rag

backend/rag_system.py

@@ -0,0 +1,175 @@
+"""
+Recipe RAG System - A retrieval-augmented generation system for recipes
+Author: [Your Name]
+Date: February 2025
+
+This system combines vector search with language model generation to provide
+contextually relevant recipe information based on user queries.
+"""
+
+from llama_index.core import VectorStoreIndex, Document, Settings
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from datasets import load_dataset
+from transformers import pipeline
+import torch
+import logging
+from typing import List, Dict, Any, Optional
+import os
+from dotenv import load_dotenv
+
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+# Load environment variables
+load_dotenv()
+
+class RecipeRAGSystem:
+    """
+    A Retrieval-Augmented Generation system specialized for recipe queries.
+    
+    This class handles both the retrieval of relevant recipe documents from a vector store
+    and the generation of helpful responses using a language model.
+    """
+    
+    def __init__(
+        self, 
+        embedding_model: str = "BAAI/bge-small-en-v1.5",
+        llm_model: str = "microsoft/Phi-3-mini-4k-instruct",
+        dataset_name: str = "m3hrdadfi/recipe_nlg_lite",
+        temperature: float = 0.7,
+        top_k: int = 3
+    ):
+        """
+        Initialize the RAG system with specified models and parameters.
+        
+        Args:
+            embedding_model: Name of the HuggingFace embedding model
+            llm_model: Name of the language model for generation
+            dataset_name: Name of the HuggingFace dataset containing recipes
+            temperature: Sampling temperature for text generation
+            top_k: Default number of documents to retrieve
+        """
+        logger.info(f"Initializing RecipeRAGSystem with {embedding_model} and {llm_model}")
+        
+        # Configure embedding model
+        Settings.llm = None
+        Settings.embed_model = HuggingFaceEmbedding(model_name=embedding_model)
+        
+        # Configure LLM
+        self.generator = pipeline(
+            "text-generation",
+            model=llm_model,
+            torch_dtype=torch.float32,
+            device_map="auto" if torch.cuda.is_available() else "cpu",
+            do_sample=True,
+            temperature=temperature
+        )
+        
+        self.default_top_k = top_k
+        self.dataset_name = dataset_name
+        self.index = None
+        
+        # Build index
+        self._build_index()
+    
+    def _build_index(self) -> None:
+        """
+        Build the vector index from the recipe dataset.
+        
+        This method loads the recipe dataset and converts entries to documents
+        suitable for indexing with LlamaIndex.
+        """
+        logger.info(f"Building index from dataset: {self.dataset_name}")
+        try:
+            dataset = load_dataset(self.dataset_name, trust_remote_code=True)
+            
+            # Build documents with structured content
+            documents = []
+            for item in dataset["train"]:
+                text = (
+                    f"Recipe: {item['name']}\n"
+                    f"Ingredients: {item['ingredients']}\n"
+                    f"Steps: {item['steps']}"
+                )
+                documents.append(Document(text=text, metadata={"name": item["name"]}))
+            
+            logger.info(f"Created {len(documents)} recipe documents")
+            self.index = VectorStoreIndex.from_documents(documents)
+            
+        except Exception as e:
+            logger.error(f"Error building index: {str(e)}")
+            raise
+    
+    def retrieve(self, query: str, top_k: Optional[int] = None) -> Dict[str, Any]:
+        """
+        Retrieve relevant recipe documents for a user query.
+        
+        Args:
+            query: The user's recipe-related query
+            top_k: Number of documents to retrieve (overrides default)
+            
+        Returns:
+            A dictionary containing query results and metadata
+        """
+        k = top_k or self.default_top_k
+        logger.info(f"Retrieving top {k} documents for query: '{query}'")
+        
+        try:
+            query_engine = self.index.as_query_engine(similarity_top_k=k)
+            result = query_engine.query(query)
+            
+            # Extract source nodes and metadata
+            sources = [n.node.get_content() for n in result.source_nodes]
+            metadata = [n.node.metadata for n in result.source_nodes]
+            
+            return {
+                "result": result,
+                "sources": sources,
+                "metadata": metadata
+            }
+        except Exception as e:
+            logger.error(f"Retrieval error: {str(e)}")
+            raise
+    
+    def generate_answer(self, question: str, context: List[str]) -> str:
+        """
+        Generate a helpful response based on the retrieved recipe context.
+        
+        Args:
+            question: The user's original question
+            context: List of retrieved recipe documents as context
+            
+        Returns:
+            The generated response
+        """
+        logger.info(f"Generating answer for: '{question}'")
+        
+        try:
+            # Build a detailed prompt with system context and retrieved information
+            prompt = f"""
+            [INST] <<SYS>>
+            You are a professional recipe assistant. Answer the user's question based on the following recipes:
+            
+            {"".join(context)}
+            <</SYS>>
+            
+            Question: {question} [/INST]
+            """
+            
+            result = self.generator(
+                prompt,
+                max_new_tokens=256,
+                temperature=0.7
+            )[0]['generated_text']
+            
+            # Extract just the model's response part
+            response = result.split("[/INST]")[-1].strip()
+            return response
+            
+        except Exception as e:
+            logger.error(f"Generation error: {str(e)}")
+            raise

backend/requirements.txt

@@ -0,0 +1,10 @@
+fastapi>=0.68.0
+uvicorn>=0.15.0
+python-dotenv>=0.19.0
+datasets>=2.0.0
+transformers>=4.30.0
+torch>=2.0.0
+llama-index-core>=0.10.0
+llama-index-embeddings-huggingface>=0.1.0
+pytest>=7.4.0
+httpx>=0.24.0

