Evan Reichard
e60b1ea8d5
Add vision/multimodal support to chat, allowing users to send images alongside or instead of text prompts. Images are transmitted and persisted as base64 data URLs. Backend: - Add Images []string to Message struct for persistence - Add Images []string to GenerateTextRequest with relaxed validation - Build multimodal user messages using OpenAI SDK content parts - Pass images through from handlers to client - Deep-copy Images slice in message cloning Frontend: - Add images?: string[] to Message and GenerateTextRequest types - Add image selection state and file input handler - Add camera icon button, hidden file input, and image preview strip - Render images in user message bubbles - Pass images through to GenerateTextRequest Tests: - Add TestSendMessageWithImage for vision model testing
127 lines
3.2 KiB
Go
127 lines
3.2 KiB
Go
package client
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"net/url"
|
|
"testing"
|
|
"time"
|
|
|
|
"reichard.io/aethera/internal/store"
|
|
)
|
|
|
|
const model = "vllm-qwen3.6-27b-thinking"
|
|
|
|
func TestSendMessage(t *testing.T) {
|
|
t.Skip("requires live LLM API - run manually with: go test -run TestSendMessage ./internal/client/")
|
|
|
|
// Initialize Client
|
|
baseURL, err := url.Parse("https://llm-api.va.reichard.io/v1")
|
|
if err != nil {
|
|
t.Fatalf("Failed to parse base URL: %v", err)
|
|
}
|
|
client := NewClient(baseURL)
|
|
|
|
// Create Context
|
|
ctx, cancel := context.WithTimeout(context.Background(), 120*time.Second)
|
|
defer cancel()
|
|
|
|
// Generate Text Stream
|
|
var contentBuf, thinkingBuf bytes.Buffer
|
|
_, err = client.SendMessage(ctx, []*store.Message{{
|
|
Role: "user",
|
|
Content: "What is 2+2? Think step by step.",
|
|
}}, model, func(mc *MessageChunk) error {
|
|
if mc.Thinking != nil {
|
|
_, err := thinkingBuf.Write([]byte(*mc.Thinking))
|
|
return err
|
|
}
|
|
if mc.Message != nil {
|
|
_, err := contentBuf.Write([]byte(*mc.Message))
|
|
return err
|
|
}
|
|
return nil
|
|
})
|
|
if err != nil {
|
|
t.Fatalf("Failed to generate text stream: %v", err)
|
|
}
|
|
|
|
// Verify Thinking
|
|
thinking := thinkingBuf.String()
|
|
if thinking == "" {
|
|
t.Error("No thinking content was received")
|
|
} else {
|
|
t.Logf("Thinking (%d bytes): %s", len(thinking), thinking)
|
|
}
|
|
|
|
// Verify Content
|
|
output := contentBuf.String()
|
|
if output == "" {
|
|
t.Error("No content was written to the buffer")
|
|
} else {
|
|
t.Logf("Content (%d bytes): %s", len(output), output)
|
|
}
|
|
}
|
|
|
|
func TestSummarizeChat(t *testing.T) {
|
|
t.Skip("requires live LLM API - run manually with: go test -run TestSummarizeChat ./internal/client/")
|
|
|
|
// Initialize Client
|
|
baseURL, err := url.Parse("https://llm-api.va.reichard.io/v1")
|
|
if err != nil {
|
|
t.Fatalf("Failed to parse base URL: %v", err)
|
|
}
|
|
client := NewClient(baseURL)
|
|
|
|
// Create Context
|
|
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
|
|
defer cancel()
|
|
|
|
// Generate Text Stream
|
|
userMessage := "Write me a go program that reads in a zip file and prints the contents along with their sizes and mimetype."
|
|
output, err := client.CreateTitle(ctx, userMessage, model)
|
|
if err != nil {
|
|
t.Fatalf("Failed to generate text stream: %v", err)
|
|
}
|
|
|
|
// Verify Results
|
|
if output == "" {
|
|
t.Error("No content was written to the buffer")
|
|
} else {
|
|
t.Logf("Successfully received %d bytes from the stream", len(output))
|
|
t.Logf("Output: %s", output)
|
|
}
|
|
}
|
|
|
|
func TestSendMessageWithImage(t *testing.T) {
|
|
t.Skip("requires live LLM API - run manually with: go test -run TestSendMessageWithImage ./internal/client/")
|
|
|
|
// Initialize Client
|
|
baseURL, err := url.Parse("https://llm-api.va.reichard.io/v1")
|
|
if err != nil {
|
|
t.Fatalf("Failed to parse base URL: %v", err)
|
|
}
|
|
client := NewClient(baseURL)
|
|
|
|
// Create Context
|
|
ctx, cancel := context.WithTimeout(context.Background(), 120*time.Second)
|
|
defer cancel()
|
|
|
|
// Generate Text Stream
|
|
_, err = client.SendMessage(ctx, []*store.Message{{
|
|
Role: "user",
|
|
Content: "What is in this image?",
|
|
Images: []string{
|
|
"https://llm-api.va.reichard.io/v1/images/test.png",
|
|
},
|
|
}}, "vllm-qwen3-8b-vision", func(mc *MessageChunk) error {
|
|
if mc.Message != nil {
|
|
t.Logf("Received: %s", *mc.Message)
|
|
}
|
|
return nil
|
|
})
|
|
if err != nil {
|
|
t.Fatalf("Failed to generate text stream: %v", err)
|
|
}
|
|
}
|