{"product_id":"154449","title":"Developing a Practical LLM App Using OpenAI's Google Gemini Upstage Solar API ","description":"\u003ccenter\u003e\u003cdiv style=\"text-align:center\"\u003e\u003cimg src=\"https:\/\/tmgdisk01.cafe24.com\/images\/vs\/4172\/sv\/3jYDPL2Q1F3Qki4iIO14KV8IQXwA9Y.png?v=1765080163\" style=\"max-width:100%;max-height:10px\"\u003e\u003c\/div\u003e\u003c\/center\u003e\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\u003ccenter\u003e\n\n\u003cdiv style=\"width:95%\"\u003e\n\n \u003cdiv style=\"text-align:center;font-size:30px;font-weight:bolder;line-height:1.6em\"\u003eDeveloping a Practical LLM App Using OpenAI, Google Gemini, and Upstage Solar APIs \u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"border-bottom:1px;border-bottom-style:dotted;border-color:;padding-bottom:20px\"\u003e\u003ccenter\u003e\u003ctable align=\"center\" width=\"100%\"\u003e\u003ctbody style=\"border:0px\"\u003e\n\n\u003ctr\u003e\u003ctd align=\"center\" style=\"line-height:1.2em;text-align:center;font-size:18px;color:black;font-weight:bold;padding-bottom:20px;\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\n\n\u003ctr\u003e\u003ctd style=\"text-align:center\"\u003e\u003cimg src=\"https:\/\/image.yes24.com\/goods\/141128415\/XL\" style=\"max-width:100%;height:auto\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\n\n\n\u003c\/tbody\u003e\u003c\/table\u003e\u003c\/center\u003e\u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"width:95%;{split_style6}padding-top:20px;padding-bottom:20px\"\u003e\n\n\u003cdiv style=\"text-align:left;font-size:16px;font-weight:bold;padding-bottom:20px\"\u003e Description \u003c\/div\u003e\n\n\u003cdiv style=\"text-align:left;word-break:break-all;font-size:14px;line-height:1.6em;\"\u003e\n\n\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eBook Introduction\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e\u003cdiv\u003e \u003cb\u003eLearn how to develop optimal LLM API applications using generative AI technology!\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e This book introduces how to develop AI applications using the latest LLM APIs, including OpenAI, Google Gemini, and Upstage Solar. It guides you step-by-step, from API integration and prompt engineering to RAG implementation, application development using LangChain and Flowise, and practical web\/desktop app development using Streamlit and Flet.\u003cbr\u003e If you have basic programming knowledge, you can grow into an LLM professional developer through this book.\u003cbr\u003e Instead of complex theories, you'll learn how to make the most of your LLM with practical examples.\u003cbr\u003e\n\u003c\/div\u003e\u003c\/div\u003e\n\u003cdiv\u003e\u003cul\u003e\u003cli\u003e You can preview some of the book's contents.\u003cbr\u003e \u003cspan\u003ePreview\u003c\/span\u003e\n\n\u003c\/li\u003e\u003c\/ul\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eindex\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e  \u003cdiv\u003e\n\u003cb\u003e▣ Chapter 1: LLM API Programming Overview\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 1.1 Learning LLM Basics in the Playground\u003cbr\u003e 1.2 How to write better instructions\u003cbr\u003e 1.3 API of OpenAI, the LLM powerhouse\u003cbr\u003e 1.4 Digging into the Google Gemini API\u003cbr\u003e 1.5 Korea's Leading LLM, Upstage Solar API\u003cbr\u003e 1.6 From the basics of the Langchain to building RAG\u003cbr\u003e 1.7 Developing LLM Web Applications with Streamlet\u003cbr\u003e 1.8 Multi-platform LLM Application Development\u003cbr\u003e 1.9 Summary\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 2: Learning LLM Basics in the OpenAI Playground\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 2.1 OpenAI Signup and Payment Settings\u003cbr\u003e __Join OpenAI\u003cbr\u003e __Register a payment card\u003cbr\u003e __Purchase credits\u003cbr\u003e 2.2 Exploring