backend/server.py

@@ -0,0 +1,164 @@
+from fastapi import FastAPI, HTTPException, Depends, Request
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse
+from pydantic import BaseModel, Field
+from typing import List, Dict, Any, Optional
+import logging
+import time
+import os
+from dotenv import load_dotenv
+
+# Import the RAG system
+from rag_system import RecipeRAGSystem
+
+# Load environment variables
+load_dotenv()
+
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+# Initialize FastAPI app
+app = FastAPI(
+    title="Recipe Assistant API",
+    description="An API for a Recipe RAG (Retrieval-Augmented Generation) system",
+    version="1.0.0"
+)
+
+# CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=os.getenv("ALLOWED_ORIGINS", "*").split(","),
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Request models
+class ChatRequest(BaseModel):
+    message: str = Field(..., description="User's recipe-related question")
+    top_k: Optional[int] = Field(3, description="Number of recipes to retrieve")
+
+class FeedbackRequest(BaseModel):
+    query_id: str = Field(..., description="Unique ID of the query")
+    rating: int = Field(..., ge=1, le=5, description="Rating (1-5)")
+    feedback: Optional[str] = Field(None, description="Optional feedback text")
+
+# Response models
+class ChatResponse(BaseModel):
+    answer: str = Field(..., description="Generated answer to the user's question")
+    sources: List[str] = Field(..., description="Recipe sources used for the answer")
+    query_id: str = Field(..., description="Unique ID for this query")
+    response_time: float = Field(..., description="Processing time in seconds")
+
+# Request ID middleware
+@app.middleware("http")
+async def add_process_time_header(request: Request, call_next):
+    start_time = time.time()
+    response = await call_next(request)
+    process_time = time.time() - start_time
+    response.headers["X-Process-Time"] = str(process_time)
+    return response
+
+# Global error handler
+@app.exception_handler(Exception)
+async def global_exception_handler(request: Request, exc: Exception):
+    logger.error(f"Global error: {str(exc)}")
+    return JSONResponse(
+        status_code=500,
+        content={"detail": "An unexpected error occurred", "type": type(exc).__name__},
+    )
+
+# Initialize the RAG system (with lazy loading)
+_rag_system = None
+
+def get_rag_system():
+    """
+    Lazily initialize the RAG system.
+    This helps with faster API startup and better resource management.
+    """
+    global _rag_system
+    if _rag_system is None:
+        logger.info("Initializing RAG system")
+        _rag_system = RecipeRAGSystem(
+            embedding_model=os.getenv("EMBEDDING_MODEL", "BAAI/bge-small-en-v1.5"),
+            llm_model=os.getenv("LLM_MODEL", "microsoft/Phi-3-mini-4k-instruct"),
+            temperature=float(os.getenv("TEMPERATURE", "0.7"))
+        )
+    return _rag_system
+
+# API endpoints
+@app.post("/api/chat", response_model=ChatResponse)
+async def chat_endpoint(request: ChatRequest, rag_system: RecipeRAGSystem = Depends(get_rag_system)):
+    """
+    Process a user query about recipes and return a generated response with sources.
+    """
+    start_time = time.time()
+    query_id = f"query-{int(start_time)}"
+    logger.info(f"Processing chat request {query_id}: {request.message}")
+    
+    try:
+        # Retrieve relevant recipes
+        retrieval_result = rag_system.retrieve(request.message, request.top_k)
+        sources = retrieval_result["sources"]
+        
+        # Generate answer based on retrieved context
+        answer = rag_system.generate_answer(request.message, sources)
+        
+        # Calculate response time
+        response_time = time.time() - start_time
+        
+        return {
+            "answer": answer,
+            "sources": sources,
+            "query_id": query_id,
+            "response_time": response_time
+        }
+    except Exception as e:
+        logger.error(f"Error in chat endpoint: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/api/feedback", status_code=201)
+async def feedback_endpoint(request: FeedbackRequest):
+    """
+    Collect user feedback about the quality of responses.
+    In a real implementation, this would store feedback in a database.
+    """
+    logger.info(f"Received feedback for query {request.query_id}: rating={request.rating}")
+    # In a production system, you would store this feedback in a database
+    return {"status": "Feedback received", "query_id": request.query_id}
+
+@app.get("/health")
+async def health_check():
+    """
+    Health check endpoint for monitoring and load balancers.
+    """
+    return {"status": "healthy", "timestamp": time.time()}
+@app.get("/")
+async def root():
+    return {
+        "message": "Welcome to Recipe Assistant API",
+        "endpoints": {
+            "/api/chat": "POST - Submit recipe questions",
+            "/api/feedback": "POST - Submit feedback",
+            "/health": "GET - Service health check",
+            "/docs": "API documentation"
+        }
+    }
+
+
+if __name__ == "__main__":
+    import uvicorn
+    port = int(os.getenv("PORT", "8000"))
+    log_level = os.getenv("LOG_LEVEL", "info")
+    
+    logger.info(f"Starting API server on port {port}")
+    uvicorn.run(
+        "server:app", 
+        host="0.0.0.0", 
+        port=port, 
+        log_level=log_level,
+        reload=os.getenv("ENVIRONMENT", "production") == "development"
+    )

fronted/.gitignore

@@ -0,0 +1,24 @@
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+pnpm-debug.log*
+lerna-debug.log*
+
+node_modules
+dist
+dist-ssr
+*.local
+
+# Editor directories and files
+.vscode/*
+!.vscode/extensions.json
+.idea
+.DS_Store
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.sw?

