_event_to_text()
- Send TokenDelta events to StreamEventProcessor for real-time updates
- Refactor request building to eliminate duplication between streaming and non-streaming
- Clean, minimal implementation following AWS SDK patterns

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* revert flake change

* fix

* feat(ai): Add tool calls and image support for Bedrock streaming

**Phase 1: Streaming Tool Call Support**
- Add stream event processing functions in bedrock_converters.rs:
  - bedrock_stream_event_to_tool_start() - Extract tool use start from ContentBlockStart
  - bedrock_stream_event_to_tool_delta() - Extract tool input deltas from ContentBlockDelta
  - bedrock_stream_event_is_block_stop() - Detect ContentBlockStop events
  - streaming_tool_calls_to_openai() - Convert accumulated tool calls to OpenAI format
- Update ai_executor.rs streaming loop with tool call accumulator (HashMap)
- Track current tool use ID during streaming
- Send ToolCallArguments events to StreamEventProcessor
- Return accumulated tool calls instead of empty vector

**Phase 2: Image Input Support**
- Add parse_image_data_url() to extract format and base64 data from data URLs
- Add content_part_to_block() to convert ContentPart to Bedrock ContentBlock
- Refactor convert_message() to handle multi-part content with images
- Support ImageUrl conversion to Bedrock ImageBlock with proper format (png/jpeg/gif/webp)
- Import AWS SDK image types: ImageBlock, ImageSource, ImageFormat
- Keep content_to_text() helper for system message text extraction

**Benefits**:
-  Tool calling now works in both streaming and non-streaming modes
-  Images are properly converted instead of being silently dropped
-  Structured output works in streaming (uses tool calling)
-  Full feature parity with manual HTTP implementation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* cleaning

* fix(ai): Add S3 image support and structured output for Bedrock

**Fixes:**
1. **S3 Image Support**: Call prepare_messages_for_api() before Bedrock SDK path to convert S3Objects to ImageUrls
   - Downloads images from S3 and encodes as base64 data URLs
   - Ensures images are properly handled in both streaming and non-streaming modes

2. **Structured Output**: Add ToolChoice::Any when structured output tool is present
   - Forces Bedrock to call the structured_output tool
   - Ensures JSON schema compliance for structured output
   - Works in both streaming and non-streaming modes

**Changes:**
- ai_executor.rs: Call prepare_messages_for_api() for Bedrock SDK path
- ai_executor.rs: Set tool_choice to Any when structured_output_tool_name is present
- aws_bedrock.rs: Remove unused ToolChoice imports (used via full path in worker)

**Testing:**
-  S3 images are now downloaded and converted before API call
-  Structured output now forces tool usage with ToolChoice::Any
-  Both work in streaming and non-streaming modes

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* cleaning

* cleaning

* cleaning

* better error

* cleaning

* cleaning

* rm

* rename

* apply region

---------

Co-authored-by: Claude <noreply@anthropic.com>

* fix default

* no panic

* no print

* use utils file

* cleaning

---------

Co-authored-by: Claude <noreply@anthropic.com>
2025-11-17 18:57:59 +00:00
2024-02-08 16:09:11 +01:00
2025-11-17 11:54:32 +00:00
2025-09-09 14:19:54 +00:00
2025-11-17 11:54:32 +00:00
2023-08-26 09:17:07 +02:00
2025-09-02 21:42:17 +00:00
2025-04-21 16:53:23 +02:00
2025-10-17 07:24:57 +00:00
2025-03-07 15:08:19 +01:00
2022-05-05 04:25:58 +02:00
2024-02-08 16:09:11 +01:00

windmill.dev

Open-source developer infrastructure for internal tools (APIs, background jobs, workflows and UIs). Self-hostable alternative to Retool, Pipedream, Superblocks and a simplified Temporal with autogenerated UIs and custom UIs to trigger workflows and scripts as internal apps.

Scripts are turned into sharable UIs automatically, and can be composed together into flows or used into richer apps built with low-code. Supported script languages supported are: Python, TypeScript, Go, Bash, SQL, and GraphQL.

Package version Docker Image CI Package version

Commit activity Discord Shield

Try it - Docs - Discord - Hub - Contributor's guide

Windmill - Developer platform for APIs, background jobs, workflows and UIs

Windmill is fully open-sourced (AGPLv3) and Windmill Labs offers dedicated instance and commercial support and licenses.

