تكوين بوابة النماذج

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

  # Model info parameters (optional)
  model_info:
    exposed: true                          # true: visible in /models list; false: internal-only
    max_input_tokens: 128000               # context window size
    max_output_tokens: 4096                # maximum tokens the model may generate
    input_cost_per_token: 0.0000025        # cost in USD per input token (used for usage metering)
    output_cost_per_token: 0.000010        # cost in USD per output token
    cache_read_input_token_cost: 0.00      # cost for cache-hit input tokens (prompt caching)
    cache_creation_input_token_cost: 0.00  # cost to write a new cache entry
    supports_prompt_caching: true          # true if the model supports prompt caching
    supports_function_calling: true        # true if the model supports tool/function calls
    supports_tool_choice: true             # true if tool_choice param is honoured
    supports_reasoning: false              # true if the model supports a reasoning_effort param
    supports_vision: false                 # true if the model accepts image inputs in chat messages
    mode: chat                             # chat | embedding | image_generation

  # Optional ordered list of model_name values to try when this model is unavailable
  fallbacks:
    - fallback_model

  # 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

openai_compatible:
  model: gpt-4o                          # Model ID as expected by the provider
  base_url: https://base_url             # Base URL of model deployment
  api_key: env.API_KEY                   # API key to authenticate. env.<VAR> reads from the container environment
  extra_headers:                         # Extra headers to include when inferencing
    example_header: env.HEADER_VALUE
  insecure_skip_verify: true             # Disable TLS verification (not recommended for production)
  ca_cert_pem: env.CA_CERT               # CA certificate for TLS verification

bedrock:
  model: claude                                  # 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   # Bedrock Secret Access Key

vertex:
  model: gemini                              # Model ID as expected by the provider
  project: my-gcp-project                    # GCP project ID
  location: global                           # Vertex AI region / "global" for Global API
  credentials: env.GEMINI_CREDENTIALS        # Service-account JSON, base64-encoded

# AWS Bedrock credentials — referenced by bedrock models.
x-aws-bedrock-auth: &aws-bedrock-auth
  region: us-east-1
  access_key_id: env.AWS_ACCESS_KEY
  secret_access_key: env.AWS_SECRET_ACCESS_KEY

models:
  - model_name: my-bedrock-model
    bedrock:
      model: claude
      <<: *aws-bedrock-auth            # merge credentials anchor defined above
    model_info:
      exposed: true
      mode: chat

x-my-base-model: &my-base-model
  vertex:
    model: gemini-2.5-pro
    project: my-gcp-project
    location: global
    credentials: env.GEMINI_CREDENTIALS
  model_info:
    exposed: false
    supports_reasoning: true
    mode: chat

models:
  - model_name: my-gemini-model
    <<: *my-base-model

  - model_name: my-second-gemini-model
    <<: *my-base-model

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

api_key: env.VAR_BAR_1

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-----

# ── Credential anchors (shared across model entries via YAML merge keys) ──────
# AWS Bedrock credentials
x-aws-bedrock-auth: &aws-bedrock-auth
  region: us-east-1
  access_key_id: env.AWS_ACCESS_KEY
  secret_access_key: env.AWS_SECRET_ACCESS_KEY

# Google Vertex AI credentials
x-vertex-auth: &vertex-auth
  project: my-gcp-project
  location: global
  credentials: env.GEMINI_CREDENTIALS

# ── Shared model anchors (optional) ───────────────────────────────────────────
x-my-base-model: &my-base-model
  vertex:
    model: gemini-2.5-pro
    <<: *vertex-auth
  model_info:
    exposed: true
    max_input_tokens: 200000
    max_output_tokens: 12000
    input_cost_per_token: 0.00000125
    output_cost_per_token: 0.00001
    cache_read_input_token_cost: 0.000000125
    supports_reasoning: true
    mode: chat

# ── Models ────────────────────────────────────────────────────────────────────
models:
  # OpenAI-compatible model (e.g. Azure OpenAI) with API key
  - model_name: my-gpt-model
    openai_compatible:
      model: gpt-4o
      base_url: https://<resource>.cognitiveservices.azure.com/openai
      api_key: env.BOB_AZURE_API_KEY
    model_info:
      exposed: true
      max_input_tokens: 128000
      max_output_tokens: 4096
      input_cost_per_token: 0.0000025
      output_cost_per_token: 0.000010
      supports_function_calling: true
      supports_tool_choice: true
      mode: chat
    chat_inference_params:
      temperature: 0.7
      top_p: 0.9

  # AWS Bedrock model
  - model_name: my-bedrock-model
    bedrock:
      model: us.anthropic.claude-3-5-sonnet-20241022-v2:0
      <<: *aws-bedrock-auth
    fallbacks:                          # optional: ordered list of fallback model names
      - my-fallback-model
    model_info:
      exposed: false
      max_input_tokens: 200000
      max_output_tokens: 8192
      input_cost_per_token: 0.000003
      output_cost_per_token: 0.000015
      cache_creation_input_token_cost: 0.00000375
      cache_read_input_token_cost: 0.0000003
      supports_prompt_caching: true
      supports_function_calling: true
      supports_tool_choice: true
      mode: chat
    chat_inference_params:
      temperature: 0.7
      top_k: 50

  # Google Vertex AI (Gemini) model using shared model anchor
  - model_name: my-gemini-model
    <<: *my-base-model

  # OpenAI-compatible model with custom CA certificate
  - model_name: example-model-mini
    openai_compatible:
      model: gpt-4o-mini
      base_url: https://llm-mock-server.ca-tor.containers.appdomain.cloud
      ca_cert_pem: env.CA_CERT
    model_info:
      exposed: true
      max_input_tokens: 131072
      input_cost_per_token: 0.00000015
      output_cost_per_token: 0.0000006
      supports_function_calling: true
      supports_tool_choice: true
      mode: chat

  # OpenAI-compatible model with extra headers
  - model_name: another-example-model-mini
    openai_compatible:
      model: gpt-4o-mini
      base_url: https://llm-mock-server.ca-tor.containers.appdomain.cloud
      extra_headers:
        model_key: env.MODEL_KEY
    model_info:
      exposed: true
      max_input_tokens: 131072
      input_cost_per_token: 0.00000015
      output_cost_per_token: 0.0000006
      supports_function_calling: true
      supports_tool_choice: true
      mode: chat

bob:
  modelGateway:
    secrets:
      BOB_AZURE_API_KEY: someapikeyvalue
      AWS_ACCESS_KEY: someapikeyvalue
      AWS_SECRET_ACCESS_KEY: someapikeyvalue
      GEMINI_CREDENTIALS: <base64_vertex_credentials>
      CA_CERT: <PEM encoded CA cert>
      MODEL_KEY: apikeyvalue

bobctl install --model-config /tmp/example/model-gateway.yaml

bobctl install --model-config path/to/model-gateway-config.yaml --accept-license

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
      BOB_AZURE_API_KEY: "<your-azure-api-key>"

      # Google Cloud Vertex AI / Gemini authentication
      BOB_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