42 recipes
Function Calling
🐦⬛ Information Extraction with Raven
Customization
Prompting
Advance Prompt Customization for Anthropic
Advanced Retrieval
RAG
Advanced RAG: Query Expansion
RAG
AstraDB 🤝 Haystack Integration
RAG
Build with Gemma and Haystack 2.x
Chat
SQL
Chat With Your SQL Database
RAG
Vector Databases
Chroma Indexing and RAG Examples
Multilingual RAG
Cohere v3 for Multilingual QA
🧪 Experimental
Chat
RAG
Conversational RAG using Memory
🧪 Experimental
Evaluation
Evaluating RAG Pipelines with EvaluationHarness
Advanced Retrieval
Metadata
Extract Metadata Filters from a Query
Function Calling
Multimodal
Function Calling and Multimodal QA with Gemini
Function Calling
Chat
Function Calling with OpenAIChatGenerator
Model Serving
RAG
Getting a Daily Digest From Tech Websites
RAG
Customization
Hacker News Summaries with Custom Components
RAG
Model Serving
Haystack RAG Pipeline with Self-Deployed AI models using NVIDIA NIMs
Advanced Retrieval
Hybrid Retrieval with BM42
Advanced Retrieval
Metadata
Improve Retrieval by Embedding Meaningful Metadata
🧪 Experimental
Advanced Retrieval
RAG
Improving Retrieval with Auto-Merging and Hierarchical Document Retrieval
🧪 Experimental
Function Calling
Invoking APIs with OpenAPITool
Summarization
Advanced Retrieval
Legal Document Analysis with jina-embeddings-v2-base-en
Audio
Multilingual RAG
Multilingual RAG on a Podcast
RAG
PDF-Based Question Answering with Amazon Bedrock and Haystack
Customization
Prompting
Prompt Optimization with DSPy
RAG
Question Answering with Amazon Sagemaker, Chroma and Haystack
Evaluation
RAG Evaluation with Prometheus 2
Evaluation
RAG Pipeline Evaluation Using DeepEval
Evaluation
RAG Pipeline Evaluation Using RAGAS
Evaluation
RAG Pipeline Evaluation Using UpTrain
RAG
Advanced Retrieval
RAG Pipeline Using FastEmbed for Embeddings Generationn
RAG
RAG with Llama 3.1
RAG
Web-QA
RAG: Extract and use website content for question answering with Apify-Haystack integration
🧪 Experimental
Customization
Run Tasks Concurrently Within a Custom Component
RAG
Advanced Retrieval
Sparse Embedding Retrieval with Qdrant and FastEmbed
Audio
Speaker Diarization with AssemblyAI
Discovery
Streaming Model Explorer
Model Serving
Use the ⚡ vLLM inference engine in Haystack 2.x
Advanced Retrieval
RAG
Using Hypothetical Document Embeddinga (HyDE) to Improve Retrieval
Web-QA
Web QA with Mixtral-8x7B-Instruct-v0.1
Function Calling
🦍 Information Extraction with Gorilla
Model Serving
Chat
🧩 Quizzes and Adventures 🏰 with Character Codex and llamafile
RAG