fronted/README.md

@@ -0,0 +1,8 @@
+# React + Vite
+
+This template provides a minimal setup to get React working in Vite with HMR and some ESLint rules.
+
+Currently, two official plugins are available:
+
+- [@vitejs/plugin-react](https://github.com/vitejs/vite-plugin-react/blob/main/packages/plugin-react/README.md) uses [Babel](https://babeljs.io/) for Fast Refresh
+- [@vitejs/plugin-react-swc](https://github.com/vitejs/vite-plugin-react-swc) uses [SWC](https://swc.rs/) for Fast Refresh

fronted/eslint.config.js

@@ -0,0 +1,38 @@
+import js from '@eslint/js'
+import globals from 'globals'
+import react from 'eslint-plugin-react'
+import reactHooks from 'eslint-plugin-react-hooks'
+import reactRefresh from 'eslint-plugin-react-refresh'
+
+export default [
+  { ignores: ['dist'] },
+  {
+    files: ['**/*.{js,jsx}'],
+    languageOptions: {
+      ecmaVersion: 2020,
+      globals: globals.browser,
+      parserOptions: {
+        ecmaVersion: 'latest',
+        ecmaFeatures: { jsx: true },
+        sourceType: 'module',
+      },
+    },
+    settings: { react: { version: '18.3' } },
+    plugins: {
+      react,
+      'react-hooks': reactHooks,
+      'react-refresh': reactRefresh,
+    },
+    rules: {
+      ...js.configs.recommended.rules,
+      ...react.configs.recommended.rules,
+      ...react.configs['jsx-runtime'].rules,
+      ...reactHooks.configs.recommended.rules,
+      'react/jsx-no-target-blank': 'off',
+      'react-refresh/only-export-components': [
+        'warn',
+        { allowConstantExport: true },
+      ],
+    },
+  },
+]

fronted/index.html

@@ -0,0 +1,13 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <link rel="icon" type="image/svg+xml" href="/vite.svg" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>Vite + React</title>
+  </head>
+  <body>
+    <div id="root"></div>
+    <script type="module" src="/src/main.jsx"></script>
+  </body>
+</html>

fronted/package.json

@@ -0,0 +1,32 @@
+{
+  "name": "fronted",
+  "private": true,
+  "version": "0.0.0",
+  "type": "module",
+  "scripts": {
+    "dev": "vite",
+    "build": "vite build",
+    "lint": "eslint .",
+    "preview": "vite preview"
+  },
+  "dependencies": {
+    "@emotion/react": "^11.14.0",
+    "@emotion/styled": "^11.14.0",
+    "axios": "^1.7.9",
+    "react": "^19.0.0",
+    "react-dom": "^19.0.0",
+    "react-markdown": "^10.0.0"
+  },
+  "devDependencies": {
+    "@eslint/js": "^9.19.0",
+    "@types/react": "^19.0.8",
+    "@types/react-dom": "^19.0.3",
+    "@vitejs/plugin-react": "^4.3.4",
+    "eslint": "^9.19.0",
+    "eslint-plugin-react": "^7.37.4",
+    "eslint-plugin-react-hooks": "^5.0.0",
+    "eslint-plugin-react-refresh": "^0.4.18",
+    "globals": "^15.14.0",
+    "vite": "^6.1.0"
+  }
+}

fronted/src/App.css

@@ -0,0 +1,112 @@
+/* Base styles */
+body {
+  font-family: Arial, sans-serif;
+  background-color: #f0f2f5;
+  margin: 0;
+  padding: 0;
+}
+
+.app {
+  max-width: 800px;
+  margin: 0 auto;
+  padding: 20px;
+}
+
+h1 {
+  text-align: center;
+  color: #333;
+}
+
+/* Chat container */
+.chat-container {
+  background: white;
+  border-radius: 10px;
+  box-shadow: 0 2px 10px rgba(0, 0, 0, 0.1);
+  padding: 20px;
+}
+
+/* Message styles */
+.messages {
+  max-height: 500px;
+  overflow-y: auto;
+  margin-bottom: 20px;
+}
+
+.message {
+  margin-bottom: 15px;
+  display: flex;
+  flex-direction: column;
+}
+
+.message.user {
+  align-items: flex-end;
+}
+
+.message.bot {
+  align-items: flex-start;
+}
+
+.message .content {
+  max-width: 70%;
+  padding: 10px 15px;
+  border-radius: 10px;
+  background-color: #e8e8e8;
+}
+
+.message.user .content {
+  background-color: #dcf8c6;
+}
+
+/* Loading indicator */
+.loading {
+  text-align: center;
+  font-style: italic;
+  color: #666;
+}
+
+/* Input and button */
+form {
+  display: flex;
+  gap: 10px;
+}
+
+input {
+  flex: 1;
+  padding: 10px;
+  border: 1px solid #ddd;
+  border-radius: 20px;
+  outline: none;
+}
+
+button {
+  padding: 10px 20px;
+  background-color: #075e54;
+  color: white;
+  border: none;
+  border-radius: 20px;
+  cursor: pointer;
+}
+
+button:disabled {
+  background-color: #ccc;
+  cursor: not-allowed;
+}
+
+/* Reference recipes */
+.sources {
+  margin-top: 10px;
+  font-size: 0.9em;
+  color: #666;
+}
+
+.sources h4 {
+  margin: 0 0 5px 0;
+  font-size: 1em;
+}
+
+.source {
+  background: #f9f9f9;
+  padding: 5px 10px;
+  border-radius: 5px;
+  margin-bottom: 5px;
+}

