LangChain in practice – building chatbots, RAG and automation with AI

Training process

Training needs analysis

If you have specific requirements regarding the training programme, we will carry out a training needs analysis for you. This will guide us on which aspects of the programme should receive greater emphasis, so that the training programme meets your specific needs.

What will you gain?

LLM chatbot design - You will build chatbots powered by local and cloud LLMs, configuring conversation memory, context handling, and custom response handlers for practical business scenarios.

End-to-end RAG pipeline - You will learn how to assemble a full RAG pipeline, from source documents through embeddings and a vector store to answer generation with relevance checks and quality control.

Document and media processing - You will master data preparation for PDF, DOCX, HTML, TXT, and multimodal sources, including OCR and video captions, so your AI systems can use clean and structured knowledge.

Vector database selection - You will learn how to choose a local or cloud vector database, build indexes, filter metadata, and update resources so semantic search stays accurate, stable, and efficient.

Better prompts and routing - You will create dynamic prompts, conditional chains, and query routing across models, databases, and knowledge sources, making responses more relevant and useful to users.

AI workflow automation - You will design workflows built with chains, agents, and classifiers that ask follow-up questions, detect user intent, and guide people through the next steps automatically.

Error diagnosis and control - You will learn practical ways to detect empty retrievals, weak answers, and hallucinations, then add fallbacks, validation, and monitoring to improve reliability after launch.

Secure solution deployment - You will be prepared to deploy AI systems with access control, data protection, GDPR awareness, action traceability, and a solid approach to ongoing maintenance and expansion.

Training programme

1. Introduction to LangChain and AI workflow architecture

what LangChain is and what role it plays in the AI ecosystem,
modular architecture: models, chains, agents, tools,
typical applications of LangChain: chatbots, RAG, recommendation systems, task automation.

2. Building chatbots with locally and remotely hosted LLM models

integration with local models (REST API, local libraries, access control),
connection with cloud-based LLMs – API key configuration and handling limits,
implementation of conversational memory and control of conversation context,
creation of custom query handlers and personalization of responses.

3. Understanding the concept of RAG

the difference between the classical LLM approach and RAG,
operation scheme: knowledge retrieval → response generation,
the role of LangChain in building flexible RAG pipelines.

4. Preparation and processing of source documents

handling formats: PDF, DOCX, HTML, TXT,
document segmentation and metadata extraction,
initial content cleaning and chunking strategy.

5. Selection and integration of vector databases

comparison of local and cloud solutions,
creating vector indexes and updating them,
metadata filtering and personalization of search results.

6. Embedding content

comparison of ready-made embedding models,
creating and testing your own embeddings,
integration of embeddings with the RAG pipeline.

7. Extension with a simple knowledge classifier

introduction of the classifier: why and when to use it,
selection of features, labels and the prediction structure,
integration of the classifier in the decision pipeline.

8. Building and testing a complete RAG pipeline

connecting all components: source → embedding → database → response,
testing the quality and relevance of responses,
diagnostics of errors: empty results, inadequate responses, hallucinations.

9. MCP Architecture in LangChain

data flow: user → chain → model,
MCP components: input, processing, generation,
examples of practical applications.

10. Creating and connecting chains

types of chains: simple, sequential, parallel,
handling dynamic parameters and input data,
data transformations and flow conditioning.

11. Designing dynamic and contextual prompts

prompt as a template vs prompt as the result of logic,
handling variables, historical and dependent data,
building adaptive prompts (e.g. „If the user did not provide X…”).

12. Automation of interactions with the user

creating agents asking follow-up questions,
intent recognition and query classification,
handling contextual conversation with memory.

13. Handling multiple data sources and components in one workflow

combining RAG with MCP and additional knowledge sources,
routing queries to different models / databases depending on classification,
managing context switching and information sources.

14. Solving synchronization and conversation memory problems

user session management,
storing and using conversation history,
fallback strategies and recognition of incomplete data.

15. Vectorization and knowledge base management

preparation of data for vectorization: cleaning, segmentation, metadata,
selection of chunking strategy and creation of vector indexes,
storage, updating and versioning of the vector knowledge base,
semantic search and metadata filtering in queries.

16. Processing various types of documents and media

handling structured and unstructured texts,
processing and extraction of data from PDF, office documents, HTML,
working with visual data: OCR, images, video subtitles,
integration of multimodal data sources in one RAG flow.

17. Automation and scaling of AI processes

18. Security, ethics and responsibility in AI systems

secure data storage and access control,
limiting „hallucinations” and validation of the model's responses,
GDPR, user privacy and regulatory compliance,
responsibility for decisions made by the system and auditability of actions.

19. Maintenance, monitoring and development of implemented solutions

registering queries and analyzing conversational logs,
monitoring response quality and user feedback loop,
refactoring and expansion of existing chains and prompting models.

What are the prerequisites for participating in the training?

Programming basics - You should be comfortable reading and editing simple code, running scripts, and understanding variables, functions, and basic data structures used in AI integrations.

API and JSON basics - You should understand how API communication works, be able to read requests and JSON responses, and know what API keys and basic authorization are used for.

Working with data - You should have basic experience with text files and documents and understand that data often needs cleaning, segmentation, and preparation before it is used in an AI system.

LLM fundamentals - You should know the general idea behind language models, understand what prompts and context are, and be aware that a model can produce incomplete or incorrect answers.