Bilge Yücel PyLadiesCon Build Your First LLM-based Application with Haystack 

01 - What is it? ● 🥑 Developer Advocate at deepset ● 🏗 Open source LLM Framework: Haystack ● 📍 Istanbul, Turkey Bilge Yücel Developer Advocate 🥑 deepset Twitter: @bilgeycl Linkedin: Bilge Yucel GitHub: @bilgeyucel 

Agenda 01 - Text Embeddings 02 - Vector Databases 03 - Retrieval Ret 04 - LLMs 05 - Build a Generative QA App 

01 Text Embeddings 

Text Embeddings/Text Vectors to be or not to be ● Manageable by computers ● Different techniques: ○ Sparse: TF-IDF, BM25... ○ Dense: Trained models (Sentence Transformers, Cohere, OpenAI...) ● Often has 768 dimensions 

02 Vector Databases 

● Databases that store high-dimensional vectors ● Optimized for vectors: ○ Vector search ○ CRUD operations ○ Metadata filtering Vector Databases 

03 Retrieval 

Retrieval Query ● Getting the most relevant information to the query ● Used for semantic search, question answering and more 

04 LLMs 

Large Language Models (LLMs) ● Big language models ● Prompt → Human-like output ● Text generation: summarization, generative QA, writing code, chat… 

05 Build a Generative QA Application 

Prompting 

LLM: Limitations ● LLMs do not know the answer to everything ● But they are good at following instructions ● We can help them in their task by giving them the relevant context + instruction 

Prompting 

Prompting 

Retrieval Augmented Generation (RAG) 

Retrieval Augmentation Use Cases Prompt Given the following context, answer the question. If the answer is not contained within the context, say ‘I don’t know’. Question Answering Context: {{context}} Question: {{question}} Answer: Prompt Summarize the following text. Summarization Text: {{text}} Summary: Question Generation Document: {{document}} Questions: Prompt Given the following document, generate some questions 

● Fully open-source framework built in Python for custom LLM applications ● Provides tools that developers need to build state-of-the-art NLP systems ● Building blocks: Pipelines & Components Haystack 

Indexing Pipeline urls 

Indexing Pipeline Notebook 

Indexing Pipeline Notebook 

Generative QA Pipeline (RAG) What is happening at OpenAI? 

Generative QA Pipeline (RAG) Notebook 

Generative QA Pipeline (RAG) Notebook 

https://haystack.deepset.ai/advent-of-haystack 

Resources Join 👇 Advent of Haystack Check out 👇 Haystack @bilgeycl Bilge Yücel Find 👇 Presentation 

Thank you!