feat: refactor frontend and fix LLM extraction

- Fix critical await bug in extract-stream endpoint - Add comprehensive logging to LLM and parser modules - Implement fallback to standard completion for incompatible models - Create enhanced v2.0 prompts with social media handling and few-shot examples - Add LLM health check endpoint - Decompose share page into 6 focused Svelte 5 snippets Resolves LM Studio integration issues and improves code maintainability
2025-12-21 03:49:33 +01:00
parent 377bdbf6d7
commit da58263aba
9 changed files with 2104 additions and 56 deletions
--- a/src/lib/server/llm.ts
+++ b/src/lib/server/llm.ts
@@ -2,11 +2,42 @@ import OpenAI from 'openai';
 import { env } from '$env/dynamic/private';

 export const createLLM = () => {
-    // Detect if we are using Ollama or OpenAI based on URL
-    const baseURL = env.OPENAI_BASE_URL;
-    const client = new OpenAI({
-        apiKey: env.OPENAI_API_KEY,
-        baseURL: baseURL
-    });
-    return { client, model: env.LLM_MODEL || 'gpt-4o' };
-};
+	// Detect if we are using Ollama or OpenAI based on URL
+	const baseURL = env.OPENAI_BASE_URL;
+	const apiKey = env.OPENAI_API_KEY;
+	const model = env.LLM_MODEL || 'gpt-4o';
+
+	console.log('[LLM] Initializing client...');
+	console.log('[LLM] Base URL:', baseURL);
+	console.log('[LLM] Model:', model);
+
+	if (!baseURL) {
+		throw new Error('OPENAI_BASE_URL environment variable is not set');
+	}
+
+	if (!apiKey) {
+		throw new Error('OPENAI_API_KEY environment variable is not set');
+	}
+
+	const client = new OpenAI({
+		apiKey,
+		baseURL
+	});
+
+	return { client, model };
+};
+
+/**
+ * Health check for LLM service
+ */
+export async function checkLLMHealth(): Promise<boolean> {
+	try {
+		const { client } = createLLM();
+		await client.models.list();
+		console.log('[LLM] Health check passed');
+		return true;
+	} catch (e) {
+		console.error('[LLM] Health check failed:', e);
+		return false;
+	}
+}
--- a/src/lib/server/parser.ts
+++ b/src/lib/server/parser.ts
@@ -1,6 +1,7 @@
 import { createLLM } from './llm';
 import { zodResponseFormat } from 'openai/helpers/zod';
 import { z } from 'zod';
+import { RECIPE_DETECTION_PROMPT, RECIPE_EXTRACTION_PROMPT } from './prompts/recipe-extraction';

 const RecipeSchema = z.object({
 	name: z.string(),
@@ -28,27 +29,34 @@ export async function detectRecipe(text: string): Promise<boolean> {
 	try {
 		const { client, model } = createLLM();

+		console.log('[LLM] Starting recipe detection...');
+		console.log('[LLM] Model:', model);
+		console.log('[LLM] Text length:', text.length);
+
 		const detectionResponse = await client.chat.completions.create({
 			model,
 			messages: [
 				{
 					role: 'system',
-					content:
-						"You are a recipe detector. Answer with ONLY 'yes' or 'no' - nothing else. A recipe MUST have: (1) name/title, (2) ingredients with quantities, (3) numbered cooking steps. If ANY are missing, answer 'no'."
+					content: RECIPE_DETECTION_PROMPT
 				},
 				{
 					role: 'user',
 					content: `Does this text contain a recipe?\n\n${text}`
 				}
 			],
-			max_tokens: 10
+			max_tokens: 10,
+			temperature: 0
 		});

 		const detectionResult = detectionResponse.choices[0].message.content?.toLowerCase() ?? '';
+		console.log('[LLM] Detection response:', detectionResult);
+
 		return detectionResult.includes('yes');
 	} catch (e) {
-		console.error('Recipe detection error:', e);
-		throw new Error('Failed to detect recipe');
+		console.error('[LLM] Recipe detection error:', e);
+		console.error('[LLM] Stack trace:', (e as Error).stack);
+		throw new Error(`Failed to detect recipe: ${(e as Error).message}`);
 	}
 }

@@ -61,47 +69,27 @@ export async function parseRecipe(text: string): Promise<Recipe> {
 	try {
 		const { client, model } = createLLM();

