feat: implement image upload and multimodal support

- Added functionality for image uploads in chat, allowing users to attach images for multimodal Q&A.
- Enhanced the input field to handle image selection via drag-and-drop and paste, with validation for file types and sizes.
- Updated the backend to process images alongside text queries, including support for image analysis.
- Introduced new UI components for image previews and management, improving user interaction with uploaded content.
- Added localization strings for image upload features and error messages, enhancing accessibility for users in multiple languages.

These changes significantly improve the chat experience by enabling users to incorporate images into their queries, facilitating richer interactions and responses.
This commit is contained in:
wizardchen
2026-03-11 17:17:32 +08:00
parent 8de1cfb6b5
commit 991bd29a14
42 changed files with 1554 additions and 226 deletions
+5
View File
@@ -35,6 +35,11 @@ export interface CustomAgentConfig {
// false: 根据 kb_selection_mode 自动检索知识库
retrieve_kb_only_when_mentioned?: boolean;
// ===== 图片上传/多模态设置 =====
image_upload_enabled?: boolean; // 是否启用图片上传(默认: false)
vlm_model_id?: string; // VLM模型ID(图片分析用)
image_storage_provider?: string; // 图片存储提供商
// ===== 文件类型限制 =====
// 支持的文件类型(如 ["csv", "xlsx", "xls"])
// 为空表示支持所有文件类型
+5 -1
View File
@@ -29,7 +29,7 @@ export function useStream() {
let renderTimer: number | null = null
// 启动流式请求
const startStream = async (params: { session_id: any; query: any; knowledge_base_ids?: string[]; knowledge_ids?: string[]; agent_enabled?: boolean; agent_id?: string; web_search_enabled?: boolean; enable_memory?: boolean; summary_model_id?: string; mcp_service_ids?: string[]; mentioned_items?: Array<{id: string; name: string; type: string; kb_type?: string}>; method: string; url: string }) => {
const startStream = async (params: { session_id: any; query: any; knowledge_base_ids?: string[]; knowledge_ids?: string[]; agent_enabled?: boolean; agent_id?: string; web_search_enabled?: boolean; enable_memory?: boolean; summary_model_id?: string; mcp_service_ids?: string[]; mentioned_items?: Array<{id: string; name: string; type: string; kb_type?: string}>; images?: Array<{data: string}>; method: string; url: string }) => {
// 重置状态
output.value = '';
error.value = null;
@@ -114,6 +114,10 @@ export function useStream() {
if (params.mentioned_items !== undefined && params.mentioned_items.length > 0) {
postBody.mentioned_items = params.mentioned_items;
}
// Include images if provided (base64 data URIs for multimodal chat)
if (params.images !== undefined && params.images.length > 0) {
postBody.images = params.images;
}
await fetchEventSource(url, {
method: params.method,
+1
View File
@@ -22,6 +22,7 @@ export interface ModelConfig {
interface_type?: 'ollama' | 'openai'; // VLLM专用
parameter_size?: string; // Ollama模型参数大小 (e.g., "7B", "13B", "70B")
extra_config?: Record<string, string>; // Provider-specific configuration
supports_vision?: boolean; // Whether the model accepts image/multimodal input
};
is_default?: boolean;
is_builtin?: boolean;