fronted/src/App.jsx

@@ -0,0 +1,14 @@
+import React from 'react';
+import Chat from './components/Chat';  // Ensure the path is correct
+import './app.css';  // Ensure the component styles are imported
+
+function App() {
+  return (
+    <div className="app">
+      <h1>Recipe Assistant</h1>
+      <Chat />
+    </div>
+  );
+}
+
+export default App;

fronted/src/components/Chat.jsx

@@ -0,0 +1,77 @@
+import React, { useState } from 'react';
+import ReactMarkdown from 'react-markdown';
+import axios from 'axios';
+
+const Chat = () => {
+  const [messages, setMessages] = useState([]);
+  const [input, setInput] = useState('');
+  const [loading, setLoading] = useState(false);
+
+  const handleSubmit = async (e) => {
+    e.preventDefault();
+    if (!input.trim()) return;
+
+    setLoading(true);
+    try {
+      // Add user message
+      setMessages(prev => [...prev, { role: 'user', content: input }]);
+      
+      // Get AI response
+      const response = await axios.post('http://localhost:8000/api/chat', {
+        message: input
+      });
+
+      // Add AI response
+      setMessages(prev => [
+        ...prev, 
+        { 
+          role: 'bot', 
+          content: response.data.answer,
+          sources: response.data.sources
+        }
+      ]);
+    } catch (error) {
+      console.error('Error:', error);
+    }
+    setLoading(false);
+    setInput('');
+  };
+
+  return (
+    <div className="chat-container">
+      <div className="messages">
+        {messages.map((msg, i) => (
+          <div key={i} className={`message ${msg.role}`}>
+            <div className="content">
+              <ReactMarkdown>{msg.content}</ReactMarkdown>
+              {msg.sources && (
+                <div className="sources">
+                  <h4>Reference Recipes:</h4>
+                  {msg.sources.map((source, idx) => (
+                    <div key={idx} className="source">
+                      <p>{source.substring(0, 150)}...</p>
+                    </div>
+                  ))}
+                </div>
+              )}
+            </div>
+          </div>
+        ))}
+        {loading && <div className="loading">Thinking...</div>}
+      </div>
+      
+      <form onSubmit={handleSubmit}>
+        <input
+          value={input}
+          onChange={(e) => setInput(e.target.value)}
+          placeholder="Enter your recipe question..."
+        />
+        <button type="submit" disabled={loading}>
+          {loading ? 'Sending...' : 'Send'}
+        </button>
+      </form>
+    </div>
+  );
+};
+
+export default Chat;

fronted/src/index.css

@@ -0,0 +1,15 @@
+/* Global reset */
+* {
+  margin: 0;
+  padding: 0;
+  box-sizing: border-box;
+}
+
+/* Root element styles */
+#root {
+  min-height: 100vh;
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  justify-content: center;
+}

fronted/src/main.jsx

@@ -0,0 +1,11 @@
+import React from 'react';
+import ReactDOM from 'react-dom/client';
+import App from './App';  // Ensure the path is correct
+import './index.css';  // Ensure the global styles are imported
+
+const root = ReactDOM.createRoot(document.getElementById('root'));
+root.render(
+  <React.StrictMode>
+    <App />
+  </React.StrictMode>
+);

fronted/vite.config.js

@@ -0,0 +1,7 @@
+import { defineConfig } from 'vite'
+import react from '@vitejs/plugin-react'
+
+// https://vite.dev/config/
+export default defineConfig({
+  plugins: [react()],
+})

