integrations.yml

integrations.yml is required at the project root. It declares the LLM that drives the agent, the channels customers reach it through, and any named model groups. The file is copied into the model archive at rasa train, and each section is read from the place that suits what it configures:

Section	Read from	Effect
`llm`	The live project directory	Change the provider or model and restart. No retraining.
`channels`	The live project directory	Change channel settings and restart.
`model_groups`	The packaged snapshot	The embedder that built the reference index is the one that queries it.
`tracing`	The live project directory	Optional Langfuse observability; restart to pick up changes.

model_groups is the one to know about. Editing it in your project after training does not change how references are searched, because the query embeddings have to match the vectors built at train time. Retrain to pick up a new embedding model.

integrations.yml

llm:
  provider: openai
  model: gpt-5.1
  api_base: https://api.openai.com/v1
  api_key_env: OPENAI_API_KEY

channels:
  rest: { enabled: true }
  inspector: { enabled: true }

# Optional — Langfuse tracing (often left commented until keys are set)
# tracing:
#   type: langfuse
#   public_key: ${LANGFUSE_PUBLIC_KEY}
#   private_key: ${LANGFUSE_SECRET_KEY}
#   host: https://cloud.langfuse.com

That is a complete, working file. Everything else is optional.

`llm`

Required. One flat block describing the single model that drives the agent.

Key	Required	Description
`provider`	Yes	Provider id (`openai`, `anthropic`, `azure`, …). Must be non-empty.
`model`	Yes*	Model name.
`deployment`	Yes*	Azure OpenAI deployment name, used instead of `model`.

* Exactly one of model or deployment must be set. A section with neither fails validation with calm_v2.validation.config.missing_provider. Every other key is passed to the provider client: api_base, temperature, timeout, and so on. Two keys are handled by Maestro before that happens:

Key	Handling
`api_key_env`	Read as the name of an environment variable and resolved into the API key
`max_prompt_tokens`	Consumed by prompt construction as the token budget for the assembled prompt

provider sits at the top level of this block, which is what makes it a flat mapping. The agent’s main LLM is always configured here, never through model_groups.

Provider examples

provider: openai, azure, and self-hosted have dedicated clients. Any other value is passed through to LiteLLM, so a provider LiteLLM supports works by naming it and its model. OpenAI

integrations.yml

llm:
  provider: openai
  model: gpt-5.1
  api_key_env: OPENAI_API_KEY

channels:
  rest: { enabled: true }

Anthropic

integrations.yml

llm:
  provider: anthropic
  model: claude-sonnet-4-5-20250929
  api_key_env: ANTHROPIC_API_KEY

channels:
  rest: { enabled: true }

Google Gemini

integrations.yml

llm:
  provider: gemini
  model: gemini-2.5-pro
  api_key_env: GEMINI_API_KEY

channels:
  rest: { enabled: true }

Azure OpenAI. Name the deployment rather than the model, and give the endpoint and API version:

integrations.yml

llm:
  provider: azure
  deployment: my-gpt-deployment
  api_base: https://my-resource.openai.azure.com/
  api_version: "2024-10-21"
  api_key_env: AZURE_OPENAI_API_KEY

channels:
  rest: { enabled: true }

Self-hosted, OpenAI-compatible. For vLLM, Ollama, TGI, or anything else serving the OpenAI API shape. provider, model, and api_base are all required:

integrations.yml

llm:
  provider: self-hosted
  model: mistralai/Mistral-7B-Instruct-v0.3
  api_base: http://localhost:8000/v1
  api_key_env: LOCAL_LLM_API_KEY

channels:
  rest: { enabled: true }

model is the name your server advertises, and api_base points at the OpenAI-compatible route, usually ending in /v1. Drop api_key_env if the server takes no key.

Secrets

api_key_env names an environment variable and works for every provider: Maestro resolves it into the API key before the config reaches the client. ${VAR} expansion happens in the channels: block, which is read with environment variables expanded. llm: and model_groups: are read without expansion, so api_key_env is the mechanism there. Never commit a literal key.

`channels`

Declares the channels customers reach the agent through.

channels:
  rest: { enabled: true }
  inspector: { enabled: true }

Each key is a channel name from the built-in channel registry. Values may be:

Form	Meaning
`{ enabled: true }`	Enable with defaults
`{ enabled: true, <key>: <value>, … }`	Enable with those keyword arguments
`{ enabled: false }`	Disabled: kept in the file but not registered
(empty / null)	Enable with defaults

The enabled flag is stripped before the remaining keys are handed to the channel. A non-boolean enabled, or an entry that is neither a mapping nor empty, raises at load.

rest and inspector are the practical minimum: rest is what the evaluation runner talks to, and inspector is required for rasa inspect. A project with no channels: block registers no channels at all.

${VAR} references inside channels: are expanded when the file is read, so channel credentials can come from the environment.