the OpenAI Playground\u003cbr\u003e Enter the __playground\u003cbr\u003e __Completions\u003cbr\u003e __Chat mode\u003cbr\u003e __TTS\u003cbr\u003e 2.3 Comparison of Chat Mode and Complete Mode\u003cbr\u003e __Single-turn and multi-turn dialogue\u003cbr\u003e __Text Summary\u003cbr\u003e __Code Completion\u003cbr\u003e 2.4 Learn by looking at various prompt examples\u003cbr\u003e 2.5 tokens\u003cbr\u003e __Token concept and number of tokens\u003cbr\u003e __Checking OpenAI's tokenization\u003cbr\u003e 2.6 Adjusting parameters\u003cbr\u003e __Model\u003cbr\u003e __Temperature\u003cbr\u003e __Maximum Tokens\u003cbr\u003e __Stop sequences\u003cbr\u003e __Top P \u003cbr\u003e__Frequency penalty and Presence penalty\u003cbr\u003e 2.7 Simple comparison of model performance\u003cbr\u003e __Text Summary\u003cbr\u003e __Q\u0026amp;A\u003cbr\u003e __Physics Problem Solving\u003cbr\u003e __College Scholastic Ability Test Korean Language Score\u003cbr\u003e 2.8 Creating an Assistant that Leverages Tools Without Coding\u003cbr\u003e __Creating Your First Assistant - A Counseling Bot\u003cbr\u003e __Creating an Assistant to Create PPT Documents with a Code Interpreter\u003cbr\u003e Creating an assistant that answers questions by referencing \"knowledge\" from PDF files and other sources\u003cbr\u003e 2.9 Realtime\u003cbr\u003e __Experience real-time conversation\u003cbr\u003e __The potential of Realtime API\u003cbr\u003e 2.10 Generation Frequency Limit\u003cbr\u003e 2.11 Summary\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 3: Writing Better Prompts\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 3.1 Give specific instructions\u003cbr\u003e 3.2 Finding the correct expression\u003cbr\u003e __An example of how behavior changes depending on word selection\u003cbr\u003e __Example of specifying the tone of a sentence\u003cbr\u003e 3.3 Positive rather than negative sentences\u003cbr\u003e 3.4 Answering the question together\u003cbr\u003e 3.5 Zero-shot, one-shot, few-shot, many-shot learning\u003cbr\u003e __Zero Shot\u003cbr\u003e __One Shot\u003cbr\u003e __Pewshot\u003cbr\u003e __Manyshot\u003cbr\u003e 3.6 Dividing the execution steps\u003cbr\u003e __Simple query\u003cbr\u003e __prompt chain \u003cbr\u003e3.7 CoT: Asking people to think things through\u003cbr\u003e __Example: Finding the price of 12 apples\u003cbr\u003e __Example: Representing a number as the product of two numbers\u003cbr\u003e 3.8 Specifying the output format\u003cbr\u003e __Short answer subjective test questions with multiple answers\u003cbr\u003e __Preferred format by LLM\u003cbr\u003e __How to get structured output\u003cbr\u003e 3.9 Generating Programming SQL Statements with LLM\u003cbr\u003e __SQL Overview\u003cbr\u003e Natural language query transformation using __LLM\u003cbr\u003e __Security and Performance Risks and Solutions\u003cbr\u003e __Use Cases\u003cbr\u003e 3.10 Improving Object Recognition Accuracy in Multimodal Models\u003cbr\u003e 3.11 ReAct\u003cbr\u003e __What is ReAct?\u003cbr\u003e __How ReAct Works\u003cbr\u003e __Benefits of ReAct\u003cbr\u003e Limitations of __ReAct\u003cbr\u003e __How to write a ReAct prompt\u003cbr\u003e __Additional information\u003cbr\u003e 3.12 Augmented Search Creation\u003cbr\u003e What is __RAG?\u003cbr\u003e __RAG's Advantages\u003cbr\u003e __Disadvantages and Limitations of RAG\u003cbr\u003e __RAG Problem Solution\u003cbr\u003e __RAG vs.