installed.txt

@@ -0,0 +1,259 @@
+absl-py @ file:///home/conda/feedstock_root/build_artifacts/absl-py_1705494584803/work
+accelerate==1.3.0
+aiofiles @ file:///home/conda/feedstock_root/build_artifacts/aiofiles_1698945915105/work
+aiohttp @ file:///Users/runner/miniforge3/conda-bld/aiohttp_1710511610826/work
+aiosignal @ file:///home/conda/feedstock_root/build_artifacts/aiosignal_1667935791922/work
+altair @ file:///home/conda/feedstock_root/build_artifacts/altair-split_1711824856061/work
+annotated-types @ file:///home/conda/feedstock_root/build_artifacts/annotated-types_1696634205638/work
+anyio @ file:///home/conda/feedstock_root/build_artifacts/anyio_1688651106312/work/dist
+astor==0.8.1
+astunparse @ file:///home/conda/feedstock_root/build_artifacts/astunparse_1610696312422/work
+async-timeout @ file:///home/conda/feedstock_root/build_artifacts/async-timeout_1691763562544/work
+attrs @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_224434dqzl/croot/attrs_1695717839274/work
+blinker @ file:///home/conda/feedstock_root/build_artifacts/blinker_1698890160476/work
+blis @ file:///Users/runner/miniforge3/conda-bld/cython-blis_1696148899313/work
+boto3==1.34.87
+botocore==1.34.87
+branca @ file:///home/conda/feedstock_root/build_artifacts/branca_1714071803448/work
+Brotli @ file:///Users/runner/miniforge3/conda-bld/brotli-split_1695989934239/work
+cached-property @ file:///home/conda/feedstock_root/build_artifacts/cached_property_1615209429212/work
+cachetools @ file:///home/conda/feedstock_root/build_artifacts/cachetools_1708987703938/work
+catalogue @ file:///Users/runner/miniforge3/conda-bld/catalogue_1695626443928/work
+certifi==2023.7.22
+cffi @ file:///private/var/folders/nz/j6p8yfhx1mv_0grj5xl4650h0000gp/T/abs_ab19r4bji3/croot/cffi_1670423206034/work
+charset-normalizer @ file:///home/conda/feedstock_root/build_artifacts/charset-normalizer_1698833585322/work
+chinese-converter==1.1.1
+click @ file:///home/conda/feedstock_root/build_artifacts/click_1692311806742/work
+cloudpathlib @ file:///home/conda/feedstock_root/build_artifacts/cloudpathlib-meta_1697837790453/work
+cloudpickle==3.0.0
+colorama @ file:///home/conda/feedstock_root/build_artifacts/colorama_1666700638685/work
+colorgram.py==1.2.0
+compress-fasttext==0.1.5
+confection @ file:///Users/runner/miniforge3/conda-bld/confection_1701179345946/work
+conll-df==0.0.4
+contourpy==1.1.0
+cryptography @ file:///Users/runner/miniforge3/conda-bld/cryptography-split_1708780317904/work
+ctranslate2==3.24.0
+curated-tokenizers==0.0.8
+curated-transformers==0.1.1
+cycler==0.11.0
+cymem @ file:///Users/runner/miniforge3/conda-bld/cymem_1695443580499/work
+Cython==3.0.9
+dataclasses-json==0.6.4
+datasets @ file:///home/conda/feedstock_root/build_artifacts/datasets_1709395865330/work
+de-core-news-sm @ https://github.com/explosion/spacy-models/releases/download/de_core_news_sm-3.7.0/de_core_news_sm-3.7.0-py3-none-any.whl#sha256=d88c737eb7eb766f730f6a2dcb99dfcdb81623e1e0d89a9c638a2182ac19c52e
+Deprecated==1.2.14
+diffusers @ file:///home/conda/feedstock_root/build_artifacts/diffusers_1736990313447/work
+dill @ file:///home/conda/feedstock_root/build_artifacts/dill_1706434688412/work
+dimsim==0.2.2
+dirtyjson==1.0.8
+distro==1.9.0
+en-core-web-lg @ https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.7.1/en_core_web_lg-3.7.1-py3-none-any.whl#sha256=ab70aeb6172cde82508f7739f35ebc9918a3d07debeed637403c8f794ba3d3dc
+en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl#sha256=86cc141f63942d4b2c5fcee06630fd6f904788d2f0ab005cce45aadb8fb73889
+es-dep-news-trf @ https://github.com/explosion/spacy-models/releases/download/es_dep_news_trf-3.7.2/es_dep_news_trf-3.7.2-py3-none-any.whl#sha256=03117d52d9077a5af65a8163b419fb94569e2048039bdbacd6484b27bfcbd272
+exceptiongroup @ file:///home/conda/feedstock_root/build_artifacts/exceptiongroup_1733208806608/work
+fastapi @ file:///home/conda/feedstock_root/build_artifacts/fastapi_1695951101499/work
+ffmpy @ file:///home/conda/feedstock_root/build_artifacts/ffmpy_1659474992694/work
+filelock==3.12.3
+flatbuffers @ file:///home/conda/feedstock_root/build_artifacts/python-flatbuffers_1711466727397/work
+folium @ file:///home/conda/feedstock_root/build_artifacts/folium_1718605969954/work
+fonttools==4.42.1
+frozenlist==1.4.0
+fsspec @ file:///home/conda/feedstock_root/build_artifacts/fsspec_1707102468451/work
+gast @ file:///home/conda/feedstock_root/build_artifacts/gast_1688368721366/work
+GDAL @ file:///Users/runner/miniforge3/conda-bld/gdal-split_1700094783563/work/build/swig/python
+gensim==4.3.2
+geopandas @ file:///home/conda/feedstock_root/build_artifacts/geopandas_1726897840759/work
+gmpy2 @ file:///Users/runner/miniforge3/conda-bld/gmpy2_1666808753481/work
+google-auth @ file:///home/conda/feedstock_root/build_artifacts/google-auth_1711011113292/work
+google-auth-oauthlib @ file:///home/conda/feedstock_root/build_artifacts/google-auth-oauthlib_1702414855226/work
+google-pasta==0.2.0
+gradio @ file:///home/conda/feedstock_root/build_artifacts/gradio_1722534833126/work
+gradio_client @ file:///home/conda/feedstock_root/build_artifacts/gradio-client_1722483282795/work
+greenlet==3.0.3
+grpcio @ file:///Users/runner/miniforge3/conda-bld/grpc-split_1707750240521/work
+h11 @ file:///home/conda/feedstock_root/build_artifacts/h11_1733327467879/work
+h2 @ file:///home/conda/feedstock_root/build_artifacts/h2_1733298745555/work
+h5py @ file:///Users/runner/miniforge3/conda-bld/h5py_1712765738236/work
+hanziconv==0.3.2
+hfst==3.16.0.1
