feat: add knowledge markdown formatting and detail retrieval

- Implemented KnowledgeWebsiteMarkdownPrompt for formatting webpage content into Markdown.
- Added GetItemDetail method in KnowledgeHandler to retrieve knowledge item details.
- Introduced KnowledgeDetailDrawer component for displaying knowledge item details in the admin web interface.
- Created MarkdownPreview component for rendering Markdown content.
- Added knowledge chunking and URL parsing logic to handle webpage content extraction and formatting.
- Updated database schema to include markdown_content in knowledge_items table.

server/internal/shared/config/config.go

@@ -79,16 +79,17 @@ type LogConfig struct {
 }
 
 type LLMConfig struct {
-	Provider        string        `mapstructure:"provider"`
-	APIKey          string        `mapstructure:"api_key"`
-	BaseURL         string        `mapstructure:"base_url"`
-	Model           string        `mapstructure:"model"`
-	Timeout         time.Duration `mapstructure:"timeout"`
-	MaxOutputTokens int64         `mapstructure:"max_output_tokens"`
-	Temperature     float64       `mapstructure:"temperature"`
-	TopP            float64       `mapstructure:"top_p"`
-	ReasoningEffort string        `mapstructure:"reasoning_effort"`
-	WebSearchLimit  int32         `mapstructure:"web_search_limit"`
+	Provider          string        `mapstructure:"provider"`
+	APIKey            string        `mapstructure:"api_key"`
+	BaseURL           string        `mapstructure:"base_url"`
+	Model             string        `mapstructure:"model"`
+	KnowledgeURLModel string        `mapstructure:"knowledge_url_model"`
+	Timeout           time.Duration `mapstructure:"timeout"`
+	MaxOutputTokens   int64         `mapstructure:"max_output_tokens"`
+	Temperature       float64       `mapstructure:"temperature"`
+	TopP              float64       `mapstructure:"top_p"`
+	ReasoningEffort   string        `mapstructure:"reasoning_effort"`
+	WebSearchLimit    int32         `mapstructure:"web_search_limit"`
 }
 
 type RetrievalConfig struct {
@@ -150,6 +151,9 @@ func applyEnvOverrides(cfg *Config) {
 	if apiKey, ok := lookupNonEmptyEnv("LLM_API_KEY"); ok {
 		cfg.LLM.APIKey = apiKey
 	}
+	if model, ok := lookupNonEmptyEnv("LLM_KNOWLEDGE_URL_MODEL"); ok {
+		cfg.LLM.KnowledgeURLModel = model
+	}
 	if apiKey, ok := lookupNonEmptyEnv("QDRANT_API_KEY"); ok {
 		cfg.Qdrant.APIKey = apiKey
 	}

server/internal/shared/llm/ark.go

@@ -113,6 +113,11 @@ func (c *arkClient) Generate(ctx context.Context, req GenerateRequest, onDelta f
 		maxOutputTokens = req.MaxOutputTokens
 	}
 
+	model := c.model
+	if strings.TrimSpace(req.Model) != "" {
+		model = strings.TrimSpace(req.Model)
+	}
+
 	callCtx, cancel := context.WithTimeout(ctx, timeout)
 	defer cancel()
 
@@ -154,7 +159,7 @@ func (c *arkClient) Generate(ctx context.Context, req GenerateRequest, onDelta f
 	}
 
 	stream, err := c.client.CreateResponsesStream(callCtx, &responses.ResponsesRequest{
-		Model:           c.model,
+		Model:           model,
 		MaxOutputTokens: &maxOutputTokens,
 		Store:           &store,
 		Stream:          &streamValue,
@@ -232,7 +237,7 @@ func (c *arkClient) Generate(ctx context.Context, req GenerateRequest, onDelta f
 
 	return &GenerateResult{
 		Content: result,
-		Model:   c.model,
+		Model:   model,
 	}, nil
 }
 

server/internal/shared/llm/client.go

@@ -13,6 +13,7 @@ import (
 var ErrNotConfigured = errors.New("llm provider is not configured")
 
 type GenerateRequest struct {
+	Model           string
 	Prompt          string
 	Timeout         time.Duration
 	MaxOutputTokens int64