تكوين بوابة النماذج

- model_name: example_model
  # Provider types (pick one per model):
  openai_compatible:  # — any OpenAI-compatible REST endpoint (Azure, vLLM, …)
  bedrock:            # — AWS Bedrock invoke endpoint
  vertex:             # — Google Vertex AI (Gemini)

  # Model metadata
  model_info:
    exposed: true                         # true: visible in /v1/model/info list; false: internal-only
    provider: openai                      # model provider (e.g. openai, anthropic, google, nvidia, mistral)
    family: gpt                           # model family within the provider (e.g. gpt, sonnet, gemini)
    version: "5.6-sol"                    # model version string (see table below)
    max_input_tokens: 270000              # context window size
    max_output_tokens: 20000              # maximum tokens the model may generate
    supports_prompt_caching: true         # true if the model supports prompt caching
    supports_vision: true                 # true if the model supports image inputs
    mode: chat                            # chat | embedding | image_generation

  # Optional free-form request parameters appended to every request sent to
  # the provider, including standard parameters (e.g. temperature, top_p,
  # max_tokens) and provider-specific extensions (e.g. top_k,
  # repetition_penalty, anthropic_beta).
  chat_inference_params:
    temperature: 0.7
    top_p: 0.9

- model_name: premium-ide
  openai_compatible:
    model: gpt-5.6-sol                     # Model ID as expected by the provider
    base_url: https://<resource>.cognitiveservices.azure.com/openai
    api_key: env.AZURE_API_KEY             # env.<VAR> reads from the model gateway secrets
    extra_headers:                         # Extra headers to include when inferencing
      example_header: env.HEADER_VALUE
    ca_cert_pem: env.CA_CERT               # CA certificate for TLS verification
  model_info:
    exposed: true
    provider: openai
    family: gpt
    version: "5.6-sol"
    max_input_tokens: 270000
    max_output_tokens: 20000
    supports_prompt_caching: true
    supports_vision: true
    mode: chat

- model_name: premium-ide
  bedrock:
    model: us.anthropic.claude-sonnet-5    # Model ID as expected by the provider
    region: us-east-1                      # AWS region where your Bedrock endpoint lives
    access_key_id: env.AWS_ACCESS_KEY      # Bedrock Access Key ID
    secret_access_key: env.AWS_SECRET_ACCESS_KEY
  model_info:
    exposed: true
    provider: anthropic
    family: sonnet
    version: "5"
    max_input_tokens: 270000
    max_output_tokens: 20000
    supports_prompt_caching: true
    supports_vision: true
    mode: chat

- model_name: premium-ide
  vertex:
    model: gemini-3.6-flash                # Model ID as expected by the provider
    project: <gcp-project-id>              # GCP project ID
    location: global                       # Vertex AI region / "global" for Global API
    credentials: env.GEMINI_CREDENTIALS    # Service-account JSON, base64-encoded
  model_info:
    exposed: true
    provider: google
    family: gemini
    version: "3.6-flash"
    max_input_tokens: 270000
    max_output_tokens: 20000
    supports_prompt_caching: true
    supports_vision: true
    mode: chat

routers:
  - name: router
    strategy: static
    static:
      default_model: premium-ide   # must match a model_name in the models list

x-providers:
  gemini: &gemini
    vertex:
      model: gemini-3.6-flash
      project: <gcp-project-id>
      location: global
      credentials: env.GEMINI_CREDENTIALS
    model_info:
      exposed: true
      provider: google
      family: gemini
      version: "3.6-flash"
      max_input_tokens: 270000
      max_output_tokens: 20000
      supports_prompt_caching: true
      supports_vision: true
      mode: chat

models:
  - &chat_llm
    <<: *gemini
    model_name: premium-ide

  - <<: *chat_llm
    model_name: security               # overrides premium-ide from the merged anchor

  - <<: *chat_llm
    model_name: background

bob:
  modelGateway:
    secrets:
      VAR_BAR_1: FOO_1
      VAR_BAR_2: FOO_2
      VAR_BAR_N: FOO_N

api_key: env.VAR_BAR_1

oc create secret generic my-model-endpoint-ca   --from-file=tls.crt=model-ca.crt   -n <instance-namespace>

oc label secret my-model-endpoint-ca   bob.ibm.com/inferencing-bundle-ca=true   -n <instance-namespace>

models:
  - model_name: example-model
    openai_compatible:
      model: mistral-3.5
      base_url: https://vllm.internal.corp:8000/v1
      api_key: env.MODEL_API_KEY
      ca_cert_pem: env.CA_CERT           # Points to the variable name defined in config.yaml
    model_info:
      exposed: true
      mode: chat

bob:
  modelGateway:
    secrets:
      MODEL_API_KEY: "<your-api-key>"
      # The actual PEM certificate content matching env.CA_CERT above:
      CA_CERT: |
        -----BEGIN CERTIFICATE-----
        MIIFazCCA1OgAwIBAgIRAIIQjJaDSmJT3g4qg05...
        ... [full PEM-encoded CA certificate data] ...
        -----END CERTIFICATE-----