\u003cbr\u003e Big context\u003cbr\u003e __organize\u003cbr\u003e 3.13 Threats and Security of Prompt Engineering\u003cbr\u003e __Example of a threat\u003cbr\u003e __Best Practices\u003cbr\u003e 3.14 Summary\u003cbr\u003e 3.15 Further Reading\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 4: OpenAI API Programming\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 4.1 Obtaining an OpenAI API Key\u003cbr\u003e 4.2 Keep your API key safe \u003cbr\u003e__Registering an API key in Google Colab's secrets\u003cbr\u003e __Registering API keys in computer environment variables\u003cbr\u003e 4.3 Trying the OpenAI API\u003cbr\u003e 4.4 Building a Conversation History\u003cbr\u003e 4.5 Structuring the Output of the OpenAI API\u003cbr\u003e __Output Structuring Overview\u003cbr\u003e __Comparing JSON Mode and Structured Outputs\u003cbr\u003e __Practice structuring output using Pydantic\u003cbr\u003e __Practice structuring output using JSON schema\u003cbr\u003e 4.6 Embedding using the OpenAI API\u003cbr\u003e __What is embedding?\u003cbr\u003e __Generating embeddings with the OpenAI API\u003cbr\u003e __Cosine similarity\u003cbr\u003e __Find words\/sentences with similar meanings\u003cbr\u003e 4.7 Image Understanding Using Multimodal Models\u003cbr\u003e __Describe an image on the web\u003cbr\u003e __Describe local images\u003cbr\u003e __Understand images containing text\u003cbr\u003e 4.8 Image Creation\u003cbr\u003e __Basic example of image creation\u003cbr\u003e __Create multiple images\u003cbr\u003e 4.9 Speech Synthesis\u003cbr\u003e 4.10 Voice Dictation with Whisper\u003cbr\u003e __Select and install packages\u003cbr\u003e __Dictation function definition\u003cbr\u003e __Transcribe audio files\u003cbr\u003e __Create YouTube video subtitles \u003cbr\u003e__Explain context and create subtitles with prompts\u003cbr\u003e __Create a transcript\u003cbr\u003e 4.11 Batch Processing Using the Batch API\u003cbr\u003e __Sentiment Analysis and Naver Movie Review Dataset\u003cbr\u003e __Different Approaches to Sentiment Analysis\u003cbr\u003e __Single Sample Sentiment Analysis Test\u003cbr\u003e __Sentiment Analysis Example Using the Batch API\u003cbr\u003e __Results Analysis and Model Selection Guide\u003cbr\u003e __Precautions when using the Batch API\u003cbr\u003e 4.12 Check for harmful text\u003cbr\u003e __Categories of Moderation\u003cbr\u003e __Moderation Practice\u003cbr\u003e __Limitations of Korean Moderation\u003cbr\u003e 4.13 Assistant API\u003cbr\u003e __Key components of the assistant\u003cbr\u003e __Simple Assistant 'Easy Word Recommendation Bot v1'\u003cbr\u003e __Function call function of Assistant API\u003cbr\u003e 'Easy Word Recommendation Bot v2' that utilizes the __ function\u003cbr\u003e __Build an assistant that writes term descriptions using the Tabili Search API\u003cbr\u003e __Things to consider when using the Assistant API\u003cbr\u003e 4.14 Fine Tuning\u003cbr\u003e __Fine Tuning Overview and Pros and Cons\u003cbr\u003e __Fine Tuning Practice Overview\u003cbr\u003e __Preparing CSV\/TSV data\u003cbr\u003e __Data processing\u003cbr\u003e __Upload data and run fine tuning \u003cbr\u003e__test\u003cbr\u003e 4.15 OpenAI API Fees by Model\u003cbr\u003e __GPT-4o\u003cbr\u003e __GPT-4o mini\u003cbr\u003e __o1 series\u003cbr\u003e __GPT-4 Turbo and GPT-4\u003cbr\u003e __GPT-3.5 Turbo\u003cbr\u003e __Fine Tuning\u003cbr\u003e __Audio Model\u003cbr\u003e __Realtime API\u003cbr\u003e 4.16 Summary\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 5: Google Gemini API\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 5.1 Google Gemini API Overview\u003cbr\u003e 5.2 Gemini API Configuration\u003cbr\u003e __Issue Google Gemini API Key\u003cbr\u003e __Main models and free usage\u003cbr\u003e __Setting Google Gemini AI environment variables and installing the SDK\u003cbr\u003e 5.3 Basic Use of Gemini AI\u003cbr\u003e __Basic Usage 1 - Sending and Receiving Messages with Singleton\u003cbr\u003e __Basic Usage 2 - Sending and Receiving Messages in Multiturn (1)\u003cbr\u003e __Basic Usage 3 - Sending and Receiving Messages in Multiturn (2)\u003cbr\u003e 5.4 Using System Guidelines\u003cbr\u003e __Creating a Persona\u003cbr\u003e __Specify the answer format\u003cbr\u003e 5.5 Gemini AI I\/O Architecture\u003cbr\u003e __Gemini AI Input Data Structure\u003cbr\u003e __Gemini AI Output Data Structure\u003cbr\u003e 5.6 Controlling