+hpack @ file:///home/conda/feedstock_root/build_artifacts/hpack_1733299205993/work
+httpcore==1.0.4
+httpx==0.27.0
+huggingface_hub @ file:///home/conda/feedstock_root/build_artifacts/huggingface_hub_1711986612800/work
+hyperframe @ file:///home/conda/feedstock_root/build_artifacts/hyperframe_1733298771451/work
+idna @ file:///private/var/folders/nz/j6p8yfhx1mv_0grj5xl4650h0000gp/T/abs_771olrhiqw/croot/idna_1666125579282/work
+importlib-metadata @ file:///home/conda/feedstock_root/build_artifacts/importlib-metadata_1688754491823/work
+importlib_resources @ file:///home/conda/feedstock_root/build_artifacts/importlib_resources_1736252299705/work
+jieba==0.42.1
+Jinja2 @ file:///private/var/folders/nz/j6p8yfhx1mv_0grj5xl4650h0000gp/T/abs_9fjgzv9ant/croot/jinja2_1666908141308/work
+jmespath==1.0.1
+joblib==1.4.0
+jsonpatch==1.33
+jsonpointer==2.4
+jsonschema @ file:///home/conda/feedstock_root/build_artifacts/jsonschema_1733472696581/work
+jsonschema-specifications @ file:///tmp/tmpk0f344m9/src
+keras @ file:///home/conda/feedstock_root/build_artifacts/keras_1700038168849/work/keras-2.15.0-py3-none-any.whl#sha256=2dcc6d2e30cf9c951064b63c1f4c404b966c59caf09e01f3549138ec8ee0dd1f
+kiwisolver @ file:///Users/runner/miniforge3/conda-bld/kiwisolver_1695379982481/work
+LAC==2.1.2
+langchain==0.1.16
+langchain-community==0.0.33
+langchain-core==0.1.44
+langchain-text-splitters==0.0.1
+langcodes @ file:///home/conda/feedstock_root/build_artifacts/langcodes_1636741340529/work
+langsmith==0.1.48
+lightgbm @ file:///home/conda/feedstock_root/build_artifacts/liblightgbm_1728547591057/work
+llama-index-agent-openai==0.2.2
+llama-index-cli==0.1.12
+llama-index-core==0.10.30
+llama-index-embeddings-openai==0.1.7
+llama-index-indices-managed-llama-cloud==0.1.5
+llama-index-legacy==0.9.48
+llama-index-llms-openai==0.1.15
+llama-index-multi-modal-llms-openai==0.1.5
+llama-index-program-openai==0.1.5
+llama-index-question-gen-openai==0.1.3
+llama-index-readers-file==0.1.19
+llama-index-readers-llama-parse==0.1.4
+llama-parse==0.4.1
+llamaindex-py-client==0.1.18
+lxml @ file:///Users/runner/miniforge3/conda-bld/lxml_1715598488246/work
+mapclassify @ file:///home/conda/feedstock_root/build_artifacts/mapclassify_1723589646909/work
+Markdown==3.5.1
+markdown-it-py @ file:///home/conda/feedstock_root/build_artifacts/markdown-it-py_1686175045316/work
+MarkupSafe @ file:///private/var/folders/nz/j6p8yfhx1mv_0grj5xl4650h0000gp/T/abs_12c133f5-0720-4727-9c18-599a3af825723lzwham3/croots/recipe/markupsafe_1654597866058/work
+marshmallow==3.21.1
+matplotlib @ file:///Users/runner/miniforge3/conda-bld/matplotlib-suite_1712606004214/work
+mdurl @ file:///home/conda/feedstock_root/build_artifacts/mdurl_1639515908913/work
+mistune @ file:///home/conda/feedstock_root/build_artifacts/mistune_1698947099619/work
+ml-dtypes @ file:///Users/runner/miniforge3/conda-bld/ml_dtypes_1695281015782/work
+mpmath @ file:///home/conda/feedstock_root/build_artifacts/mpmath_1678228039184/work
+multidict==6.0.4
+multiprocess @ file:///Users/runner/miniforge3/conda-bld/multiprocess_1706514928763/work
+munkres==1.1.4
+murmurhash @ file:///Users/runner/miniforge3/conda-bld/murmurhash_1695449903748/work
+mypy-extensions==1.0.0
+networkx==3.1
+nltk==3.8.1
+numpy @ file:///Users/runner/miniforge3/conda-bld/numpy_1707225416355/work/dist/numpy-1.26.4-cp310-cp310-macosx_11_0_arm64.whl#sha256=14c628943f67e9c10d22faa9c1cdcbf69c3192e88f2f597d03b77a252e589567
+oauthlib @ file:///home/conda/feedstock_root/build_artifacts/oauthlib_1666056362788/work
+openai==1.22.0
+opt-einsum @ file:///home/conda/feedstock_root/build_artifacts/opt_einsum_1696448916724/work
+orjson==3.10.1
+packaging==23.2
+paddle-bfloat==0.1.7
+paddlepaddle==2.4.0
+pandas==2.1.0
+pathy @ file:///private/var/folders/nz/j6p8yfhx1mv_0grj5xl4650h0000gp/T/abs_24y4elqnou/croot/pathy_1674585921280/work
+Pillow==10.0.0
+pinyin-jyutping-sentence==1.3
+pkgutil_resolve_name @ file:///home/conda/feedstock_root/build_artifacts/pkgutil-resolve-name_1733344503739/work
+pkuseg==0.0.25
+plotly==5.24.1
+portalocker==2.10.1
+preshed @ file:///Users/runner/miniforge3/conda-bld/preshed_1695645021215/work
+protobuf==3.20.0
+psutil==5.9.8
+pyarrow==15.0.0
+pyarrow-hotfix @ file:///home/conda/feedstock_root/build_artifacts/pyarrow-hotfix_1700596371886/work
+pyasn1 @ file:///home/conda/feedstock_root/build_artifacts/pyasn1_1713209357222/work
+pyasn1_modules @ file:///home/conda/feedstock_root/build_artifacts/pyasn1-modules_1713209683338/work
+pyconll==3.2.0
+pycparser @ file:///tmp/build/80754af9/pycparser_1636541352034/work
+pydantic @ file:///home/conda/feedstock_root/build_artifacts/pydantic_1700669197061/work
+pydantic_core @ file:///Users/runner/miniforge3/conda-bld/pydantic-core_1700664087163/work
+pydub @ file:///home/conda/feedstock_root/build_artifacts/pydub_1734638032476/work
+Pygments @ file:///home/conda/feedstock_root/build_artifacts/pygments_1691408637400/work
+PyJWT @ file:///home/conda/feedstock_root/build_artifacts/pyjwt_1706895065046/work
+pyogrio @ file:///Users/runner/miniforge3/conda-bld/pyogrio_1700083253656/work
+pyonmttok==1.37.1
+pyOpenSSL @ file:///home/conda/feedstock_root/build_artifacts/pyopenssl_1706660063483/work
+pyparsing==3.1.1
+pypdf==4.2.0
+pypinyin==0.52.0
+pyproj @ file:///Users/runner/miniforge3/conda-bld/pyproj_1699268117362/work
+pyrsistent @ file:///Users/ktietz/ci_310/pyrsistent_1643962172005/work
+PySocks @ file:///home/conda/feedstock_root/build_artifacts/pysocks_1661604839144/work
+python-dateutil @ file:///home/conda/feedstock_root/build_artifacts/python-dateutil_1626286286081/work