# ── Provider definitions ───────────────────────────────────────────────────────
# The x-providers key is ignored by the model gateway — it is a YAML scratchpad
# for provider examples. Only the active provider's anchor is referenced below.
x-providers:

  # AWS Bedrock
  bedrock: &bedrock
    bedrock:
      model: us.anthropic.claude-sonnet-5
      region: us-east-1
      access_key_id: env.AWS_ACCESS_KEY
      secret_access_key: env.AWS_SECRET_ACCESS_KEY
    model_info:
      exposed: true
      provider: anthropic
      family: sonnet
      version: "5"
      max_input_tokens: 270000
      max_output_tokens: 20000
      supports_prompt_caching: true
      supports_vision: true
      mode: chat

  # Google Vertex AI (Gemini)
  gemini: &gemini
    vertex:
      model: gemini-3.6-flash
      project: <gcp-project-id>
      location: global
      credentials: env.GEMINI_CREDENTIALS
    model_info:
      exposed: true
      provider: google
      family: gemini
      version: "3.6-flash"
      max_input_tokens: 270000
      max_output_tokens: 20000
      supports_prompt_caching: true
      supports_vision: true
      mode: chat

  # Azure OpenAI
  azure: &azure
    openai_compatible:
      model: gpt-5.6-sol
      base_url: https://<resource>.cognitiveservices.azure.com/openai
      api_key: env.AZURE_API_KEY
    model_info:
      exposed: true
      provider: openai
      family: gpt
      version: "5.6-sol"
      max_input_tokens: 270000
      max_output_tokens: 20000
      supports_prompt_caching: true
      supports_vision: true
      mode: chat

  # Custom inference service (RHOAI, vLLM, etc.)
  inference_service: &isvc
    openai_compatible:
      model: nvidia/nemotron-3-ultra-550b
      base_url: https://<llm-inference-server>
      api_key: env.INFERENCE_API_KEY
    model_info:
      exposed: true
      provider: nvidia
      family: nemotron
      version: "3-ultra"
      max_input_tokens: 262144
      supports_vision: false
      mode: chat

# ── Models ────────────────────────────────────────────────────────────────────
models:

  # ── ACTIVE MODEL ─────────────────────────────────────────────────────────────
  # Change <<: *bedrock to e.g. *azure, *gemini, or *isvc to switch providers.
  - &chat_llm
    <<: *bedrock                       # ← change provider here
    model_name: premium-ide
    model_info:
      exposed: true

  # ── Aliases ───────────────────────────────────────────────────────────────────
  - <<: *chat_llm
    model_name: security               # overrides premium-ide from the merged anchor

  - <<: *chat_llm
    model_name: background

# ── Router ────────────────────────────────────────────────────────────────────
routers:
  - name: router
    strategy: static
    static:
      default_model: premium-ide

bob:
  modelGateway:
    secrets:
      AWS_ACCESS_KEY: "<your-aws-access-key-id>"
      AWS_SECRET_ACCESS_KEY: "<your-aws-secret-access-key>"
      GEMINI_CREDENTIALS: "<base64-encoded service-account JSON>"
      AZURE_API_KEY: "<your-azure-api-key>"
      INFERENCE_API_KEY: "<your-inference-api-key>"
      CA_CERT: <PEM encoded CA cert>

bobctl install --model-config /tmp/example/model-gateway.yaml --accept-license --registry-creds <username:password>

bobctl install --model-config path/to/model-gateway-config.yaml --accept-license --registry-creds <username:password>

bob:
  modelGateway:
    secrets:
      # AWS Bedrock authentication
      AWS_ACCESS_KEY: "<your-aws-access-key-id>"
      AWS_SECRET_ACCESS_KEY: "<your-aws-secret-access-key>"

      # Azure OpenAI authentication
      AZURE_API_KEY: "<your-azure-api-key>"

      # Google Cloud Vertex AI / Gemini authentication
      GEMINI_CREDENTIALS: "<your-gemini-credentials-json>"

      # Custom endpoint API keys / tokens or internal proxy auth
      # RITS_APIKEY: "<your-api-key>"

      # Custom CA certificate in PEM format for self-signed internal endpoints
      # CA_CERT: |
      #   -----BEGIN CERTIFICATE-----
      #   ...
      #   -----END CERTIFICATE-----

# Update only the model config file
bobctl update-model-config --model-config ./my-model-config.yaml

# Update only the secrets (keys come from config.yaml)
bobctl update-model-config --update-secrets

# Update both at once
bobctl update-model-config --model-config ./my-model-config.yaml --update-secrets

# Preview what would be applied without touching the cluster
bobctl update-model-config --model-config ./my-model-config.yaml --update-secrets --dry-run