Gemini AI\u003cbr\u003e __Setting parameters\u003cbr\u003e __Check safety\u003cbr\u003e 5.7 Recognizing YouTube Videos with the Gemini API\u003cbr\u003e __YouTube video recognition pipeline \u003cbr\u003e__Download YouTube videos\u003cbr\u003e __Upload YouTube videos\u003cbr\u003e 5.8 Recognizing Voice Using the File API\u003cbr\u003e __Voice recognition\u003cbr\u003e 5.9 Calling Functions with Gemini\u003cbr\u003e __Function Call Basics\u003cbr\u003e __LMM function call process\u003cbr\u003e __Implementing function calls\u003cbr\u003e __Implementing a smartphone ordering chatbot\u003cbr\u003e __Implementing a two-step function call\u003cbr\u003e 5.10 Improving the Quality of Answers with Internet Search\u003cbr\u003e __Using the grounding function\u003cbr\u003e __Control Internet Search\u003cbr\u003e 5.11 OpenAI Compatibility\u003cbr\u003e __How to call API without SDK\u003cbr\u003e __Why OpenAI Compatibility Is Possible\u003cbr\u003e __OpenAI Compatibility Application Strategy\u003cbr\u003e 5.12 Summary\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 6: Upstage API\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 6.1 Upstage API Overview\u003cbr\u003e __Solar LLM-based API\u003cbr\u003e __API for document processing\u003cbr\u003e 6.2 Experience the Upstage Model\u003cbr\u003e __Upstage Playground\u003cbr\u003e Chat at __Poe.com\u003cbr\u003e Solar Custom Translate, where you can experience the solar translation model\u003cbr\u003e 6.3 Sign up for Upstage and get an API key\u003cbr\u003e 6.4 Implementing Chat with Solar LLM\u003cbr\u003e __Check the example code in the official documentation\u003cbr\u003e __Solar Chat API Practice \u003cbr\u003e6.5 Using the Solr Translation API\u003cbr\u003e __Basic usage of the Solar Translation API\u003cbr\u003e __Input translation examples together\u003cbr\u003e 6.6 Solr Embedding API\u003cbr\u003e __Simple embedding example\u003cbr\u003e __Embedding function definition\u003cbr\u003e __Find similar proverbs\u003cbr\u003e 6.7 Trying Document OCR\u003cbr\u003e 6.8 Crawling images on the web, extracting text, and answering questions\u003cbr\u003e __Prepare API key\u003cbr\u003e __Get image\u003cbr\u003e __Extract text from images\u003cbr\u003e __Q\u0026amp;A\u003cbr\u003e 6.9 Introducing Applications Using the Upstage API\u003cbr\u003e 6.10 Summary\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 7: Langchain and Flowy\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 7.1 Langchain Overview\u003cbr\u003e __RangeChain Framework\u003cbr\u003e __LangChain for Python and JavaScript\u003cbr\u003e __Major changes by Langchain version\u003cbr\u003e __LCEL\u003cbr\u003e Criticism and Improvement of __Rangchain\u003cbr\u003e __Langchain-based low-code\/no-code tools\u003cbr\u003e __Alternative to Langchain\u003cbr\u003e 7.2 Leveraging Langchain without Coding with Flowwise\u003cbr\u003e __Installing Node.js\u003cbr\u003e __Installing and running Flowwise\u003cbr\u003e __Creating a Simple Chatbot\u003cbr\u003e __Various nodes available in Flowwise\u003cbr\u003e __Creating a Product Catalog Chatbot with Flowise \u003cbr\u003e7.3 Components of the Langchain\u003cbr\u003e __Model I\/O\u003cbr\u003e __search\u003cbr\u003e __mixture\u003cbr\u003e __Additional Components\u003cbr\u003e 7.4 Basic Langchain Practice\u003cbr\u003e Simple Q\u0026amp;A and chat using the __Sola API\u003cbr\u003e __Replace language model\u003cbr\u003e __Prompt Template\u003cbr\u003e 7.5 LCEL\u003cbr\u003e __LCEL Overview\u003cbr\u003e __LCEL Practice\u003cbr\u003e 7.6 Agents using the Tabili search tool\u003cbr\u003e 7.7 Building a RAG System Using Gemini, Langchain, and ChromaDB\u003cbr\u003e __Getting ready\u003cbr\u003e __Creating a vector DB\u003cbr\u003e __Creating a question-and-answer program based on a vector DB\u003cbr\u003e 7.8 Web Scraping and Summarization\u003cbr\u003e __Configuring the Jupyter Practice