recallA retrieval
field guide

THE RECALL PLAYGROUND

Search. Rank.
See what changes.

Explore retrieval through small, focused experiments. Change the inputs and inspect indexes, rankings, metrics, and every stage of a RAG pipeline.

151experiments to exploreRight here in your browser.
151 experimentsLabs run in your browser · no API key needed · Python loads on first run
Unit 01

One question, four ways of searching

How Search Systems Evolved

Interactive experiment
Unit 01

Ahead of time or during the search?

How Search Systems Evolved

Interactive experiment
Unit 01

Should these count as the same word?

Boolean Search and Inverted Indexes

Interactive experiment
Unit 01

Look up words and combine them

Boolean Search and Inverted Indexes

Interactive experiment
Unit 01

Strong clue or weak clue?

Ranking with TF-IDF and BM25

Interactive experiment
Unit 01

Does repeating a word help?

Ranking with TF-IDF and BM25

Interactive experiment
Unit 01

Mark the results, watch the scores

Measuring Retrieval Quality

Interactive experiment
Unit 01

Which score fits the job?

Measuring Retrieval Quality

Interactive experiment
Unit 01

Missed page or wrong page?

Where Lexical Search Falls Short

Interactive experiment
Unit 01

Close the word gap by hand

Where Lexical Search Falls Short

Interactive experiment
Unit 01

The same question, four ways

Why LLMs Need External Knowledge

Interactive experiment
Unit 01

Find the unsupported claims

Why LLMs Need External Knowledge

Interactive experiment
Unit 01

Pick the starting approach

RAG, Prompting, Fine-tuning or Long Context

Interactive experiment
Unit 01

Follow a question through RAG, then break it

Anatomy of a RAG System

Interactive experiment
Unit 01

Which stage would you check first?

Anatomy of a RAG System

Interactive experiment
Unit 02

Find the nearest meaning

What Embeddings Are

Interactive experiment
Unit 02

Match the idea to what it does

How Embedding Models Learn Meaning

Interactive experiment
Unit 02

Angle, length and distance

Similarity Metrics

Interactive experiment
Unit 02

Same query, three models

Modern Embedding Models

Interactive experiment
Unit 02

What will embeddings cost?

Choosing an Embedding Model

Interactive experiment
Unit 02

Pick a starting model

Choosing an Embedding Model

Interactive experiment
Unit 02

One Telugu question, three approaches

Multilingual and Indic Retrieval

Interactive experiment
Unit 02

What kind of query is this?

Multilingual and Indic Retrieval

Interactive experiment
Unit 02

Which method wins this query?

Sparse vs Dense Retrieval

Interactive experiment
Unit 02

How much work is one brute-force search?

Building Semantic Search from Scratch

Interactive experiment
Unit 03

Which format causes this problem?

Enterprise Documents and Their Formats

Interactive experiment
Unit 03

Three ways to read the same PDF page

Parsing Documents into Markdown

Interactive experiment
Unit 03

The same scanned circular, three ways

OCR for Scanned Documents

Interactive experiment
Unit 03

Pick the fix

OCR for Scanned Documents

Interactive experiment
Unit 03

Three versions of the same fee table

Extracting Tables, Forms and Figures

Interactive experiment
Unit 03

How would you store this?

Extracting Tables, Forms and Figures

Interactive experiment
Unit 03

Clean the page without losing the facts

Cleaning and Normalizing Text

Interactive experiment
Unit 03

Clean it or keep it?

Cleaning and Normalizing Text

Interactive experiment
Unit 03

Mask the identifiers, keep the request

Handling Sensitive Data at Ingestion

Interactive experiment
Unit 03

Drop, mask or restrict?

Handling Sensitive Data at Ingestion

Interactive experiment
Unit 03

One night of incremental sync

Document Connectors

Interactive experiment
Unit 03

How should we sync this source?

Document Connectors

Interactive experiment
Unit 03

Four files through the same pipeline

Building an Ingestion Pipeline

Interactive experiment
Unit 03

How long will a full run take?

Building an Ingestion Pipeline

Interactive experiment
Unit 04

Where does this document belong?

Designing a Knowledge Base

Interactive experiment
Unit 04

Find a chunk size that keeps the answer together

Chunk Size and Overlap

Interactive experiment
Unit 04

Fixed size, sentences or headings?

Recursive and Structure-aware Chunking

Interactive experiment
Unit 04

Where should the cuts go?

Semantic Chunking

Interactive experiment
Unit 04

The same messy notice, chunked three ways

Semantic Chunking

Interactive experiment
Unit 04

What does the model get to read?

Parent-Child Chunking

Interactive experiment
Unit 04

Which fix fits?

Late Chunking

Interactive experiment
Unit 04

Same search, with and without metadata

Metadata Engineering

Interactive experiment
Unit 04

What does this change require?

Keeping the Index Fresh

Interactive experiment
Unit 04

Full rebuild or incremental?

Keeping the Index Fresh

Interactive experiment
Unit 05

How much work is one brute-force search?

Why Vector Databases Exist

Interactive experiment
Unit 05

Keyword SQL versus vector search on the same table

Why Vector Databases Exist

Interactive experiment
Unit 05

Matrix, library or database?

Why Vector Databases Exist

Interactive experiment
Unit 05

Search fewer buckets, find most neighbours

Exact vs Approximate Nearest Neighbour Search

Interactive experiment
Unit 05

Clusters and probes

ANN Index Types

Interactive experiment
Unit 05

Hop towards the query

ANN Index Types

Interactive experiment
Unit 05

Which index would you start with?

ANN Index Types

Interactive experiment
Unit 05

Flat, IVF and HNSW on one million vectors

Vector Search with FAISS

Interactive experiment
Unit 05

Which operator?

