🧑‍🍳 Cookbook

You can use these examples as guidelines on how to make use of different model providers, vector databases, retrieval techniques and more with Haystack. Most of them showcase a specific, small demo.

🧑‍🍳 Cookbook

66 recipes

Agent-Powered Retrieval with Haystack

Calculating a Hallucination Score with the OpenAIChatGenerator

Build Browser Agents with Gemini + Playwright MCP

AI Guardrails: Content Moderation and Safety with Open Language Models

Introduction to Multimodal Text Generation

Build with Llama Stack and Haystack Agent

Breakpoint on Agent in a Pipeline

Build a GitHub PR Creator Agent

Trace and Evaluate RAG with Arize Phoenix

Simple Keyword Extraction using OpenAIChatGenerator

DevOps Support Agent with Human in the Loop

Hybrid RAG Pipeline with Breakpoints

Building an Interactive Feedback Review Agent with Azure AI Search and Haystack

Extracting Metadata with an LLM

Build a GitHub Issue Resolver Agent

RAG: Web Search and Analysis with Apify and Haystack

Running Haystack Pipelines in Asynchronous Environments

Create a Swarm of Agents

Web-Enhanced Self-Reflecting Agent

Multimodal Agent with fastRAG and Haystack

Evaluating AI with Haystack

Newsletter Sending Agent with Tools

Advanced RAG: Automated Structured Metadata Enrichment

Agentic RAG with Llama 3.2 3B

Define & Run Tools

Advanced RAG: Query Decomposition and Reasoning

Improving Retrieval with Auto-Merging and Hierarchical Document Retrieval

Analyze Your Instagram Comments’ Vibe with Apify and Haystack

Conversational RAG using Memory

Advanced RAG: Query Expansion

RAG: Extract and use website content for question answering with Apify-Haystack integration

Invoking APIs with OpenAPITool

Hybrid Retrieval with BM42

🧩 Quizzes and Adventures 🏰 with Character Codex and llamafile

RAG Evaluation with Prometheus 2

Prompt Optimization with DSPy

Haystack RAG Pipeline with Self-Deployed AI models using NVIDIA NIMs

Extract Metadata Filters from a Query

Sparse Embedding Retrieval with Qdrant and FastEmbed

RAG with Llama 3.1

Chat With Your SQL Database

RAG Pipeline Evaluation Using DeepEval

RAG Pipeline Evaluation Using RAGAS

Speaker Diarization with AssemblyAI

Advanced Prompt Customization for Anthropic

🐦‍⬛ Information Extraction with Raven

RAG Pipeline Using FastEmbed for Embeddings Generation

Using Hypothetical Document Embeddings (HyDE) to Improve Retrieval

Getting a Daily Digest From Tech Websites

Build with Gemma and Haystack

Use the ⚡ vLLM inference engine with Haystack

Function Calling with OpenAIChatGenerator

Question Answering with Amazon Sagemaker, Chroma and Haystack

Cohere v3 for Multilingual QA

Streaming Model Explorer

AstraDB 🤝 Haystack Integration

PDF-Based Question Answering with Amazon Bedrock and Haystack

Improve Retrieval by Embedding Meaningful Metadata

🦍 Information Extraction with Gorilla

Multilingual RAG on a Podcast

Legal Document Analysis with jina-embeddings-v2-base-en

Function Calling and Multimodal QA with Gemini

Chroma Indexing and RAG Examples

Web QA with Mixtral-8x7B-Instruct-v0.1

Hacker News Summaries with Custom Components

🪁 RAG pipelines with Haystack + Zephyr 7B Beta

Want to contribute on GitHub?

Looking for a tutorial?

No results found

There has been an error.