Environment\u003cbr\u003e __Python Practice\u003cbr\u003e 7.9 Creating a Custom Loader\u003cbr\u003e Installing the __package\u003cbr\u003e __Set the API key to an environment variable\u003cbr\u003e __Loader class definition\u003cbr\u003e __Load Wikidocs book contents\u003cbr\u003e __Index creation and query answering\u003cbr\u003e 7.10 Building a Multilingual Review Sentiment Analysis System Using Runnable\u003cbr\u003e Introducing the __Runnable concept\u003cbr\u003e __Practice Code Overview\u003cbr\u003e __Language detection settings\u003cbr\u003e __Preparing to build a multilingual review sentiment analysis system\u003cbr\u003e __Implementation of translation function\u003cbr\u003e __Sentiment analysis and keypoint extraction settings \u003cbr\u003eDefining a __Runnable component\u003cbr\u003e __Configure the entire workflow\u003cbr\u003e __System execution and result analysis\u003cbr\u003e 7.11 Creating a Lyric Generator Web App with Langservo\u003cbr\u003e __Write code\u003cbr\u003e __Running and testing the web server\u003cbr\u003e __Automatic generation of API documentation\u003cbr\u003e __API call\u003cbr\u003e __Practice Ended\u003cbr\u003e 7.12 Langsmith\u003cbr\u003e __Langsmith's main features\u003cbr\u003e __Get an API key\u003cbr\u003e __Code Practice\u003cbr\u003e 7.13 Summary\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 8: Building AI Web Applications with Streamlet\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 8.1 Streamlet Basics\u003cbr\u003e __Creating Your First Streamlet App\u003cbr\u003e __Running and quitting the Streamlet app\u003cbr\u003e __Basic structure of a Streamlet app\u003cbr\u003e __Creating a data converter for fine-tuning\u003cbr\u003e __Build a Streamlet app that calculates BMI and draws a chart\u003cbr\u003e __Storing confidential information safely\u003cbr\u003e 8.2 Creating a Streamlet App to Create Test Questions\u003cbr\u003e 8.3 Creating a Streamlet App to Classify and Visualize Product Reviews\u003cbr\u003e 8.4 Creating a Streamlit Chatbot Using the Gemini API\u003cbr\u003e __Caching and Session State\u003cbr\u003e __Message Container\u003cbr\u003e __Step-by-step implementation of the Gemini chatbot \u003cbr\u003e__Improving the response method\u003cbr\u003e 8.5 Creating a Streamlet App that Describes Images\u003cbr\u003e 8.6 Creating a Streamlet App that Generates Images with DALL·E 3\u003cbr\u003e 8.7 Creating a Streamlet app that extracts subtitles from YouTube videos and generates content\u003cbr\u003e __Preparing for the practice\u003cbr\u003e __Function to get YouTube video title and description\u003cbr\u003e __Function to extract keywords from video descriptions\u003cbr\u003e __Function to download the audio of a video\u003cbr\u003e __Function to extract text from speech\u003cbr\u003e __Content Type\u003cbr\u003e __Create summaries, essays, blogs, and critiques\u003cbr\u003e __Transcript\/Subtitle Translation\u003cbr\u003e __execution\u003cbr\u003e 8.8 Creating a Streamlet App that Extracts and Summarizes Text from Images\u003cbr\u003e 8.9 Creating a Streamlet App to Analyze Receipt Images\u003cbr\u003e Step 1: Upload the receipt image and display it on the screen.\u003cbr\u003e Step 2: Extract receipt information and display it on the screen.\u003cbr\u003e Step 3: Complete by adding automatic expense classification function.