Skip to content

chore: remove deployments field from Azure/Vertex schema and replace with models/aliases in values.yaml comments #6510

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Pratham-Mishra04 merged 1 commit into from
Aug 26, 2026
Merged

chore: remove deployments field from Azure/Vertex schema and replace with models/aliases in values.yaml comments #6510

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 0 additions & 28 deletions helm-charts/bifrost/values.schema.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5688,13 +5688,6 @@
},
"description": "Azure scopes for authentication"
},
"deployments": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Model to deployment mappings"
},
"api_version": {
"type": "string",
"description": "Azure API version"
Expand Down Expand Up @@ -5731,13 +5724,6 @@
"type": "boolean",
"description": "When true, always call the configured region and skip automatic promotion of multi-region-only models to a multi-region endpoint. Enable for provisioned throughput.",
"default": false
},
"deployments": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Model to deployment mappings"
}
},
"required": ["project_id", "region"],
Expand Down Expand Up @@ -6752,13 +6738,6 @@
},
"description": "Azure scopes for authentication"
},
"deployments": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Model to deployment mappings"
},
"api_version": {
"type": "string",
"description": "Azure API version"
Expand Down Expand Up @@ -6794,13 +6773,6 @@
"type": "boolean",
"description": "When true, always call the configured region and skip automatic promotion of multi-region-only models to a multi-region endpoint. Enable for provisioned throughput.",
"default": false
},
"deployments": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Model to deployment mappings"
}
},
"additionalProperties": false
Expand Down
94 changes: 47 additions & 47 deletions helm-charts/bifrost/values.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -335,50 +335,50 @@ bifrost:
# Use direct values or env.VAR_NAME syntax (required when keys come from providerSecrets).
# See https://getbifrost.ai/schema for the full provider schema.
providers: {}
# openai:
# keys:
# - name: "primary-key" # Key name (required, must be unique)
# value: "sk-..." # Direct value
# weight: 1
# models: ["gpt-4o", "gpt-4o-mini"] # Restrict key to specific models
# use_for_batch_api: false # Whether this key can be used for batch API
# # use_anthropic_endpoints: false # deepseek/fireworks/vllm/sgl keys only: route chat completions
# # and responses through Anthropic-compatible endpoints (also
# # settable per-alias alongside use_deployments_endpoint)
# - name: "secondary-key"
# value: "env.OPENAI_KEY" # Reference to environment variable
# weight: 1
# # Network configuration (optional, per-provider)
# network_config:
# base_url: "" # Custom base URL (required for Ollama)
# extra_headers: {} # Additional headers to send with requests
# default_request_timeout_in_seconds: 300 # Request timeout
# max_retries: 3 # Maximum number of retries
# retry_backoff_initial_ms: 500 # Initial retry backoff in ms
# retry_backoff_max_ms: 5000 # Max retry backoff in ms
# stream_idle_timeout_in_seconds: 60 # Max wait for next stream chunk (default: 60)
# keep_alive_timeout_in_seconds: 30 # Idle keep-alive for pooled connections; set below the upstream's keep-alive (default: 30)
# max_conns_per_host: 5000 # Max TCP connections per host (default: 5000)
# enforce_http2: false # Force HTTP/2 on provider connections (e.g. Bedrock)
# http2_ping_interval_in_seconds: 0 # Idle seconds before a client-initiated HTTP/2 keepalive PING (0 = disabled; only when enforce_http2). Max 3600.
# insecure_skip_verify: false # Disable TLS certificate verification (last resort)
# ca_cert_pem: "" # PEM-encoded CA cert for self-signed/private CA
# allow_private_network: false # Allow connections to RFC 1918 private IPs (k8s pod network, LAN, VPC)
# beta_header_overrides: # Override Anthropic beta header support (optional)
# redact-thinking-: true # Enable/disable specific beta headers by prefix
# # Concurrency configuration (optional)
# concurrency_and_buffer_size:
# concurrency: 100 # Number of concurrent requests
# buffer_size: 200 # Buffer size for requests
# # Proxy configuration (optional)
# proxy_config:
# type: "none" # Options: none, http, socks5, environment
# url: ""
# username: ""
# password: ""
# ca_cert_pem: "" # PEM-encoded CA cert for SSL-intercepting proxies
# send_back_raw_response: false # Include raw response in BifrostResponse
# store_raw_request_response: false # Capture raw payloads for plugins only; not returned to client
# openai:
# keys:
# - name: "primary-key" # Key name (required, must be unique)
# value: "sk-..." # Direct value
# weight: 1
# models: ["gpt-4o", "gpt-4o-mini"] # Restrict key to specific models
# use_for_batch_api: false # Whether this key can be used for batch API
# # use_anthropic_endpoints: false # deepseek/fireworks/vllm/sgl keys only: route chat completions
# # and responses through Anthropic-compatible endpoints (also
# # settable per-alias alongside use_deployments_endpoint)
# - name: "secondary-key"
# value: "env.OPENAI_KEY" # Reference to environment variable
# weight: 1
# # Network configuration (optional, per-provider)
# network_config:
# base_url: "" # Custom base URL (required for Ollama)
# extra_headers: {} # Additional headers to send with requests
# default_request_timeout_in_seconds: 300 # Request timeout
# max_retries: 3 # Maximum number of retries
# retry_backoff_initial_ms: 500 # Initial retry backoff in ms
# retry_backoff_max_ms: 5000 # Max retry backoff in ms
# stream_idle_timeout_in_seconds: 60 # Max wait for next stream chunk (default: 60)
# keep_alive_timeout_in_seconds: 30 # Idle keep-alive for pooled connections; set below the upstream's keep-alive (default: 30)
# max_conns_per_host: 5000 # Max TCP connections per host (default: 5000)
# enforce_http2: false # Force HTTP/2 on provider connections (e.g. Bedrock)
# http2_ping_interval_in_seconds: 0 # Idle seconds before a client-initiated HTTP/2 keepalive PING (0 = disabled; only when enforce_http2). Max 3600.
# insecure_skip_verify: false # Disable TLS certificate verification (last resort)
# ca_cert_pem: "" # PEM-encoded CA cert for self-signed/private CA
# allow_private_network: false # Allow connections to RFC 1918 private IPs (k8s pod network, LAN, VPC)
# beta_header_overrides: # Override Anthropic beta header support (optional)
# redact-thinking-: true # Enable/disable specific beta headers by prefix
# # Concurrency configuration (optional)
# concurrency_and_buffer_size:
# concurrency: 100 # Number of concurrent requests
# buffer_size: 200 # Buffer size for requests
# # Proxy configuration (optional)
# proxy_config:
# type: "none" # Options: none, http, socks5, environment
# url: ""
# username: ""
# password: ""
# ca_cert_pem: "" # PEM-encoded CA cert for SSL-intercepting proxies
# send_back_raw_response: false # Include raw response in BifrostResponse
# store_raw_request_response: false # Capture raw payloads for plugins only; not returned to client
#
# anthropic:
# keys:
Expand All @@ -392,11 +392,11 @@ bifrost:
# - name: "azure-key"
# value: "..."
# weight: 1
# models: ["gpt-4o"] # The model name is used as the Azure deployment name
# aliases: # Map a model name to a different deployment name (only when they differ).
# gpt-4o: "my-gpt4o-deployment"
# azure_key_config:
# endpoint: "https://your-resource.openai.azure.com"
# api_version: "2024-02-15-preview"
# deployments:
# gpt-4o: "my-gpt4o-deployment"
#
# # Google Vertex AI example (requires vertex_key_config)
# vertex:
Expand Down
Loading