+		console.log('[LLM] Starting recipe parsing...');
+		console.log('[LLM] Model:', model);
+
 		const completion = await client.beta.chat.completions.parse({
 			model,
 			messages: [
 				{
 					role: 'system',
-					content: `You are a RECIPE EXTRACTOR. Extract the recipe from the provided text.
-
-✅ REQUIREMENTS:
-1. Extract the exact recipe name from the text
-2. List all ingredients with their quantities and units
-3. List all cooking steps in order
-4. Translate everything to Italian
-5. Convert measurements to SI units (g, mL, °C)
-
-📋 CONVERSION TABLE:
- 1 cup = 240 mL, 1 tbsp = 15 mL, 1 tsp = 5 mL
- 1 oz = 28.35 g, 1 lb = 453.59 g
- 1 stick butter = 113 g
- °F→°C: (°F–32)×5/9
-
-🔄 OUTPUT FORMAT:
-{
-  "name": "recipe name in Italian",
-  "servings": number or null,
-  "description": "description in Italian or null",
-  "ingredients": [{"item": "ingredient name", "amount": "quantity", "unit": "SI unit"}],
-  "steps": ["1. First step", "2. Second step", ...]
-}
-
-Extract ONLY what's explicitly in the text. Be accurate and literal.
-				`
+					content: RECIPE_EXTRACTION_PROMPT
 				},
 				{
 					role: 'user',
 					content: `Extract the recipe from this text:\n\n${text}`
 				}
 			],
-			response_format: zodResponseFormat(RecipeSchema, 'recipe')
+			response_format: zodResponseFormat(RecipeSchema, 'recipe'),
+			temperature: 0.3
 		});

 		const recipe = completion.choices[0].message.parsed;
+		console.log('[LLM] Parse response:', recipe?.name);

 		if (!recipe || !recipe.name) {
 			throw new Error('Failed to extract recipe - missing name');
@@ -109,8 +97,17 @@ Extract ONLY what's explicitly in the text. Be accurate and literal.

 		return recipe;
 	} catch (e) {
-		console.error('Recipe parsing error:', e);
-		throw new Error('Failed to parse recipe');
+		console.error('[LLM] Recipe parsing error:', e);
+		console.error('[LLM] Stack trace:', (e as Error).stack);
+
+		// If structured output fails, try standard completion
+		if ((e as any).message?.includes('response_format') ||
+			(e as any).message?.includes('structured output')) {
+			console.warn('[LLM] Falling back to standard completion');
+			return await parseRecipeWithStandardCompletion(text);
+		}
+
+		throw new Error(`Failed to parse recipe: ${(e as Error).message}`);
 	}
 }

@@ -128,3 +125,56 @@ export async function extractRecipe(text: string): Promise<Recipe | null> {

