Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

allow image urls in image-reader #796

Merged
merged 2 commits into from
Dec 12, 2024
Merged

allow image urls in image-reader #796

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6efe291
allow image urls in image-reader
Dec 12, 2024
51a319a
minor change
Dec 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 16 additions & 3 deletions src/Plugins/BotSharp.Plugin.FileHandler/Functions/ReadImageFn.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,8 +23,9 @@ public async Task<bool> Execute(RoleDialogModel message)
var agentService = _services.GetRequiredService<IAgentService>();

var wholeDialogs = conv.GetDialogHistory();
var dialogs = AssembleFiles(conv.ConversationId, wholeDialogs);
var agent = await agentService.LoadAgent(BuiltInAgentId.UtilityAssistant);
var dialogs = AssembleFiles(conv.ConversationId, args?.ImageUrls, wholeDialogs);
var agentId = !string.IsNullOrWhiteSpace(message.CurrentAgentId) ? message.CurrentAgentId : BuiltInAgentId.UtilityAssistant;
var agent = await agentService.LoadAgent(agentId);
var fileAgent = new Agent
{
Id = agent?.Id ?? Guid.Empty.ToString(),
Expand All @@ -38,7 +39,7 @@ public async Task<bool> Execute(RoleDialogModel message)
return true;
}

private List<RoleDialogModel> AssembleFiles(string conversationId, List<RoleDialogModel> dialogs)
private List<RoleDialogModel> AssembleFiles(string conversationId, IEnumerable<string>? imageUrls, List<RoleDialogModel> dialogs)
{
if (dialogs.IsNullOrEmpty())
{
Expand Down Expand Up @@ -66,6 +67,18 @@ private List<RoleDialogModel> AssembleFiles(string conversationId, List<RoleDial
}).ToList();
}

if (!imageUrls.IsNullOrEmpty())
{
var lastDialog = dialogs.Last();
var files = lastDialog.Files ?? [];
var addnFiles = imageUrls.Select(x => x?.Trim())
.Where(x => !string.IsNullOrWhiteSpace(x))
.Select(x => new BotSharpFile { FileUrl = x }).ToList();

files.AddRange(addnFiles);
lastDialog.Files = files;
}

return dialogs;
}

Expand Down
8 changes: 8 additions & 0 deletions src/Plugins/BotSharp.Plugin.FileHandler/LlmContexts/LlmContextIn.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,4 +11,12 @@ public class LlmContextIn
[JsonPropertyName("image_description")]
[JsonIgnore(Condition = JsonIgnoreCondition.WhenWritingNull)]
public string? ImageDescription { get; set; }

//[JsonPropertyName("image_url")]
//[JsonIgnore(Condition = JsonIgnoreCondition.WhenWritingNull)]
//public string? ImageUrl { get; set; }

[JsonPropertyName("image_urls")]
[JsonIgnore(Condition = JsonIgnoreCondition.WhenWritingNull)]
public IEnumerable<string>? ImageUrls { get; set; }
}
8 changes: 8 additions & 0 deletions ...dler/data/agents/6745151e-6d46-4a02-8de4-1c4f21c7da95/functions/util-file-read_image.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,14 @@
"user_request": {
"type": "string",
"description": "The request posted by user, which is related to analyzing requested images. User can request for multiple images to process at one time."
},
"image_urls": {
"type": "array",
"description": "The image, photo or picture urls that user requests for analysis. They typically start with 'http' or 'https'. If user doesn't include any url, then leave this array empty. Please remove any duplicated urls",
"items": {
"type": "string",
"description": "The image, photo or picture url that user requests for analysis. It typically starts with http or https."
}
}
},
"required": [ "user_request" ]
Expand Down