db123-ai
3895ca68c0
- internal/llama/template.go: ChatML/Llama3 template engine with stop tokens - internal/agent/reasoning.go: parse <think>/<reasoning> tags from LLM output - companion/promptbuilder.go: output structured BuildResult, add date/time context - agent/agent.go: wire templates + reasoning split into message loop - storage: add reasoning TEXT column to messages table + migration - channel/tui.go: collapsible reasoning (tab toggle), mouse scroll, polished dimmed style - config: CHAT_TEMPLATE env var (chatml|llama3|none) - plan.md: mark Phase 2 complete, add themes TODO
105 lines
2.4 KiB
Go
105 lines
2.4 KiB
Go
package llama
|
|
|
|
import (
|
|
"bytes"
|
|
"encoding/json"
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
"time"
|
|
)
|
|
|
|
type Client struct {
|
|
baseURL string
|
|
httpClient *http.Client
|
|
}
|
|
|
|
type CompletionRequest struct {
|
|
Prompt string `json:"prompt"`
|
|
Temperature float64 `json:"temperature"`
|
|
TopP float64 `json:"top_p"`
|
|
MaxTokens int `json:"n_predict"`
|
|
Stop []string `json:"stop,omitempty"`
|
|
Stream bool `json:"stream"`
|
|
CachePrompt bool `json:"cache_prompt"`
|
|
}
|
|
|
|
type CompletionResponse struct {
|
|
Content string `json:"content"`
|
|
Tokens int `json:"tokens_predicted"`
|
|
Timings struct {
|
|
PredictedPerSecond float64 `json:"predicted_per_second"`
|
|
} `json:"timings"`
|
|
}
|
|
|
|
type EmbeddingRequest struct {
|
|
Content string `json:"content"`
|
|
}
|
|
|
|
type EmbeddingResponse struct {
|
|
Embedding []float64 `json:"embedding"`
|
|
}
|
|
|
|
func NewClient(baseURL string) *Client {
|
|
return &Client{
|
|
baseURL: baseURL,
|
|
httpClient: &http.Client{
|
|
Timeout: 120 * time.Second,
|
|
},
|
|
}
|
|
}
|
|
|
|
func (c *Client) Health() error {
|
|
resp, err := c.httpClient.Get(c.baseURL + "/health")
|
|
if err != nil {
|
|
return err
|
|
}
|
|
defer resp.Body.Close()
|
|
if resp.StatusCode != http.StatusOK {
|
|
return fmt.Errorf("llama.cpp health check failed: %s", resp.Status)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func (c *Client) Complete(req *CompletionRequest) (*CompletionResponse, error) {
|
|
body, err := json.Marshal(req)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
resp, err := c.httpClient.Post(c.baseURL+"/completion", "application/json", bytes.NewReader(body))
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
defer resp.Body.Close()
|
|
if resp.StatusCode != http.StatusOK {
|
|
data, _ := io.ReadAll(resp.Body)
|
|
return nil, fmt.Errorf("llama.cpp completion failed (%d): %s", resp.StatusCode, string(data))
|
|
}
|
|
var res CompletionResponse
|
|
if err := json.NewDecoder(resp.Body).Decode(&res); err != nil {
|
|
return nil, err
|
|
}
|
|
return &res, nil
|
|
}
|
|
|
|
func (c *Client) Embed(content string) ([]float64, error) {
|
|
body, err := json.Marshal(EmbeddingRequest{Content: content})
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
resp, err := c.httpClient.Post(c.baseURL+"/embedding", "application/json", bytes.NewReader(body))
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
defer resp.Body.Close()
|
|
if resp.StatusCode != http.StatusOK {
|
|
data, _ := io.ReadAll(resp.Body)
|
|
return nil, fmt.Errorf("llama.cpp embedding failed (%d): %s", resp.StatusCode, string(data))
|
|
}
|
|
var res EmbeddingResponse
|
|
if err := json.NewDecoder(resp.Body).Decode(&res); err != nil {
|
|
return nil, err
|
|
}
|
|
return res.Embedding, nil
|
|
}
|