Skip to main content
This module provides Haystack-based retrieval and RAG pipeline implementations across all five supported vector database backends. Every feature is organized as a self-contained directory with configuration files, indexing scripts, and search scripts for each backend.

​
What you get

  • Seventeen retrieval and RAG patterns implemented using Haystack’s pipeline and component abstractions
  • Full portability across Pinecone, Weaviate, Chroma, Milvus, and Qdrant (with feature-specific notes on backend support)
  • YAML-driven configuration with environment variable substitution so credentials stay out of code
  • Evaluation support via shared utils/evaluation.py metrics
  • Shared reusable components and helper factories that all feature pipelines draw from

​
Module structure

Each feature directory follows the same layout: 
feature_name/
├── configs/
│   ├── chroma_triviaqa.yaml
│   ├── milvus_triviaqa.yaml
│   ├── pinecone_triviaqa.yaml
│   ├── qdrant_triviaqa.yaml
│   ├── weaviate_triviaqa.yaml
│   └── (one config per backend × dataset combination)
├── indexing/
│   ├── chroma.py
│   ├── milvus.py
│   ├── pinecone.py
│   ├── qdrant.py
│   └── weaviate.py
├── search/
│   ├── chroma.py
│   ├── milvus.py
│   ├── pinecone.py
│   ├── qdrant.py
│   └── weaviate.py
└── README.md

​
Feature catalog

Semantic search

Dense vector similarity search - the baseline pattern

Hybrid search

Combines dense + sparse embeddings with RRF fusion

Components

Reusable pipeline components for routing, compression, and query enhancement

Pipelines

Pipeline architecture patterns and composition

​
Core retrieval patterns

FeatureDescriptionUse when
semantic_searchDense vector similarity searchStarting point and baseline
hybrid_indexingDense + sparse embeddings with RRFBoth semantic and keyword precision needed
sparse_indexingSparse-only retrievalPure keyword/lexical precision
rerankingTwo-stage retrieval with cross-encoderBetter final ranking needed
mmrMaximal Marginal RelevanceRelevant + diverse results
diversity_filteringSimilarity count filteringLess redundant context

​
Advanced retrieval

FeatureDescriptionUse when
metadata_filteringStructured constraintsNeed to filter by attributes
json_indexingJSON-native documentsStructured fields + semantic content
query_enhancementMulti-query, HyDE, step-backBetter query recall
contextual_compressionAbstractive, extractive, relevance filteringShorter, cleaner context
parent_document_retrievalIndex children, retrieve parentsLong docs with fragment search

​
Production features

FeatureDescriptionUse when
cost_optimized_ragToken/compute budget controlCost reduction needed
agentic_ragMulti-step iterative RAG with self-reflectionComplex multi-hop questions
multi_tenancyTenant-scoped isolationPer-customer data isolation
namespacesLogical segmentationEnvironment separation

​
Embedding configuration

All Haystack feature pipelines read embedding configuration from the YAML config: 
embeddings:
  model: "sentence-transformers/all-MiniLM-L6-v2"  # Required
  device: "cpu"                                      # Optional
  batch_size: 32                                      # Optional
For hybrid and sparse features: 
sparse:
  model: "naver/splade-cocondenser-ensembledistil"

​
RAG configuration

Generation is controlled by the rag section: 
rag:
  enabled: true
  model: "llama-3.3-70b-versatile"
  api_key: "${GROQ_API_KEY}"
  api_base_url: "https://api.groq.com/openai/v1"
  temperature: 0.7
  max_tokens: 2048
Set enabled: false to run retrieval-only pipelines without generation.
1

Run semantic search baseline

Start with semantic_search on your target backend with a small dataset limit (100-200 records) and verify the pipeline loads, indexes, and retrieves successfully.
2

Measure retrieval quality

Use evaluation_queries() and evaluate_retrieval() to establish baseline metrics.
3

Add improvements incrementally

Add one improvement feature at a time (e.g., reranking or hybrid_indexing) and measure whether quality improves on your evaluation set.
4

Add production features

Once the retrieval baseline is strong, adopt multi_tenancy or namespaces for data isolation, and cost_optimized_rag for budget controls.
5

Handle complex queries

Use agentic_rag or query_enhancement for hard multi-hop questions where single-pass retrieval falls short.

​
Supported backends

  • Chroma: Local embedded vector database with SQLite persistence
  • Milvus: High-performance distributed vector database
  • Pinecone: Managed vector database with native sparse vector support
  • Qdrant: Vector database with advanced filtering and multitenancy
  • Weaviate: GraphQL-based vector database with semantic search
Each backend has consistent API patterns through Haystack’s abstraction layer.

​
Next steps

Semantic search

Start with the baseline semantic search pattern

Hybrid search

Learn about dense + sparse hybrid retrieval

Components

Explore reusable pipeline components

Pipelines

Understand pipeline architecture patterns

Build docs developers (and LLMs) love

Get started for freeTalk to us