Voice channels

A voice channel takes asr: and tts: sub-mappings, and that is where speech recognition and synthesis are configured. Each takes a name: selecting the engine, plus that engine’s own settings:

integrations.yml

llm:
  provider: openai
  model: gpt-5.1
  api_key_env: OPENAI_API_KEY

channels:
  browser_audio:
    enabled: true
    server_url: localhost:5005
    asr:
      name: deepgram
      language_map:
        en-US:
          language: en
          model: flux-general-en
    tts:
      name: deepgram
      language_map:
        en-US:
          model: aura-2-asteria-en

Engine	Built-in names
`asr.name`	`deepgram`, `azure`
`tts.name`	`deepgram`, `azure`, `cartesia`, `rime`

Every key besides name goes to that engine, so the available settings are the engine’s own. language_map keys the model and language off the conversation language, which is how both engines take their settings. name also accepts a Python module path, which loads a custom engine implementing from_config_dict.

Deepgram Flux for speech recognition

Flux is the model family to reach for on a live voice agent. It does turn detection inside the ASR rather than inferring it from silence, so the agent takes its turn on the signal the recogniser already has. Naming a flux- model selects it. The engine reads the model name out of language_map and switches to the Flux API on its own, so there is nothing else to declare:

integrations.yml

llm:
  provider: openai
  model: gpt-5.1
  api_key_env: OPENAI_API_KEY

channels:
  browser_audio:
    enabled: true
    server_url: localhost:5005
    asr:
      name: deepgram
      language_map:
        en-US:
          language: en
          model: flux-general-en
      eot_threshold: 0.8
      eot_timeout_ms: 5000
    tts:
      name: deepgram
      language_map:
        en-US:
          model: aura-2-asteria-en

The two turn-detection knobs are optional:

Key	Range	Default	Effect
`eot_threshold`	0.5 to 0.9	0.7	Confidence needed to call end of turn. Lower responds faster and interrupts more.
`eot_timeout_ms`	500 to 10000	5000	Ceiling on silence before the turn is ended regardless.

A Flux config takes these two keys and no others. Anything unrecognised fails the load rather than being ignored, so a typo surfaces at startup. The same asr: / tts: shape applies to every voice channel, including jambonz, audiocodes, twilio_media_streams, and genesys. What differs between them is the telephony connection: server_url, and any credentials that provider needs.

`model_groups`

Optional. Named model configurations, used today only by the references embedder.

model_groups:
  - id: reference_embeddings
    models:
      - provider: openai
        model: text-embedding-3-large

Point agent.yml at one by id:

agent.yml

agent:
  persona: You are a helpful assistant.

references:
  embeddings: reference_embeddings

references.embeddings must name a group declared here. Naming an undeclared group fails the index build at rasa train with a message saying so.

Validation

rasa train and rasa data validate check this file:

Code	Cause
`calm_v2.validation.config.missing_integrations`	No `integrations.yml` at the project root
`calm_v2.validation.config.missing_llm`	No `llm:` section, or it is not a mapping
`calm_v2.validation.config.missing_provider`	`llm:` lacks `provider`, or lacks both `model` and `deployment`
`calm_v2.validation.config.invalid_tracing`	Invalid or unsupported `tracing:` section

Tracing (Langfuse)

Maestro projects configure Langfuse under tracing: in integrations.yml.

tracing:
  type: langfuse
  public_key: ${LANGFUSE_PUBLIC_KEY}
  private_key: ${LANGFUSE_SECRET_KEY}
  host: https://cloud.langfuse.com

Key	Required	Notes
`type`	yes	Must be `langfuse`.
`public_key`	yes	Must use a `${ENV_VAR}` reference — literal secrets are rejected.
`private_key`	yes	Must use a `${ENV_VAR}` reference — literal secrets are rejected.
`host`	yes	Langfuse Cloud or your self-hosted URL.
`environment`	no	Optional Langfuse environment name (lowercase, digits, `-`/`_`).
`timeout`	no	HTTP timeout in seconds (maps to `LANGFUSE_TIMEOUT`).
`debug`	no	Enable Langfuse debug logging (`LANGFUSE_DEBUG`).
`release`	no	Release/version tag attached to traces (`LANGFUSE_RELEASE`).
`sample_rate`	no	Trace sampling rate between 0 and 1 (`LANGFUSE_SAMPLE_RATE`).
`media_upload_thread_count`	no	Media upload thread pool size (`LANGFUSE_MEDIA_UPLOAD_THREAD_COUNT`).

public_key and private_key must use ${ENV_VAR} references — literal secrets are rejected at validation and apply time. Those references are kept as literal strings when integrations.yml is parsed (they are not expanded like channel credentials). They are resolved when Langfuse configures at CLI startup; if a variable is unset, resolution is best-effort and may leave the literal ${VAR} in the process environment, so tracing is skipped rather than aborting startup. Use rasa data validate to catch invalid shape or key syntax before deploy. Install the monitoring extra (pip install rasa-pro[monitoring]), set LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY, then enable the block. Example agents ship it commented out so local defaults stay key-free.

File Reference

Language

Tools

Runtime

Prompts

integrations.yml

`llm`

Provider examples

Secrets

`channels`

Voice channels

Deepgram Flux for speech recognition

`model_groups`

Validation

Tracing (Langfuse)

See also

​llm

​Provider examples

​Secrets

​channels

​Voice channels

​Deepgram Flux for speech recognition

​model_groups

​Validation

​Tracing (Langfuse)

​See also

`llm`

Provider examples

Secrets

`channels`

Voice channels

Deepgram Flux for speech recognition

`model_groups`

Validation

Tracing (Langfuse)

See also