Recipe
litellm-gateway
An AI gateway on Kubernetes via the helm provider's Workload synthesis, running the official upstream proxy image directly. Renders a Deployment, a ClusterIP Service and a ConfigMap carrying the routing table. Every credential reaches the gateway as an env secretKeyRef, so no credential value appears in its own resources. It is proven at LiteLLM v1.103.1 and halts on any other engine_version. On every Release a second ConfigMap carries a request guard, which forwards only the request fields the proxy declares for the route, plus any the Release admits in infra.admitted_request_fields, and refuses the rest naming the field. The same ConfigMap configures a path allowlist, a container running the official nginx image (BSD-2-Clause) on infra.port, which answers 403 to every path but the routes the gateway serves. A core/context-propagation attachment, a core/data-masking one listing what to mask, or values.log_masking listing it, adds the module each relies on. A core/prompt-injection-shield attachment sends every map entry to the guard on the guard socket. PROXY_BASE_URL and the Presidio and cache store addresses appear only when infra.external_base_url and their sockets are set. A store publishing redis-tls is reached over TLS, its password inside the cache's URL: keep that password to letters and digits. With `values.metrics_enabled` true the path allowlist forwards a GET of /metrics alone from port 9090, on the ClusterIP Service, to the gateway's metrics, published as provides.metrics_endpoint; false leaves that key empty. Reach for this realization where the build must fetch nothing; reach for `litellm-gateway-chart`, BerriAI's own chart, where its registry is reachable at build time.
Pochodzenie
- Skrót zawartości
- sha256:1bd9c826a387e9d5d865a58bd1be2954fde9373af8533b5c24dfae2fa9896e22
- Opublikowano
- 2026-11-10T10:25:06Z
- Tożsamość podpisująca
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Podpis
- Oficjalnyapplication/vnd.dev.sigstore.bundle.v0.3+json
https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
sha256:c2097aaeb345d727adeb5057c268933b86653cef71a6e4e4240558784ea99db5
Referencja w tej wersji
oci://hub.aggrega.ai/recipe/helm/litellm-gateway:1.0.0- Cel
- —
- Implementuje
- core/gateway/litellm:1.0.0
Udostępnia
Deterministyczne szablony wskaźników, które ta receptura podłącza dla konsumentów.
| Nazwa | Szablon |
|---|---|
| host | {{ .context.rendered_name }}-default |
| port | {{ .infra.port }} |
| endpoint | http://{{ .context.rendered_name }}-default:{{ .infra.port }}/v1 |
| model | {{ .locals.published_model }} |
| protocol | http |
| metrics_endpoint | {{ if .values.metrics_enabled }}http://{{ .context.rendered_name }}-default:{{ .locals.metrics_port }}/metrics{{ end }} |
Workload
Workload · form: stateless · replicas: 1 · containers: main
Zmienne lokalne
| Nazwa | Szablon |
|---|---|
| config_file | config.yaml |
| provider_key_variable | LITELLM_PROVIDER_API_KEY |
| connection_key_variable_prefix | LITELLM_MODEL_ |
| connection_key_variable_suffix | _API_KEY |
| guard_api_key | the-guard-holds-the-upstream-credential |
| caller_identity_module | caller_identity |
| masking_module | data_masking |
| field_entity_masking_class | FieldEntityMasking |
| reply_masking_class | ReplyMasking |
| buffered_reply_masking_class | BufferedReplyMasking |
| field_pattern_masking_class | FieldPatternMasking |
| held_reply_class | HeldStreamedReply |
| log_masking_module | log_masking |
| log_masking_class | LogMasking |
| log_masking_failure_callback | withhold_failed_calls |
| request_filter_module | request_field_filter |
| gateway_address | 127.0.0.1 |
| gateway_port | {{ if eq (int .infra.port) 65535 }}65534{{ else }}{{ add1 (int .infra.port) }}{{ end }} |
| metrics_port | 9090 |
| gateway_metrics_port | 9091 |
| path_allowlist_file | path-allowlist.conf |
| path_allowlist_image_tag | 1.27.5-alpine |
| request_guard_config_map_name | {{ .context.instance_id }}-request-guard |
| request_guard_dir | /etc/litellm-request-guard |
| request_guard_delivery | config_map |
| forward_organization_routes | false |
| model_aliases | {{ $aliases := list }}{{ range (optional .values "models" list) }}{{ $aliases = append $aliases .name }}{{ end }}{{ toJson $aliases }} |
| model_entries | {{ toJson (optional .values "models" list) }} |
| published_model | {{ with optional .values "model" "" }}{{ . }}{{ else }}{{ with optional .values "models" list }}{{ (index . 0).name }}{{ end }}{{ end }} |
| analyzer_entity_types | ["CREDIT_CARD", "CRYPTO", "DATE_TIME", "EMAIL_ADDRESS", "IBAN_CODE", "IP_ADDRESS", "LOCATION", "MAC_ADDRESS", "MEDICAL_LICENSE", "NRP", "PERSON", "PHONE_NUMBER", "UK_NHS", "URL", "US_BANK_NUMBER", "US_DRIVER_LICENSE", "US_ITIN", "US_PASSPORT", "US_SSN"] |
| proven_engine_versions | ["v1.103.1"] |
| cache_store_host_variable | SEMANTIC_CACHE_STORE_HOST |
| cache_store_port_variable | SEMANTIC_CACHE_STORE_PORT |
| cache_store_password_variable | REDIS_PASSWORD |
| cache_store_url_variable | SEMANTIC_CACHE_STORE_URL |
Mapowanie wartości
Nie zadeklarowano mapowania wartości.
Relacje
Typowane krawędzie do innych opublikowanych encji i od nich. Odwołanie bez opublikowanego celu jest renderowane jako przerwana krawędź, a nie jako łącze.
Używa
- implementujeimplementujekontrakt zgodny
core/gateway/litellm:1.0.0
Wszystkie wymagane wyjścia są spełnione, a każde udostępniane wyjście jest wymienione w kontrakcie.
Używane przez
Nic w katalogu nie zależy od tej encji.