Windmill Diagram

https://github.com/windmill-labs/windmill/assets/122811744/0b132cd1-ee67-4505-822f-0c7ee7104252

Main Concepts

  1. Define a minimal and generic script in Python, TypeScript, Go or Bash that solves a specific task. The code can be defined in the provided Web IDE or synchronized with your own GitHub repo (e.g. through VS Code extension):

    Step 1

  2. Your scripts parameters are automatically parsed and generate a frontend.

Step 2

Step 3

  1. Make it flow! You can chain your scripts or scripts made by the community shared on WindmillHub.

    Step 3

  2. Build complex UIs on top of your scripts and flows.

    Step 4

Scripts and flows can also be triggered by a cron schedule (e.g. '_/5 _ * * *') or through webhooks.

You can build your entire infra on top of Windmill!

Show me some actual script code

//import any dependency  from npm
import * as wmill from "windmill-client";
import * as cowsay from "cowsay@1.5.0";

// fill the type, or use the +Resource type to get a type-safe reference to a resource
type Postgresql = {
  host: string;
  port: number;
  user: string;
  dbname: string;
  sslmode: string;
  password: string;
};

export async function main(
  a: number,
  b: "my" | "enum",
  c: Postgresql,
  d = "inferred type string from default arg",
  e = { nested: "object" }
  //f: wmill.Base64
) {
  const email = process.env["WM_EMAIL"];
  // variables are permissioned and by path
  let variable = await wmill.getVariable("f/company-folder/my_secret");
  const lastTimeRun = await wmill.getState();
  // logs are printed and always inspectable
  console.log(cowsay.say({ text: "hello " + email + " " + lastTimeRun }));
  await wmill.setState(Date.now());

  // return is serialized as JSON
  return { foo: d, variable };
}

CLI

We have a powerful CLI to interact with the windmill platform and sync your scripts from local files, GitHub repos and to run scripts and flows on the instance from local commands. See more details.

CLI Screencast

Running scripts locally

You can run your script locally easily, you simply need to pass the right environment variables for the wmill client library to fetch resources and variables from your instance if necessary. See more: https://www.windmill.dev/docs/advanced/local_development.

To develop & test locally scripts & flows, we recommend using the Windmill VS Code extension: https://www.windmill.dev/docs/cli_local_dev/vscode-extension.

Stack

  • Postgres as the database.
  • Backend in Rust with the following highly-available and horizontally scalable. Architecture:
    • Stateless API backend.
    • Workers that pull jobs from a queue in Postgres (and later, Kafka or Redis. Upvote #173 if interested).
  • Frontend in Svelte.
  • Scripts executions are sandboxed using Google's nsjail.
  • Javascript runtime is the deno_core rust library (which itself uses the rusty_v8 and hence V8 underneath).
  • TypeScript runtime is Bun and deno.
  • Python runtime is python3.
  • Golang runtime is 1.19.1.

Fastest Self-Hostable Workflow Engine

We have compared Windmill to other self-hostable workflow engines (Airflow, Prefect & Temporal) and Windmill is the most performant solution for both benchmarks: one flow composed of 40 lightweight tasks & one flow composed of 10 long-running tasks.

All methodology & results on our Benchmarks page.

Fastest workflow engine

Security

Sandboxing

Windmill can use nsjail. It is production multi-tenant grade secure. Do not take our word for it, take fly.io's one.

Secrets, credentials and sensitive values

There is one encryption key per workspace to encrypt the credentials and secrets stored in Windmill's K/V store.

In addition, we strongly recommend that you encrypt the whole Postgres database. That is what we do at https://app.windmill.dev.

Performance

Once a job started, there is no overhead compared to running the same script on the node with its corresponding runner (Deno/Go/Python/Bash). The added latency from a job being pulled from the queue, started, and then having its result sent back to the database is ~50ms. A typical lightweight deno job will take around 100ms total.

Architecture

How to self-host

We only provide docker-compose setup here. For more advanced setups, like compiling from source or using without a postgres super user, see Self-Host documentation.

Docker compose

Windmill can be deployed using 3 files: (docker-compose.yml, Caddyfile and a .env) in a single command.

Make sure Docker is started, and run:

curl https://raw.githubusercontent.com/windmill-labs/windmill/main/docker-compose.yml -o docker-compose.yml
curl https://raw.githubusercontent.com/windmill-labs/windmill/main/Caddyfile -o Caddyfile
curl https://raw.githubusercontent.com/windmill-labs/windmill/main/.env -o .env

docker compose up -d

Go to http://localhost et voilà :)

The default super-admin user is: admin@windmill.dev / changeme.