+python-dotenv==1.0.1
+python-multipart @ file:///home/conda/feedstock_root/build_artifacts/python-multipart_1734420773152/work
+pytz==2023.3.post1
+pyu2f @ file:///home/conda/feedstock_root/build_artifacts/pyu2f_1604248910016/work
+PyYAML @ file:///Users/runner/miniforge3/conda-bld/pyyaml_1695373498369/work
+pyzmq==26.0.0
+referencing @ file:///home/conda/feedstock_root/build_artifacts/referencing_1737120398748/work
+regex==2023.10.3
+requests @ file:///home/conda/feedstock_root/build_artifacts/requests_1684774241324/work
+requests-oauthlib @ file:///home/conda/feedstock_root/build_artifacts/requests-oauthlib_1711290127547/work
+rich @ file:///home/conda/feedstock_root/build_artifacts/rich-split_1700160075651/work/dist
+rouge==1.0.1
+rpds-py @ file:///Users/runner/miniforge3/conda-bld/rpds-py_1733366666571/work
+rsa @ file:///home/conda/feedstock_root/build_artifacts/rsa_1658328885051/work
+ruff @ file:///Users/runner/miniforge3/conda-bld/ruff_1737378870230/work
+s3transfer==0.10.1
+sacrebleu==2.4.2
+sacremoses==0.1.1
+safetensors @ file:///Users/runner/miniforge3/conda-bld/safetensors_1713253511904/work
+scikit-learn==1.4.2
+SciPy @ file:///Users/runner/miniforge3/conda-bld/scipy-split_1700812700233/work/dist/scipy-1.11.4-cp310-cp310-macosx_11_0_arm64.whl#sha256=375d32c2e30658f658c57cabef9cbbe6df2df8a14f5cb858d49fc66e910be7a5
+seaborn==0.12.2
+semantic-version @ file:///home/conda/feedstock_root/build_artifacts/semantic_version_1653579368137/work
+sentencepiece==0.2.0
+shapely @ file:///Users/runner/miniforge3/conda-bld/shapely_1697191406032/work
+shellingham @ file:///home/conda/feedstock_root/build_artifacts/shellingham_1698144360966/work
+six @ file:///home/conda/feedstock_root/build_artifacts/six_1620240208055/work
+smart-open @ file:///home/conda/feedstock_root/build_artifacts/smart_open_split_1694066705667/work/dist
+sniffio @ file:///home/conda/feedstock_root/build_artifacts/sniffio_1733244044561/work
+spaces==0.32.0
+spacy @ file:///Users/runner/miniforge3/conda-bld/spacy_1699195026989/work
+spacy-conll==4.0.1
+spacy-curated-transformers==0.2.1
+spacy-legacy @ file:///home/conda/feedstock_root/build_artifacts/spacy-legacy_1674550301837/work
+spacy-loggers @ file:///home/conda/feedstock_root/build_artifacts/spacy-loggers_1694527114282/work
+spacy-pkuseg==0.0.33
+SQLAlchemy==2.0.29
+srsly @ file:///Users/runner/miniforge3/conda-bld/srsly_1695654012378/work
+starlette @ file:///home/conda/feedstock_root/build_artifacts/starlette-recipe_1684245096404/work
+striprtf==0.0.26
+sympy==1.13.1
+tabulate==0.9.0
+tenacity==8.2.3
+tensorboard @ file:///home/conda/feedstock_root/build_artifacts/tensorboard_1707486779203/work/tensorboard-2.15.2-py3-none-any.whl#sha256=a6f6443728064d962caea6d34653e220e34ef8df764cb06a8212c17e1a8f0622
+tensorboard-data-server @ file:///Users/runner/miniforge3/conda-bld/tensorboard-data-server_1695425507462/work/tensorboard_data_server-0.7.0-py3-none-any.whl#sha256=d64d6779d77d7ddd0e3ca6179f5719a9609921e96c89c5b6e126fbe37cb6a9cb
+tensordict==0.3.2
+tensorflow @ file:///Users/uwe/Development/conda-forge/tensorflow-feedstock/tensorflow-feedstock-osx_arm64_numpy1.22python3.10.____cpython/miniforge3/conda-bld/tensorflow-split_1705684890772/work/tensorflow_pkg/tensorflow-2.15.0-cp310-cp310-macosx_11_0_arm64.whl#sha256=29950c12963854214b40eb023bea9ad684abeb97c26d33c4184b9c4536f9c4a5
+tensorflow-addons==0.21.0
+tensorflow_estimator @ file:///Users/uwe/Development/conda-forge/tensorflow-feedstock/tensorflow-feedstock-osx_arm64_numpy1.22python3.10.____cpython/miniforge3/conda-bld/tensorflow-split_1705684890772/work/tensorflow-estimator/wheel_dir/tensorflow_estimator-2.15.0-py2.py3-none-any.whl#sha256=d475182953e6133aade7c6c9271d7beffe86758164ca1d39d9758018c7c82747
+termcolor @ file:///home/conda/feedstock_root/build_artifacts/termcolor_1704357939450/work
+thinc @ file:///Users/runner/miniforge3/conda-bld/thinc_1695623306101/work
+threadpoolctl==3.4.0
+thulac==0.2.2
+tiktoken==0.6.0
+tokenizers==0.19.1
+tomlkit @ file:///home/conda/feedstock_root/build_artifacts/tomlkit_1690458286251/work
+toolz @ file:///home/conda/feedstock_root/build_artifacts/toolz_1733736030883/work
+torch==2.6.0
+torchaudio==2.6.0
+torcheval==0.0.7
+torchvision==0.17.2
+tornado @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_28d93aezp2/croot/tornado_1690848278715/work
+tqdm @ file:///home/conda/feedstock_root/build_artifacts/tqdm_1691671248568/work
+transformers==4.40.0
+typeguard==2.13.3
+typer==0.15.1
+typing-inspect==0.9.0
+typing_extensions @ file:///home/conda/feedstock_root/build_artifacts/typing_extensions_1712329955671/work
+tzdata==2023.3
+unicodedata2 @ file:///Users/runner/miniforge3/conda-bld/unicodedata2_1695848003431/work
+urllib3==2.0.4
+uvicorn @ file:///home/conda/feedstock_root/build_artifacts/uvicorn_1734292939144/work
+wasabi @ file:///Users/runner/miniforge3/conda-bld/wasabi_1686131568298/work
+weasel @ file:///home/conda/feedstock_root/build_artifacts/weasel_1699295455892/work
+websockets @ file:///Users/runner/miniforge3/conda-bld/websockets_1695410052706/work
+Werkzeug @ file:///home/conda/feedstock_root/build_artifacts/werkzeug_1712099422348/work
+wikipedia==1.4.0
+wrapt @ file:///Users/runner/miniforge3/conda-bld/wrapt_1666806247108/work
+xxhash @ file:///Users/runner/miniforge3/conda-bld/python-xxhash_1696486346782/work
+xyzservices @ file:///home/conda/feedstock_root/build_artifacts/xyzservices_1725366347586/work
+yarl==1.9.2
+zipp @ file:///home/conda/feedstock_root/build_artifacts/zipp_1689374466814/work