 	return parseRecipe(text);
 }
+
+/**
+ * Fallback parser using standard completion (no structured output)
+ * Used when the model doesn't support beta.chat.completions.parse()
+ */
+async function parseRecipeWithStandardCompletion(text: string): Promise<Recipe> {
+	const { client, model } = createLLM();
+
+	console.log('[LLM] Using standard completion fallback');
+
+	const completion = await client.chat.completions.create({
+		model,
+		messages: [
+			{
+				role: 'system',
+				content: `You are a recipe extractor. Return ONLY valid JSON matching this schema:
+{
+  "name": "recipe name in Italian",
+  "servings": number or null,
+  "description": "description in Italian or null",
+  "ingredients": [{"item": "ingredient name", "amount": "quantity", "unit": "SI unit"}],
+  "steps": ["1. First step", "2. Second step", ...]
+}
+
+Convert all measurements to SI units (g, mL, °C).
+Translate everything to Italian.
+Extract ONLY what's in the text.`
+			},
+			{
+				role: 'user',
+				content: `Extract the recipe from this text:\n\n${text}`
+			}
+		],
+		max_tokens: 2000,
+		temperature: 0.3
+	});
+
+	const jsonResponse = completion.choices[0].message.content;
+	if (!jsonResponse) {
+		throw new Error('Empty response from LLM');
+	}
+
+	console.log('[LLM] Standard completion raw response:', jsonResponse.substring(0, 200));
+
+	// Parse and validate JSON (remove code fences if present)
+	const cleanedJson = jsonResponse.replace(/```json\n?|```\n?/g, '').trim();
+	const parsedData = JSON.parse(cleanedJson);
+	const recipe = RecipeSchema.parse(parsedData);
+
+	console.log('[LLM] Standard completion parsed recipe:', recipe.name);
+
+	return recipe;
+}
--- a/src/lib/server/prompts/recipe-extraction.ts
+++ b/src/lib/server/prompts/recipe-extraction.ts
@@ -0,0 +1,220 @@
+/**
+ * Recipe Extraction System Prompts - Version 2.0
+ * 
+ * Changelog:
+ * - v2.0 (2025-12-21): Added social media handling, few-shot examples, partial recipe support
+ * - v1.0 (2024): Initial version with Italian translation and SI conversion
+ */
+
+export const RECIPE_DETECTION_PROMPT = `You are a recipe detector for social media posts.
+
+Your task: Determine if the text contains a complete or partial recipe.
+
+REQUIREMENTS FOR "YES":
+1. Recipe name/title is present
+2. At least 3 ingredients with quantities (even if approximate)
+3. At least 2 cooking steps
+
+IGNORE:
+- Hashtags (#recipe, #food, etc.)
+- Mentions (@username)
+- Emojis
+- Like counts, comments, social metadata
+- Promotional text
+
+OUTPUT: Answer with ONLY 'yes' or 'no' - nothing else.
+
+EXAMPLES:
+
+Text: "🍝 Pasta al Pomodoro 🍅 Ingredients: 320g pasta, 400g tomatoes, 2 garlic cloves. Boil pasta. Sauté garlic. Add tomatoes. Mix! #italianfood @chef"
+Answer: yes
+
+Text: "Amazing dinner tonight! 😍 So delicious! 🔥 #foodporn"
+Answer: no
+
+Text: "You need pasta, tomatoes, and garlic for this recipe"
+Answer: no (missing steps)
+`;
+
+export const RECIPE_EXTRACTION_PROMPT = `You are an EXPERT RECIPE EXTRACTOR specialized in parsing recipes from social media posts.
+
+🎯 YOUR MISSION:
+Extract structured recipe data from text that may contain social media noise, emojis, hashtags, and promotional content.
+
+✅ CORE REQUIREMENTS:
+
+1. **Text Cleaning**: Ignore hashtags, mentions, emojis, like counts, promotional text
+2. **Name Extraction**: Extract exact recipe name (translate to Italian)
+3. **Ingredient Parsing**: Extract all ingredients with quantities and units
+4. **Step Extraction**: Extract all cooking steps in order
+5. **Translation**: Translate ALL content to Italian
+6. **Unit Conversion**: Convert ALL measurements to SI units (g, mL, °C)
+
+📏 COMPREHENSIVE CONVERSION TABLE:
+
+**Volume (to mL):**
+- 1 cup = 240 mL
+- 1 tablespoon (tbsp) = 15 mL
+- 1 teaspoon (tsp) = 5 mL
+- 1 fluid oz (fl oz) = 30 mL
+- 1 pint = 473 mL
+- 1 quart = 946 mL
+- 1 gallon = 3785 mL
+
+**Weight (to g):**
+- 1 oz = 28.35 g
+- 1 lb (pound) = 453.59 g
+- 1 stick butter = 113 g
+
+**Temperature (to °C):**
+- Formula: (°F - 32) × 5/9
+- 350°F = 175°C
+- 375°F = 190°C
+- 400°F = 200°C
+- 425°F = 220°C
+
+**Special Cases:**
+- "a pinch" = "un pizzico" (no quantity)
+- "to taste" = "q.b." (quanto basta)
+- "1-2 cups" → use midpoint → 1.5 cup = 360 mL
+- "1/2 cup" = 120 mL
+- "1/4 cup" = 60 mL
+
+🔄 OUTPUT FORMAT (JSON):
+
+{
