-
Notifications
You must be signed in to change notification settings - Fork 3.1k
/
Google_GeminiVision.cs
123 lines (102 loc) · 5.18 KB
/
Google_GeminiVision.cs
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
// Copyright (c) Microsoft. All rights reserved.
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.ChatCompletion;
using Resources;
namespace ChatCompletion;
public sealed class Google_GeminiVision(ITestOutputHelper output) : BaseTest(output)
{
[Fact]
public async Task GoogleAIAsync()
{
Console.WriteLine("============= Google AI - Gemini Chat Completion with vision =============");
string geminiApiKey = TestConfiguration.GoogleAI.ApiKey;
string geminiModelId = TestConfiguration.GoogleAI.Gemini.ModelId;
if (geminiApiKey is null)
{
Console.WriteLine("Gemini credentials not found. Skipping example.");
return;
}
Kernel kernel = Kernel.CreateBuilder()
.AddGoogleAIGeminiChatCompletion(
modelId: geminiModelId,
apiKey: geminiApiKey)
.Build();
var chatHistory = new ChatHistory("Your job is describing images.");
var chatCompletionService = kernel.GetRequiredService<IChatCompletionService>();
// Load the image from the resources
await using var stream = EmbeddedResource.ReadStream("sample_image.jpg")!;
using var binaryReader = new BinaryReader(stream);
var bytes = binaryReader.ReadBytes((int)stream.Length);
chatHistory.AddUserMessage(
[
new TextContent("What’s in this image?"),
// Google AI Gemini API requires the image to be in base64 format, doesn't support URI
// You have to always provide the mimeType for the image
new ImageContent(bytes, "image/jpeg"),
]);
var reply = await chatCompletionService.GetChatMessageContentAsync(chatHistory);
Console.WriteLine(reply.Content);
}
[Fact]
public async Task VertexAIAsync()
{
Console.WriteLine("============= Vertex AI - Gemini Chat Completion with vision =============");
string geminiBearerKey = TestConfiguration.VertexAI.BearerKey;
string geminiModelId = TestConfiguration.VertexAI.Gemini.ModelId;
string geminiLocation = TestConfiguration.VertexAI.Location;
string geminiProject = TestConfiguration.VertexAI.ProjectId;
if (geminiBearerKey is null || geminiLocation is null || geminiProject is null)
{
Console.WriteLine("Gemini vertex ai credentials not found. Skipping example.");
return;
}
Kernel kernel = Kernel.CreateBuilder()
.AddVertexAIGeminiChatCompletion(
modelId: geminiModelId,
bearerKey: geminiBearerKey,
location: geminiLocation,
projectId: geminiProject)
.Build();
// To generate bearer key, you need installed google sdk or use google web console with command:
//
// gcloud auth print-access-token
//
// Above code pass bearer key as string, it is not recommended way in production code,
// especially if IChatCompletionService will be long lived, tokens generated by google sdk lives for 1 hour.
// You should use bearer key provider, which will be used to generate token on demand:
//
// Example:
//
// Kernel kernel = Kernel.CreateBuilder()
// .AddVertexAIGeminiChatCompletion(
// modelId: TestConfiguration.VertexAI.Gemini.ModelId,
// bearerKeyProvider: () =>
// {
// // This is just example, in production we recommend using Google SDK to generate your BearerKey token.
// // This delegate will be called on every request,
// // when providing the token consider using caching strategy and refresh token logic when it is expired or close to expiration.
// return GetBearerKey();
// },
// location: TestConfiguration.VertexAI.Location,
// projectId: TestConfiguration.VertexAI.ProjectId);
var chatHistory = new ChatHistory("Your job is describing images.");
var chatCompletionService = kernel.GetRequiredService<IChatCompletionService>();
// Load the image from the resources
await using var stream = EmbeddedResource.ReadStream("sample_image.jpg")!;
using var binaryReader = new BinaryReader(stream);
var bytes = binaryReader.ReadBytes((int)stream.Length);
chatHistory.AddUserMessage(
[
new TextContent("What’s in this image?"),
// Vertex AI Gemini API supports both base64 and URI format
// You have to always provide the mimeType for the image
new ImageContent(bytes, "image/jpeg"),
// The Cloud Storage URI of the image to include in the prompt.
// The bucket that stores the file must be in the same Google Cloud project that's sending the request.
// new ImageContent(new Uri("gs://generativeai-downloads/images/scones.jpg"),
// metadata: new Dictionary<string, object?> { { "mimeType", "image/jpeg" } })
]);
var reply = await chatCompletionService.GetChatMessageContentAsync(chatHistory);
Console.WriteLine(reply.Content);
}
}