\u003cbr\u003e 8.10 Building a Sentence Corrector Using a Fine-Tuned Model\u003cbr\u003e __Sentence Corrector Overview\u003cbr\u003e __AsyncOpenAI Introduction \u003cbr\u003e__Implementing a sentence corrector\u003cbr\u003e __Running and using the app\u003cbr\u003e __Additional examples\u003cbr\u003e 8.11 Building a Chatbot Using Streamlet and Langchain\u003cbr\u003e 8.12 Summary\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 9: Building a Multilingual Chat App Using the Flet Framework and LLM API\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 9.1 Introduction to the Flet Framework\u003cbr\u003e 9.2 Configuring the environment for Flet development\u003cbr\u003e __Activate the virtual environment\u003cbr\u003e __Flet installation\u003cbr\u003e 9.3 Creating Your First Flet App\u003cbr\u003e Create a __Flet project\u003cbr\u003e __Code Description\u003cbr\u003e __Run the Flet app\u003cbr\u003e 9.4 Creating a Basic Chat App\u003cbr\u003e __Understanding the basic structure of a chat app\u003cbr\u003e __Creating a basic Flet chat app\u003cbr\u003e __Enter username when entering\u003cbr\u003e __Login and chat message distinction\u003cbr\u003e __Change how messages are displayed\u003cbr\u003e 9.5 Added and completed multilingual chat translation feature\u003cbr\u003e __Create app\u003cbr\u003e __Code Description\u003cbr\u003e __Run the app\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Appendix A: Comparison of Token Usage by Model\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e A.1 OpenAI model\u003cbr\u003e __GPT-3.5 Turbo, GPT-4 Turbo, GPT-4\u003cbr\u003e __GPT-4o, GPT-4o mini\u003cbr\u003e A.2 Gemini Pro\u003cbr\u003e A.3 Solar\u003cbr\u003e A.4 Comparison\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Appendix B: Using Vertex Geminai on Google Cloud\u003c\/b\u003e\u003cbr\u003e \u003cbr\u003eB.1 Logical Path to Vertex Gemini\u003cbr\u003e B.2 Getting Started with Vertex AI on Google Cloud Platform\u003cbr\u003e __Sign up for Google Cloud Platform\u003cbr\u003e __Create a service account\u003cbr\u003e __Enabling the Vertex AI API\u003cbr\u003e __Vertex Gemini API is working properly\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Appendix C: Using the OpenAI API in .NET\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e C.1 Prepare your OpenAI API key\u003cbr\u003e C.2 Installing Visual Studio\u003cbr\u003e C.3 Creating a New Project\u003cbr\u003e C.4 Installing the OpenAI Package\u003cbr\u003e C.5 Writing Example Code\u003cbr\u003e C.6 Code Execution\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Appendix D: OpenAI Realtime API Practice\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e D.1 Installing Node.js\u003cbr\u003e D.2 Download the example source code\u003cbr\u003e __Method 1: Download and unzip the compressed file\u003cbr\u003e __Second method: Clone the Git repository\u003cbr\u003e D.3 Prepare your OpenAI API key\u003cbr\u003e D.4 Running the Example Code\u003cbr\u003e __Running relay server\u003cbr\u003e __Run real-time console\u003cbr\u003e __Real-time console testing\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Appendix E: Guardrails for LLM Application Stability\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e E.1 The concept and necessity of guardrails\u003cbr\u003e __Types of guardrails\u003cbr\u003e __Difference between cases with and without guardrails \u003cbr\u003eE.2 Getting Started with Guardrails AI\u003cbr\u003e __Sign up and get an API key\u003cbr\u003e __Installation and Basic Setup\u003cbr\u003e __Guardrails Hub\u003cbr\u003e __Detecting phone numbers using RegexMath\u003cbr\u003e __Detecting and masking personally identifiable information using Dectec PII\u003cbr\u003e Validate SQL statements with __Valid SQL\u003cbr\u003e Masking personally identifiable information with a custom detector\u003cbr\u003e E.3 Conclusion\u003cbr\u003e E.4 References\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eDetailed image\u003c\/b\u003e \u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\u003cdiv\u003e\u003cimg src=\"https:\/\/image.yes24.com\/momo\/TopCate5081\/MidCate10\/508099633.jpg\" border=\"0\" alt=\"Detailed Image 1\"\u003e\u003c\/div\u003e\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003ePublisher's Review\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e \u003cb\u003e★ What this book covers ★\u003cbr\u003e\u003cbr\u003e ◎ How to integrate and use LLM API\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e - Introduce the features and usage methods of major LLM APIs such as OpenAI, Google Gemini, and Upstage Solr, and acquire the basic knowledge required to utilize LLM APIs, such as issuing API keys, calling APIs, and processing responses.