readme.md

@@ -0,0 +1,59 @@
+# Recipe RAG System
+
+**Author:** [Your Name]  
+**Date:** February 2025
+
+## Project Overview
+
+A production-ready Retrieval-Augmented Generation (RAG) system specialized for recipe queries. This system combines vector search with language model generation to provide contextually relevant recipe information based on user queries.
+
+### Key Features
+
+- **Efficient Information Retrieval**: Semantic search using BGE embeddings to find the most relevant recipes
+- **Contextual Response Generation**: LLM-powered responses that incorporate retrieved recipe information
+- **Scalable API Architecture**: FastAPI-based RESTful API with proper error handling and documentation
+- **Fully Containerized**: Docker and Docker Compose setup for easy deployment
+- **Comprehensive Testing**: Unit and integration tests covering core functionalities
+- **Monitoring Setup**: Prometheus and Grafana integration (optional)
+
+## Architecture
+
+The system consists of two main components:
+
+1. **Recipe RAG Core**: Handles document indexing, retrieval, and response generation
+2. **API Server**: Exposes the RAG functionality through REST endpoints
+
+## Technology Stack
+
+- **Vector Search**: LlamaIndex with HuggingFace embeddings (BGE model)
+- **Language Model**: Microsoft Phi-3-mini-4k-instruct
+- **API Framework**: FastAPI
+- **Dataset**: HuggingFace Recipe NLG Lite
+- **Containerization**: Docker & Docker Compose
+- **Testing**: pytest & unittest
+- **Monitoring**: Prometheus & Grafana (optional)
+
+## Skills Demonstrated
+
+- **Natural Language Processing**: Implementation of a RAG system using modern techniques
+- **API Development**: RESTful API design with proper validation and error handling
+- **Software Engineering**: Clean code architecture with appropriate abstractions
+- **MLOps Practices**: Containerization, testing, and monitoring setup
+- **Python Development**: Type hints, logging, configuration management
+
+## Deployment
+
+The system can be deployed with a single command:
+
+```bash
+docker-compose up -d
+```
+
+This will start the API server and (optionally) the monitoring stack.
+
+## Future Improvements
+
+- Implement caching layer for frequently asked questions
+- Add a vector database for improved scalability
+- Implement a feedback loop for continuous improvement
+- Develop a user-friendly front-end interface