Course : Create an AI assistant using your data with RAG
Practical course - 3d
- 21h00 - Ref. ARG
|
Download in PDF format
Share this course by email
 | Building an AI assistant capable of responding based on a corpus of domain-specific documents |
| Implement a RAG architecture that integrates embeddings and vector search |
| Optimizing the Relevance of Responses Through Hybrid Search and Prompt Engineering |
| Define a strategy for the industrialization and evolution of a RAG system |
Intended audience
Developers, engineers, data analysts, technical consultants, and professionals who want to design AI assistants that utilize internal or document-based data.
Prerequisites
Basic knowledge of JavaScript web development or [line break]TypeScript[line break]. No prior knowledge of artificial intelligence is required.
Course schedule
1 Designing a First Document-Based AI Assistant
- Understanding the Principles of Retrieval-Augmented Generation and Its Use Cases
- Implement a dialog interface connected to a language model
- Upload and prepare a corpus of documents that can be used by an AI assistant
- Learn about the mechanisms for data segmentation and context preservation
Hands-on work
Development of an initial assistant capable of providing responses based on a simple document corpus.
2 Structuring Data and Implementing Vector Searches
- Understanding the Concept of Embeddings and Semantic Similarity
- Implement a vector search tailored to a domain-specific corpus
- Adjust search parameters such as chunk size and top-k
- Identify the functional limitations of a basic RAG system
Hands-on work
Improving the quality of search results by adjusting search parameters.
3 Improving the Relevance of Responses with Prompt Engineering
- Understanding the Role of the Prompt in a RAG System
- Structuring an augmented prompt with constraints and contextualization
- Analyze cases of failure and inaccurate or incomplete responses
- Implement strategies to improve the quality of responses
Hands-on work
Optimization of prompts and comparative analysis of the results obtained.
4 Implementing an Effective Hybrid Search
- Understanding the Principles of Lexical Search and the BM25 Engine
- Understanding the Principles of Lexical Search and the BM25 Engine
- Combining vector search and keyword search
- Identify the benefits and limitations of hybrid approaches
- Learn about the principles of iterative RAG to enhance responses
Hands-on work
Implementation of a hybrid search and measurement of improvements in relevance.
5 Using Real-World Data in an AI Wizard
- Integrate business data from real-world and heterogeneous sources
- Learn about the principles of structured data and StructRAG
- Connecting an AI assistant to a simple database
- Identify technical constraints related to business data
Hands-on work
Development of an AI assistant connected to a business dataset.
6 Structuring an Approach to the Industrialization of a RAG
- Identify the limitations of a prototype and the requirements for mass production
- Assess the performance, quality, and safety issues related to the responses
- Define a strategy for the gradual evolution of an AI assistant
- Developing a Roadmap for Improvement and Deployment
Hands-on work
Development of an operational roadmap to scale up a RAG project.
PARTICIPANTS
Developers, engineers, data analysts, technical consultants, and professionals who want to design AI assistants that utilize internal or document-based data.
PREREQUISITES
Basic knowledge of JavaScript web development or [line break]TypeScript[line break]. No prior knowledge of artificial intelligence is required.
TRAINER QUALIFICATIONS
The experts leading the training are specialists in the covered subjects. They have been approved by our instructional teams for both their professional knowledge and their teaching ability, for each course they teach. They have at least five to ten years of experience in their field and hold (or have held) decision-making positions in companies.
ASSESSMENT TERMS
The trainer evaluates each participant’s academic progress throughout the training using multiple choice, scenarios, hands-on work and more.
Participants also complete a placement test before and after the course to measure the skills they’ve developed.
TERMS AND DEADLINES
Registration must be completed 24 hours before the start of the training.
ACCESSIBILITY FOR PEOPLE WITH DISABILITIES
Do you need special accessibility accommodations? Contact Mrs. Fosse, Disability Manager, at psh-accueil@orsys.fr to review your request and its feasibility.
Developers, engineers, data analysts, technical consultants, and professionals who want to design AI assistants that utilize internal or document-based data.
PREREQUISITES
Basic knowledge of JavaScript web development or [line break]TypeScript[line break]. No prior knowledge of artificial intelligence is required.
TRAINER QUALIFICATIONS
The experts leading the training are specialists in the covered subjects. They have been approved by our instructional teams for both their professional knowledge and their teaching ability, for each course they teach. They have at least five to ten years of experience in their field and hold (or have held) decision-making positions in companies.
ASSESSMENT TERMS
The trainer evaluates each participant’s academic progress throughout the training using multiple choice, scenarios, hands-on work and more.
Participants also complete a placement test before and after the course to measure the skills they’ve developed.
TEACHING AIDS AND TECHNICAL RESOURCES
• The main teaching aids and instructional methods used in the training are audiovisual aids, documentation and course material, hands-on application exercises and corrected exercises for practical training courses, case studies and coverage of real cases for training seminars.
• At the end of each course or seminar, ORSYS provides participants with a course evaluation questionnaire that is analysed by our instructional teams.
• A check-in sheet for each half-day of attendance is provided at the end of the training, along with a course completion certificate if the trainee attended the entire session.
• The main teaching aids and instructional methods used in the training are audiovisual aids, documentation and course material, hands-on application exercises and corrected exercises for practical training courses, case studies and coverage of real cases for training seminars.
• At the end of each course or seminar, ORSYS provides participants with a course evaluation questionnaire that is analysed by our instructional teams.
• A check-in sheet for each half-day of attendance is provided at the end of the training, along with a course completion certificate if the trainee attended the entire session.
TERMS AND DEADLINES
Registration must be completed 24 hours before the start of the training.
ACCESSIBILITY FOR PEOPLE WITH DISABILITIES
Do you need special accessibility accommodations? Contact Mrs. Fosse, Disability Manager, at psh-accueil@orsys.fr to review your request and its feasibility.
This programme is an original creation, developed by the teaching teams at ORSYS Formation. Any reproduction, representation, adaptation or use, in whole or in part, without the prior written authorisation of ORSYS, is strictly prohibited. ORSYS reserves the right to take any action necessary to protect its intellectual property rights.
Dates and locations
Select your location or opt for the remote class then choose your date.
Remote class
Dernières places
Date garantie en présentiel ou à distance
Session garantie
This programme is an original creation, developed by the teaching teams at ORSYS Formation. Any reproduction, representation, adaptation or use, in whole or in part, without the prior written authorisation of ORSYS, is strictly prohibited. ORSYS reserves the right to take any action necessary to protect its intellectual property rights.