feat: add SAP AI Core client for Anthropic models
Implements native AI Core support with: - OAuth2 token refresh - Deployment discovery via /v2/lm/deployments - Anthropic Messages API via /invoke endpoint - Uses bedrock-2023-05-31 API version (AI Core uses Bedrock format) - Model field omitted from body (deployment URL specifies model) - Retry logic with exponential backoff Tested via integration tests against live AI Core endpoint.
This commit is contained in:
+38
-7
@@ -1,6 +1,6 @@
|
||||
// Package llm provides clients for LLM chat completion APIs.
|
||||
//
|
||||
// Supports OpenAI-compatible (default) and Anthropic Messages API providers.
|
||||
// Supports OpenAI-compatible (default), Anthropic Messages API, and SAP AI Core providers.
|
||||
package llm
|
||||
|
||||
import (
|
||||
@@ -22,6 +22,8 @@ const (
|
||||
ProviderOpenAI Provider = "openai"
|
||||
// ProviderAnthropic uses the Anthropic Messages API endpoint.
|
||||
ProviderAnthropic Provider = "anthropic"
|
||||
// ProviderAICore uses SAP AI Core with OAuth authentication.
|
||||
ProviderAICore Provider = "aicore"
|
||||
)
|
||||
|
||||
// Client calls an LLM chat completion API.
|
||||
@@ -35,6 +37,7 @@ type Client struct {
|
||||
temperature float64
|
||||
provider Provider
|
||||
http *http.Client
|
||||
aicore *AICoreClient // Only set when provider is aicore
|
||||
}
|
||||
|
||||
// NewClient creates a new LLM client. Default provider is OpenAI-compatible.
|
||||
@@ -49,8 +52,12 @@ func NewClient(baseURL, apiKey, model string) *Client {
|
||||
}
|
||||
|
||||
// WithTimeout sets the HTTP request timeout for LLM calls (default 5 minutes).
|
||||
// When using AI Core, this also sets the timeout on the AI Core client.
|
||||
func (c *Client) WithTimeout(d time.Duration) *Client {
|
||||
c.http.Timeout = d
|
||||
if c.aicore != nil {
|
||||
c.aicore.WithTimeout(d)
|
||||
}
|
||||
return c
|
||||
}
|
||||
|
||||
@@ -60,12 +67,21 @@ func (c *Client) WithTemperature(t float64) *Client {
|
||||
return c
|
||||
}
|
||||
|
||||
// WithProvider sets the API provider format (openai or anthropic).
|
||||
// WithProvider sets the API provider format (openai, anthropic, or aicore).
|
||||
func (c *Client) WithProvider(p Provider) *Client {
|
||||
c.provider = p
|
||||
return c
|
||||
}
|
||||
|
||||
// WithAICore configures the client to use SAP AI Core for authentication.
|
||||
// This sets the provider to aicore automatically.
|
||||
// The AI Core client inherits the current HTTP timeout from this client.
|
||||
func (c *Client) WithAICore(cfg AICoreConfig) *Client {
|
||||
c.provider = ProviderAICore
|
||||
c.aicore = NewAICoreClient(cfg).WithTimeout(c.http.Timeout)
|
||||
return c
|
||||
}
|
||||
|
||||
// Message represents a chat message.
|
||||
type Message struct {
|
||||
Role string `json:"role"`
|
||||
@@ -82,6 +98,8 @@ func (c *Client) Complete(ctx context.Context, messages []Message) (string, erro
|
||||
switch c.provider {
|
||||
case ProviderAnthropic:
|
||||
result, err = c.completeAnthropic(ctx, messages)
|
||||
case ProviderAICore:
|
||||
result, err = c.completeAICore(ctx, messages)
|
||||
default:
|
||||
result, err = c.completeOpenAI(ctx, messages)
|
||||
}
|
||||
@@ -106,6 +124,18 @@ func (c *Client) Complete(ctx context.Context, messages []Message) (string, erro
|
||||
return "", err
|
||||
}
|
||||
|
||||
// completeAICore routes to AI Core using the appropriate endpoint based on model type.
|
||||
func (c *Client) completeAICore(ctx context.Context, messages []Message) (string, error) {
|
||||
if c.aicore == nil {
|
||||
return "", fmt.Errorf("AI Core client not configured")
|
||||
}
|
||||
|
||||
if IsAnthropicModel(c.model) {
|
||||
return c.aicore.CompleteAnthropic(ctx, c.model, messages, 8192, c.temperature)
|
||||
}
|
||||
return c.aicore.CompleteOpenAI(ctx, c.model, messages, c.temperature)
|
||||
}
|
||||
|
||||
// isRetryableError returns true for transient errors worth retrying.
|
||||
func isRetryableError(err error) bool {
|
||||
if err == nil {
|
||||
@@ -176,11 +206,12 @@ func (c *Client) completeOpenAI(ctx context.Context, messages []Message) (string
|
||||
// --- Anthropic Messages API implementation ---
|
||||
|
||||
type anthropicRequest struct {
|
||||
Model string `json:"model"`
|
||||
MaxTokens int `json:"max_tokens"`
|
||||
System string `json:"system,omitempty"`
|
||||
Messages []anthropicMsg `json:"messages"`
|
||||
Temperature float64 `json:"temperature,omitempty"`
|
||||
AnthropicVersion string `json:"anthropic_version,omitempty"`
|
||||
Model string `json:"model,omitempty"`
|
||||
MaxTokens int `json:"max_tokens"`
|
||||
System string `json:"system,omitempty"`
|
||||
Messages []anthropicMsg `json:"messages"`
|
||||
Temperature float64 `json:"temperature,omitempty"`
|
||||
}
|
||||
|
||||
type anthropicMsg struct {
|
||||
|
||||
Reference in New Issue
Block a user