From there, you can follow the setup app and create other users.

More details in Self-Host Documention.

Kubernetes (k8s) and Helm charts

We publish helm charts at: https://github.com/windmill-labs/windmill-helm-charts.

Run from binaries

Each release includes the corresponding binaries for x86_64. You can simply download the latest windmill binary using the following set of bash commands.

BINARY_NAME='windmill-amd64' # or windmill-ee-amd64 for the enterprise edition
LATEST_RELEASE=$(curl -L -s -H 'Accept: application/json' https://github.com/windmill-labs/windmill/releases/latest)
LATEST_VERSION=$(echo $LATEST_RELEASE | sed -e 's/.*"tag_name":"\([^"]*\)".*/\1/')
ARTIFACT_URL="https://github.com/windmill-labs/windmill/releases/download/$LATEST_VERSION/$BINARY_NAME"
wget "$ARTIFACT_URL" -O windmill

OAuth, SSO & SMTP

Windmill Community Edition allows to configure the OAuth, SSO (including Google Workspace SSO, Microsoft/Azure and Okta) directly from the UI in the superadmin settings. Do note that there is a limit of 10 SSO users on the community edition.

See documentation.

Commercial license

See the LICENSE file for the full license text.

The "Community Edition" of Windmill available in the docker images hosted under ghcr.io/windmill-labs/windmill and the github binary releases contains the files under the AGPLv3 and Apache 2 sources but also includes proprietary and non-public code and features which are not open source and under the following terms: Windmill Labs, Inc. grants a right to use all the features of the "Community Edition" for free without restrictions other than the limits and quotas set in the software and a right to distribute the community edition as is but not to sell, resell, serve Windmill as a managed service, modify or wrap under any form without an explicit agreement.

The binary compilable from source code in this repository without the "enterprise" feature flag is open-source under the LICENSE-AGPLv3 License terms and conditions.

To re-expose directly any Windmill parts to your users as a feature of your product, with the exception of iframed public Windmill "apps", or to build a feature on top of "Windmill Community Edition" that you sell commercially or embed in a distributable product or binary, you must get a commercial license. Contact us at sales@windmill.dev if you have any questions. To do the same from the binary compiled from the source code in this repository without the "enterprise" feature flag, you must comply with the AGPLv3 license terms and conditions or get a commercial license from Windmill Labs, Inc.

To use Windmill "Community Edition" as is internally in your organization, or to use its APIs as is, you do NOT need a commercial license.

Integrations

In Windmill, integrations are referred to as resources and resource types. Each Resource has a Resource Type that defines the schema that the resource needs to implement.

On self-hosted instances, you might want to import all the approved resource types from WindmillHub. A setup script will prompt you to have it being synced automatically everyday.