\u003cbr\u003e\u003cbr\u003e \u003cb\u003e◎ Learn the basics of LLM through the OpenAI Playground\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e - Learn the basics of using LLM, including prompt writing, tokenization, and parameter tuning, in the OpenAI Playground, and compare and analyze the performance of various LLM models.\u003cbr\u003e\u003cbr\u003e \u003cb\u003e◎ Core principles and techniques of prompt engineering\u003c\/b\u003e\u003cbr\u003e \u003cbr\u003e- Introduces the core principles of prompt engineering that maximize the performance of LLM, and learns effective prompt design methods through various prompt writing techniques and practical application cases.\u003cbr\u003e\u003cbr\u003e \u003cb\u003eHow to Use the OpenAI, Google Gemini, and Upstage Solar APIs\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e - Learn in detail the features and usage of each LLM API, and practice how to utilize the LLM API for various tasks such as text generation, image captioning, translation, and chatbots.\u003cbr\u003e\u003cbr\u003e \u003cb\u003e◎ Building a knowledge-based AI system using augmented search generation (RAG).\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e - Introduces the Augmented Search Generation (RAG) technique and practices building an LLM application that leverages external knowledge using RankChain.\u003cbr\u003e\u003cbr\u003e \u003cb\u003e◎ LLM application development using Langchain and Flowwise\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e - Learn the main features and usage of the LangChain framework, and learn how to develop LLM applications without coding using Flowwise.\u003cbr\u003e \u003cbr\u003e\u003cb\u003e◎ Various AI web applications implemented with Streamlet\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e - Introduces how to develop various LLM-based web applications using Streamlet, and learns the skills required for actual web app development, such as data visualization, user interface design, and API integration.\u003cbr\u003e\u003cbr\u003e \u003cb\u003e◎ Real-time multilingual chat app created with Flet\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e - Implement a real-time multilingual chat app using the Flet framework and add an automatic translation function using the OpenAI API to enable real-time communication in a multilingual environment. \u003cbr\u003e\n\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"width:95%;padding-top:20px;padding-bottom:20px\"\u003e\n\n\u003cdiv style=\"text-align:left;font-size:16px;font-weight:bold;padding-bottom:20px\"\u003e GOODS SPECIFICS \u003c\/div\u003e\n\n\u003cdiv style=\"text-align:left;font-size:14px;line-height:1.6em;\"\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003eDate of issue:\u003c\/strong\u003e January 15, 2025\u003c\/div\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003ePage count, weight, size:\u003c\/strong\u003e 632 pages | 175*235*26mm\u003c\/div\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003eISBN13:\u003c\/strong\u003e 9791158395667 \u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\u003ccenter\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cspan\u003e\u003c\/span\u003e\n\n\u003c\/center\u003e\n\n\n\u003c\/center\u003e","brand":"LIBRAIRIE COREENNE","offers":[{"title":"Default Title","offer_id":43893428092970,"sku":"154449","price":44.0,"currency_code":"EUR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0683\/2750\/5962\/files\/009277dbd53e779c6d0192fe353ccc22.jpg?v=1765401565","url":"https:\/\/librairie.coreenne.fr\/en\/products\/154449","provider":"LIBRAIRIE COREENNE","version":"1.0","type":"link"}