+  "name": "Nome della Ricetta in Italiano",
+  "servings": 4 or null,
+  "description": "Descrizione in italiano o null",
+  "ingredients": [
+    {"item": "nome ingrediente", "amount": "quantità", "unit": "unità SI"},
+    {"item": "aglio", "amount": "2", "unit": "spicchi"}
+  ],
+  "steps": [
+    "1. Primo passaggio dettagliato",
+    "2. Secondo passaggio dettagliato"
+  ]
+}
+
+🎓 FEW-SHOT EXAMPLES:
+
+**Example 1: Clean Recipe**
+
+Input:
+"Chocolate Chip Cookies
+
+Ingredients:
+- 2 cups all-purpose flour
+- 1 tsp baking soda
+- 1 cup butter
+- 3/4 cup sugar
+- 2 eggs
+- 2 cups chocolate chips
+
+Instructions:
+1. Preheat oven to 375°F
+2. Mix flour and baking soda
+3. Cream butter and sugar
+4. Add eggs
+5. Fold in chocolate chips
+6. Bake for 10 minutes"
+
+Output:
+{
+  "name": "Biscotti con Gocce di Cioccolato",
+  "servings": null,
+  "description": null,
+  "ingredients": [
+    {"item": "farina 00", "amount": "480", "unit": "mL"},
+    {"item": "bicarbonato di sodio", "amount": "5", "unit": "mL"},
+    {"item": "burro", "amount": "240", "unit": "mL"},
+    {"item": "zucchero", "amount": "180", "unit": "mL"},
+    {"item": "uova", "amount": "2", "unit": "pz"},
+    {"item": "gocce di cioccolato", "amount": "480", "unit": "mL"}
+  ],
+  "steps": [
+    "1. Preriscaldare il forno a 190°C",
+    "2. Mescolare farina e bicarbonato di sodio",
+    "3. Montare burro e zucchero a crema",
+    "4. Aggiungere le uova",
+    "5. Incorporare le gocce di cioccolato",
+    "6. Cuocere per 10 minuti"
+  ]
+}
+
+**Example 2: Social Media Post**
+
+Input:
+"🍝 OMG this pasta is AMAZING! 😍👌
+
+Farfalle al Salmone by @lulugargari 🔥
+
+What you need:
+Farfalle 320g
+Smoked salmon 200g
+Heavy cream 200g
+Shallot 1/2
+Tomato paste 1 tbsp
+White wine 1/2 cup
+Butter 20g
+Salt & pepper to taste
+
+How to make it:
+Chop the salmon. Melt butter, add shallot, cook a bit. Deglaze with wine, add salmon, cook 2 mins. Add cream, pepper, tomato paste. Cook pasta al dente, finish in pan. Enjoy! 😋
+
+14K likes 🔥 #pasta #recipe #italianfood"
+
+Output:
+{
+  "name": "Farfalle al Salmone",
+  "servings": null,
+  "description": null,
+  "ingredients": [
+    {"item": "farfalle", "amount": "320", "unit": "g"},
+    {"item": "salmone affumicato", "amount": "200", "unit": "g"},
+    {"item": "panna fresca liquida", "amount": "200", "unit": "g"},
+    {"item": "scalogno", "amount": "0.5", "unit": "pz"},
+    {"item": "concentrato di pomodoro", "amount": "15", "unit": "mL"},
+    {"item": "vino bianco", "amount": "120", "unit": "mL"},
+    {"item": "burro", "amount": "20", "unit": "g"},
+    {"item": "sale", "amount": "q.b.", "unit": ""},
+    {"item": "pepe nero", "amount": "q.b.", "unit": ""}
+  ],
+  "steps": [
+    "1. Tritare il salmone affumicato",
+    "2. Sciogliere il burro e aggiungere lo scalogno tritato, far andare per qualche minuto",
+    "3. Sfumare con il vino e aggiungere il salmone, cuocere un paio di minuti",
+    "4. Aggiungere la panna, il pepe e il concentrato di pomodoro",
+    "5. Cuocere la pasta al dente e ultimare la cottura in padella"
+  ]
+}
+
+🛡️ EDGE CASE HANDLING:
+
+1. **Missing Servings**: Set to null
+2. **Missing Description**: Set to null
+3. **Ingredient Ranges** (e.g., "1-2 cups"): Use midpoint
+4. **Vague Quantities** ("a handful"): Use "q.b." and empty unit
+5. **Missing Units**: Infer from context (e.g., "2 eggs" → "2 pz")
+6. **Multiple Recipes**: Extract ONLY the first recipe
+7. **Incomplete Recipe**: Extract what's available, set missing fields to null or empty array
+
+⚠️ CRITICAL RULES:
+
+- Extract ONLY what's explicitly in the text - DO NOT invent ingredients or steps
+- Be LITERAL and ACCURATE - preserve ingredient names and quantities
+- IGNORE all social media metadata (likes, comments, emojis, hashtags, mentions)
+- If units are missing, use context clues or standard assumptions
+- Translate faithfully to Italian, preserving culinary terms accurately
+- Number all steps sequentially starting with "1."
+
+🎯 QUALITY CHECKLIST:
+
+Before returning, verify:
+- [ ] All ingredients have item, amount, and unit
+- [ ] All measurements converted to SI units (g, mL, °C)
+- [ ] All text translated to Italian
+- [ ] All steps numbered sequentially
+- [ ] No social media noise (emojis, hashtags, mentions) in output
+- [ ] JSON is valid and matches schema
+`;