Environment Variables

Environment Variable name Default Description Api Server/Worker/All
DATABASE_URL The Postgres database url. All
WORKER_GROUP default The worker group the worker belongs to and get its configuration pulled from Worker
MODE standalone The mode if the binary. Possible values: standalone, worker, server, agent All
METRICS_ADDR None (ee only) The socket addr at which to expose Prometheus metrics at the /metrics path. Set to "true" to expose it on port 8001 All
JSON_FMT false Output the logs in json format instead of logfmt All
BASE_URL http://localhost:8000 The base url that is exposed publicly to access your instance. Is overriden by the instance settings if any. Server
ZOMBIE_JOB_TIMEOUT 30 The timeout after which a job is considered to be zombie if the worker did not send pings about processing the job (every server check for zombie jobs every 30s) Server
RESTART_ZOMBIE_JOBS true If true then a zombie job is restarted (in-place with the same uuid and some logs), if false the zombie job is failed Server
SLEEP_QUEUE 50 The number of ms to sleep in between the last check for new jobs in the DB. It is multiplied by NUM_WORKERS such that in average, for one worker instance, there is one pull every SLEEP_QUEUE ms. Worker
KEEP_JOB_DIR false Keep the job directory after the job is done. Useful for debugging. Worker
LICENSE_KEY (EE only) None License key checked at startup for the Enterprise Edition of Windmill Worker
SLACK_SIGNING_SECRET None The signing secret of your Slack app. See Slack documentation Server
COOKIE_DOMAIN None The domain of the cookie. If not set, the cookie will be set by the browser based on the full origin Server
DENO_PATH /usr/bin/deno The path to the deno binary. Worker
PYTHON_PATH The path to the python binary if wanting to not have it managed by uv. Worker
GO_PATH /usr/bin/go The path to the go binary. Worker
GOPRIVATE The GOPRIVATE env variable to use private go modules Worker
GOPROXY The GOPROXY env variable to use Worker
NETRC The netrc content to use a private go registry Worker
PY_CONCURRENT_DOWNLOADS 20 Sets the maximum number of in-flight concurrent python downloads that windmill will perform at any given time. Worker
PATH None The path environment variable, usually inherited Worker
HOME None The home directory to use for Go and Bash , usually inherited Worker
DATABASE_CONNECTIONS 50 (Server)/3 (Worker) The max number of connections in the database connection pool All
SUPERADMIN_SECRET None A token that would let the caller act as a virtual superadmin superadmin@windmill.dev Server
TIMEOUT_WAIT_RESULT 20 The number of seconds to wait before timeout on the 'run_wait_result' endpoint Worker
QUEUE_LIMIT_WAIT_RESULT None The number of max jobs in the queue before rejecting immediately the request in 'run_wait_result' endpoint. Takes precedence on the query arg. If none is specified, there are no limit. Worker
DENO_AUTH_TOKENS None Custom DENO_AUTH_TOKENS to pass to worker to allow the use of private modules Worker
DISABLE_RESPONSE_LOGS false Disable response logs Server
CREATE_WORKSPACE_REQUIRE_SUPERADMIN true If true, only superadmins can create new workspaces Server
MIN_FREE_DISK_SPACE_MB 15000 Minimum amount of free space on worker. Sends critical alert if worker has less free space. Worker
RUN_UPDATE_CA_CERTIFICATE_AT_START false If true, runs CA certificate update command at startup before other initialization All
RUN_UPDATE_CA_CERTIFICATE_PATH /usr/sbin/update-ca-certificates Path to the CA certificate update command/script to run when RUN_UPDATE_CA_CERTIFICATE_AT_START is true All

Run a local dev setup

Using Nix (Recommended).

See the ./frontend/README_DEV.md file for all running options.

only Frontend

This will use the backend of https://app.windmill.dev but your own frontend with hot-code reloading. Note that you will need to use a username / password login due to CSRF checks using a different auth provider.

In the frontend/ directory:

  1. install the dependencies with npm install (or pnpm install or yarn)
  2. generate the windmill client:
npm run generate-backend-client
## on mac use
npm run generate-backend-client-mac
  1. Run your dev server with npm run dev
  2. Et voilà, windmill should be available at http://localhost/

Backend + Frontend

See the ./frontend/README_DEV.md file for all running options.

  1. Start a local Postgres database using for instance the start-dev-db.sh script which will make a database available at postgres://postgres:changeme@localhost:5432/windmill Then run the migrations using the following command:
    cargo install sqlx-cli
    env DATABASE_URL=<YOUR_DATABASE_URL> sqlx migrate run
    
    This will also avoid compile time issue with sqlx's query! macro.
  2. (optional, linux only) Install nsjail and have it accessible in your PATH
  3. Install bun, deno and python3 (+ any languages you want to use), have the bins at /usr/bin/bun,/usr/bin/deno, and /usr/local/bin/python3 or set the corresponding environment variables.
  4. (optional) Install the lld linker
  5. Go to frontend/:
    1. npm install, npm run generate-backend-client then REMOTE=http://localhost:8000 npm run dev
    2. You might need to set some extra heap space for the node runtime export NODE_OPTIONS="--max-old-space-size=4096"
    3. Create an empty frontend/build folder using mkdir frontend/build
  6. Go to backend/:
    1. env DATABASE_URL=<YOUR_DATABASE_URL> RUST_LOG=info cargo run
    2. You can specify any feature flag you want to enable, for example cargo run --features python to enable the python executor.
  7. Et voilà, windmill should be available at http://localhost:3000

Contributors

Windmill Labs, Inc 2023

S
Description
Open-source developer platform to power your entire infra and turn scripts into webhooks, workflows and UIs. Fastest workflow engine (13x vs Airflow). Open-source alternative to Retool and Temporal.
Readme 826 MiB
Languages
Rust 33.4%
Svelte 24.3%
TypeScript 24.2%
HTML 14%
JavaScript 1.6%
Other 2.3%