Rodin
4b3cac66c3
- install.sh: verify SHA-256 checksum before installing binary - install.sh: fallback to ~/.local/bin if /usr/local/bin not writable - install.sh: use sed instead of grep for POSIX-safe JSON parsing - release.yml: remove jq dependency, parse release ID with sed - llm: make temperature configurable via --llm-temperature / LLM_TEMPERATURE - llm: add WithTemperature builder method on Client - llm: omit temperature from request when zero (uses server default)
109 lines
2.5 KiB
Go
109 lines
2.5 KiB
Go
package llm
|
|
|
|
import (
|
|
"bytes"
|
|
"encoding/json"
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
"strings"
|
|
)
|
|
|
|
// Client calls an OpenAI-compatible chat completion API.
|
|
type Client struct {
|
|
BaseURL string
|
|
APIKey string
|
|
Model string
|
|
Temperature float64
|
|
HTTP *http.Client
|
|
}
|
|
|
|
// NewClient creates a new LLM client.
|
|
func NewClient(baseURL, apiKey, model string) *Client {
|
|
return &Client{
|
|
BaseURL: strings.TrimRight(baseURL, "/"),
|
|
APIKey: apiKey,
|
|
Model: model,
|
|
HTTP: &http.Client{},
|
|
}
|
|
}
|
|
|
|
// WithTemperature sets the temperature for LLM requests.
|
|
// If not set (zero value), the server default is used.
|
|
func (c *Client) WithTemperature(t float64) *Client {
|
|
c.Temperature = t
|
|
return c
|
|
}
|
|
|
|
// Message represents a chat message.
|
|
type Message struct {
|
|
Role string `json:"role"`
|
|
Content string `json:"content"`
|
|
}
|
|
|
|
// ChatRequest is the request payload.
|
|
type ChatRequest struct {
|
|
Model string `json:"model"`
|
|
Messages []Message `json:"messages"`
|
|
Temperature float64 `json:"temperature,omitempty"`
|
|
}
|
|
|
|
// ChatResponse is the response from the API.
|
|
type ChatResponse struct {
|
|
Choices []struct {
|
|
Message struct {
|
|
Content string `json:"content"`
|
|
} `json:"message"`
|
|
} `json:"choices"`
|
|
}
|
|
|
|
// Complete sends a chat completion request and returns the assistant's response content.
|
|
func (c *Client) Complete(messages []Message) (string, error) {
|
|
reqBody := ChatRequest{
|
|
Model: c.Model,
|
|
Temperature: c.Temperature,
|
|
Messages: messages,
|
|
|
|
}
|
|
|
|
data, err := json.Marshal(reqBody)
|
|
if err != nil {
|
|
return "", fmt.Errorf("marshal request: %w", err)
|
|
}
|
|
|
|
url := c.BaseURL + "/chat/completions"
|
|
req, err := http.NewRequest("POST", url, bytes.NewReader(data))
|
|
if err != nil {
|
|
return "", fmt.Errorf("create request: %w", err)
|
|
}
|
|
req.Header.Set("Authorization", "Bearer "+c.APIKey)
|
|
req.Header.Set("Content-Type", "application/json")
|
|
|
|
resp, err := c.HTTP.Do(req)
|
|
if err != nil {
|
|
return "", fmt.Errorf("LLM request: %w", err)
|
|
}
|
|
defer resp.Body.Close()
|
|
|
|
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
|
|
body, _ := io.ReadAll(resp.Body)
|
|
return "", fmt.Errorf("LLM API error (status %d): %s", resp.StatusCode, string(body))
|
|
}
|
|
|
|
body, err := io.ReadAll(resp.Body)
|
|
if err != nil {
|
|
return "", fmt.Errorf("read response: %w", err)
|
|
}
|
|
|
|
var chatResp ChatResponse
|
|
if err := json.Unmarshal(body, &chatResp); err != nil {
|
|
return "", fmt.Errorf("parse response: %w", err)
|
|
}
|
|
|
|
if len(chatResp.Choices) == 0 {
|
|
return "", fmt.Errorf("no choices in LLM response")
|
|
}
|
|
|
|
return chatResp.Choices[0].Message.Content, nil
|
|
}
|