Setup

1. Install Poetry. See the official installation guide.

1. (Optional) Specify custom Python or Poetry executables in .env.dev. This is useful if multiple versions are installed. By default, python and poetry are used.

   POETRY_PYTHON=path-to-python-exe
   POETRY=path-to-poetry-exe
   

1. Create and activate the virtual environment:

   make init_env
   source .venv/bin/activate
   

1. Install project dependencies (including linting, formatting, and test tools):

   make install
   

Environment Variables

Copy .env.example to .env and customize it for your environment:

Compatibility configuration in DIAL Core config

Since: 0.37.0

It's possible to define compatible model on per-upstream basis in the DIAL Core configuration.

E.g. the following configuration enables anthropic.claude-3-5-sonnet-20250210-v3:0 model (that isn't supported by the Adapter natively) via anthropic.claude-3-5-sonnet-20241022-v2:0 model (that is supported by the Adapter natively):

{
  "models": {
    "dial-deployment-id-for-claude-3-5": {
      "type": "chat",
      "endpoint": "${ADAPTER_ORIGIN}/deployments/anthropic.claude-3-5-sonnet-20250210-v3:0/chat/completions",
      "upstreams": [
        {
          "extraData": {
            "compatible_model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0"
          }
        }
      ]
    }
  }
}

The given configuration enables the adapter to handle requests to anthropic.claude-3-5-sonnet-20250210-v3:0 deployment. The requests will be processed by the same pipeline as anthropic.claude-3-5-sonnet-20241022-v2:0, but the call to AWS Bedrock will be done to anthropic.claude-3-5-sonnet-20250210-v3:0 deployment name.

Naturally, this will only work if the APIs of v2 and v3 deployments are compatible:

1. The requests utilizing the modalities supported by both v2 and v3 will work just fine.
2. However, the requests with modalities that are supported by v3 (e.g. audio) and aren't supported by v2, won't be processed correctly. You will have to wait until the adapter supports the v3 deployment natively.

When a version of the adapter supporting the v3 model is released, you may migrate to it and safely remove the compatible_model_id from the DIAL Core config.

Note that setting compatible_model_id=stability.stable-image-ultra-v1:0 will be ineffectual, since the APIs of the two model and their capabilities are drastically different.

[!IMPORTANT] If the DIAL deployment has many upstreams, the compatible_model_id field should be set in all of the upstreams.

Compatibility configuration in Adapter

COMPATIBILITY_MAPPING env variable enables compatibility mode on the adapter level. It hold a mapping from unsupported deployment ids to supported deployment ids.

E.g. the following mapping enables anthropic.claude-3-5-sonnet-20250210-v3:0 via anthropic.claude-3-5-sonnet-20241022-v2:0:

COMPATIBILITY_MAPPING={"anthropic.claude-3-5-sonnet-20250210-v3:0": "anthropic.claude-3-5-sonnet-20241022-v2:0"}

[!IMPORTANT] Model compatibility configuration using the COMPATIBILITY_MAPPING environment variable has been deprecated since 0.37.0 in favor of configuration in DIAL Core. While still supported for now, its use is discouraged and it may be removed in a future release.

Development Environment

This project requires Python ≥3.11 and Poetry ≥2.1.1 for dependency management.

IDE configuration

The recommended IDE is VS Code. Open the project in VS Code and install the recommended extensions. VS Code is configured to use the Ruff formatter.

Alternatively you can use PyCharm that has built-in Ruff support.

Anthropic API

The adapter supports authentication with Anthropic API for Claude deployments.

1. Choose one of the Claude API model names from the official documentation. Let's call it CLAUDE_API_MODEL_NAME.
2. Find which AWS Bedrock model name corresponds to the chosen Claude API model name on the same documentation page. Let's call it AWS_BEDROCK_MODEL_NAME.
3. Add the Claude deployment to the DIAL Core configuration with API key configured on a per upstream basis:

    {
      "models": {
        "dial-claude-deployment-name": {
          "endpoint": "${ADAPTER_ORIGIN}/deployments/${CLAUDE_API_MODEL_NAME}/chat/completions",
          "upstreams": [
            {
              "key": "${ANTHROPIC_API_KEY}",
              "extraData": {
                "compatible_model_id": "${AWS_BEDROCK_MODEL_NAME}"
              }
            }
          ]
        }
      }
    }
    

Note that there is no need to configure the upstream endpoint, since there is only one endpoint for the model inference in the Anthropic API and it will be used by default: https://api.anthropic.com/v1/messages.

The same Anthropic models have different model names in Claude API and AWS Bedrock. For example:

1. claude-sonnet-4-5-20250929 (${CLAUDE_API_MODEL_NAME}) in Claude API corresponds to
2. anthropic.claude-sonnet-4-5-20250929-v1:0 (${AWS_BEDROCK_MODEL_NAME}) in AWS Bedrock.

The Bedrock adapter uses model names from AWS Bedrock. Therefore, in order to use Claude API model name you need to specify the corresponding name from AWS Bedrock in the compatible_model_id field. Otherwise, the adapter returns 404.

---

Supported models