Build Yourself a Private Search System with Retrieval-Augmentation and Haystack

In this talk we will have a look at Haystack, an open source LLM framework, and how we can use it to create custom, private search systems on our own data. We will look at how we can build retrieval augmented generative pipelines for our Notion pages, and how Haystack can help you create custom tooling for larger NLP applications.

Transcript

1. Tuana Çelik Machine Learning & Data Science Meetup Build Yourself a Private Search System with Retrieval-Augmentation and Haystack
2. 01 - What is it? • Twitter: @tuanacelik • Linkedin: Tuana Celik • GitHub: @tuanacelik • 🏗 Open source LLM Framework: Haystack • 📍 Amsterdam, Netherlands Tuana Çelik Lead Developer Advocate 🥑 deepset
3. Making use of LLM capabilities
4. Making use of LLM capabilities
5. Making use of LLM capabilities
6. Making use of LLM capabilities
7. Making use of LLM capabilities • 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 • Most production use-cases are unique and need customization
8. 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
9. Use Case Requirements Where is the data coming from?
10. • Fully open-source framework built in Python for custom LLM applications Haystack (2.0-Beta)
11. • Fully open-source framework built in Python for custom LLM applications • Provides tools that developers need to build state-of-the-art NLP systems Haystack (2.0-Beta)
12. • 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 (2.0-Beta)
13. urls Pipeline
14. Pipeline
15. RAG Pipeline • Data flows from one node to the next, until it reaches the end
16. RAG Pipeline • Data flows from one node to the next, until it reaches the end
17. • Haystack provides a simple interface for the creation of custom components Haystack (2.0-Beta): Custom Components
18. • Haystack provides a simple interface for the creation of custom components Haystack (2.0-Beta): Custom Components Notebook + Blog
19. • Haystack provides a simple interface for the creation of custom components Haystack (2.0-Beta): Custom Components Notebook + Blog
20. • Haystack provides a simple interface for the creation of custom components Haystack (2.0-Beta): Custom Components Notebook + Blog
21. My Private Notion RAG Notebook
22. My Private Notion RAG Notebook
23. My Private Notion RAG Notebook
24. https://haystack.deepset.ai/advent-of-haystack
25. Resources Join 👇 Advent of Haystack Check out 👇 Haystack Read 👇 What is Haystack 2.0-Beta Twitter (X) Linkedin Thank you!