Skip to documentation
Documentation navigation

Documentation navigation

Documentation / guides

Snowflake Cortex

Configure the Snowflake Cortex provider from its released llm package, including endpoint, auth, formats, capabilities, counters, and failure boundaries.

developer

Snowflake Cortex Chat client translating max_tokens to max_completion_tokens and normalizing empty assistant roles.

Contract and endpoint

The public constructor is func New(selected model.Model, key auth.APIKey, options ...Option) (inference.Client, error). It binds provider identity snowflake-cortex and resolves the base below when Model.BaseURL is empty, unless the dynamic rule says otherwise.

FieldSource-backed behavior
Packagegithub.com/looprig/llm/providers/snowflake-cortex (package snowflake)
Providersnowflake-cortex
FormatsOpenAI
Default basedynamic: account Snowflake Cortex URL
Authenticationaccount token
Header or signerAuthorization: Bearer
OptionsWithAccount; WithHeader; WithReasoningEnabled; WithServiceTier

Token falls back from SNOWFLAKE_CORTEX_TOKEN to SNOWFLAKE_CORTEX_PAT. Account is required only when BaseURL is empty.

An explicit model BaseURL is caller-controlled and is used by the provider route builder. It replaces the package default; it is not appended to the default.

Authentication and model formats

The llm provider registry classifies this identity as requiring account token. The constructor receives resolved credential material rather than a secret reference. A credentials or secrets integration can resolve a descriptor and lease before passing the value here; secret labels do not belong in model.Model.

DecisionResult
Credentialaccount token
Wire authAuthorization: Bearer
Format gateOpenAI; unsupported values fail model validation before I/O
Model identityProvider and APIFormat select the route and codec; optional capabilities remain request-level and are not inferred from the model string.

Optional capability bits on model.Model remain caller input. Request validation is authoritative for tools, structured output, images, thinking, sampling, and output limits; this page records only features encoded by the selected codec or provider patch.

Streaming, structured output, and tools

The client returns the shared stream reader from Stream. Its selected codec encodes provider-neutral tool declarations, tool results, and structured-output schemas when the request is valid. Streaming responses preserve codec usage and finish metadata; no capability beyond the source-backed format is inferred.

A stream owns its response body through the returned reader. Transport and non-success HTTP failures are returned before a reader is exposed; decode failures surface from Next or the terminal result.

%%{init: {"theme":"base","themeVariables":{"background":"#0b1020","primaryColor":"#172554","primaryTextColor":"#f8fafc","primaryBorderColor":"#60a5fa","lineColor":"#94a3b8","secondaryColor":"#1e293b","tertiaryColor":"#111827","fontFamily":"ui-sans-serif,system-ui"}}}%%
flowchart LR
    Req[Request] --> Enc[format codec]
    Enc --> Wire[provider route]
    Wire --> Stream[stream framing]
    Stream --> Reader[StreamReader]
    Reader --> Result[terminal result and usage]
    classDef dark fill:#172554,stroke:#60a5fa,color:#f8fafc;
    class Req,Enc,Wire,Stream,Reader,Result dark;

Caching controls

No provider cache controls are exported.

Counters, errors, and retries

NewCounter returns a typed llm.CounterSupportError because no exact provider counter is implemented.

The shared inference boundary returns typed model-validation, authentication, network, HTTP, request-encoding, response-decoding, and stream errors. A provider-local retry loop is not implied by a constructor name.

conversation_complete is normalized to an empty response. No general response retry is declared.

Consumer example

The example keeps credentials out of model.Model and calls the public constructor. Replace environment lookup with an application-owned credentials or secrets lease.

package example
import (
    "context"
    "os"
    "github.com/looprig/inference"
    "github.com/looprig/inference/auth"
    model "github.com/looprig/inference/model"
    snowflake "github.com/looprig/llm/providers/snowflake-cortex"
)
func invoke() error {
    // Resolve credentials from an application-owned lease or environment, never model.Model.
    selected := model.CustomModel(model.ProviderName("snowflake-cortex"), model.APIFormatOpenAI, "", "model-name")
    // Construction validates provider policy and binds its endpoint and codec.
    client, err := snowflake.New(selected, auth.APIKey(os.Getenv("SNOWFLAKE_CORTEX_API_KEY")))
    if err != nil { return err }
    // The context controls the request lifetime, including a stream if used.
    _, err = client.Invoke(context.Background(), inference.Request{Model: selected})
    return err
}

Source and proof

The provider identity and API-format truth table are defined in provider.go. Adjacent behavior tests:

← back to documentation