PostgreSQL + pgvector

Interactive experiment
Unit 05

Index or no index?

PostgreSQL + pgvector

Interactive experiment
Unit 05

Where should this field live?

Schema Design for Vector Storage

Interactive experiment
Unit 05

What ends up in the store?

Vector Database Operations

Interactive experiment
Unit 05

Which operation does this need?

Vector Database Operations

Interactive experiment
Unit 05

How many passages reach the model?

Tuning Retrieval Parameters

Interactive experiment
Unit 05

Relevance or variety?

Tuning Retrieval Parameters

Interactive experiment
Unit 05

Fuse two rankings with RRF

Hybrid Search and Rank Fusion

Interactive experiment
Unit 05

Which method rescues this query?

Hybrid Search and Rank Fusion

Interactive experiment
Unit 05

Same question, different filters

Filtered Vector Search

Interactive experiment
Unit 05

Filter before or after the search?

Filtered Vector Search

Interactive experiment
Unit 05

Does compression change the ranking?

Vector Compression

Interactive experiment
Unit 05

How much memory do the vectors need?

Vector Compression

Interactive experiment
Unit 05

Pick a vector store

Choosing a Vector Database

Interactive experiment
Unit 06

Retrieve, then build the prompt

Building a Naïve RAG Pipeline

Interactive experiment
Unit 06

Which step failed?

Building a Naïve RAG Pipeline

Interactive experiment
Unit 06

Which component do you change?

RAG with LangChain

Interactive experiment
Unit 06

Pack the prompt

Constructing the Context and Prompt

Interactive experiment
Unit 06

Check the citations

Citations and Grounded Answers

Interactive experiment
Unit 06

Three ways to improve one query

Query Rewriting, Expansion and HyDE

Interactive experiment
Unit 06

Which technique would help most?

Query Rewriting, Expansion and HyDE

Interactive experiment
Unit 06

Plain search, multi-query or self-query?

Multi-query and Self-query Retrieval

Interactive experiment
Unit 06

Multi-query, self-query or neither?

Multi-query and Self-query Retrieval

Interactive experiment
Unit 06

Does reranking change what the model sees?

Reranking Retrieved Results

Interactive experiment
Unit 06

Searching a follow-up question

Conversational RAG

Interactive experiment
Unit 06

Does this message need rewriting?

Conversational RAG

Interactive experiment
Unit 06

Route the question

Query Routing

Interactive experiment
Unit 06

An agent answers a multi-part question

Agentic RAG

Interactive experiment
Unit 06

Fixed pipeline or agent?

Agentic RAG

Interactive experiment
Unit 07

Five hard questions for a naïve RAG system

Where Naïve RAG Breaks

Interactive experiment
Unit 07

Name the failure pattern

Where Naïve RAG Breaks

Interactive experiment
Unit 07

What does adding context cost?

Contextual Retrieval

Interactive experiment
Unit 07

Would contextual retrieval help here?

Contextual Retrieval

Interactive experiment
Unit 07

Walk the graph

Knowledge Graphs for Retrieval

Interactive experiment
Unit 07

Vector search or graph walk?

Knowledge Graphs for Retrieval

Interactive experiment
Unit 07

A global question with GraphRAG

GraphRAG

Interactive experiment
Unit 07

Local search, global search or plain vector RAG?

GraphRAG

Interactive experiment
Unit 07

How much bigger is a multi-vector index?

Multi-vector Retrieval

Interactive experiment
Unit 07

Would multi-vector retrieval help?

Multi-vector Retrieval

Interactive experiment
Unit 07

Text search or SQL?

Retrieval over Structured Data

Interactive experiment
Unit 07

Where should this question go?

Retrieval over Structured Data

Interactive experiment
Unit 07

Long context or RAG: tokens and cost

Long Context vs RAG

Interactive experiment
Unit 07

Long context, RAG or both?

Long Context vs RAG

Interactive experiment
Unit 07

Match the idea to the problem

Emerging Retrieval Paradigms

Interactive experiment
Unit 07

Recommend an architecture

Choosing a Retrieval Architecture

Interactive experiment
Unit 08

Text-only or multimodal?

Multimodal Enterprise Knowledge

Interactive experiment
Unit 08

One annual report page, three parsers

Vision-Language Document Parsing

Interactive experiment
Unit 08

OCR or vision-language model?

Vision-Language Document Parsing

Interactive experiment
Unit 08

Images and text in one space

Multimodal Embeddings

Interactive experiment
Unit 08

Good fit for a CLIP-style model?

Multimodal Embeddings

Interactive experiment
Unit 08

Finding an image three ways

Cross-modal Retrieval

Interactive experiment
Unit 08

Which direction is this search?

Cross-modal Retrieval

Interactive experiment
Unit 08

Answering from a page image

Page-image Retrieval

Interactive experiment
Unit 08

How big is a page-image index?

Page-image Retrieval

Interactive experiment
Unit 08

Text extraction or page images?

Page-image Retrieval

Interactive experiment
Unit 08

How should this be stored?

Multimodal Knowledge Base Design

Interactive experiment
Unit 08

One question, three answer pipelines

Multimodal RAG

Interactive experiment
Unit 08

What do images add to a prompt?

Multimodal RAG

Interactive experiment
Unit 08

How long should a transcript chunk be?

Audio and Video Retrieval

Interactive experiment
Unit 08

How would you make this searchable?

Audio and Video Retrieval

Interactive experiment
Unit 09

Find the first broken stage

How RAG Systems Fail

Interactive experiment
Unit 09

Four deliberately broken pipelines

How RAG Systems Fail

Interactive experiment
Unit 09

Good test item or weak one?

Building an Evaluation Dataset

Interactive experiment
Unit 09

Score one configuration's results

Benchmarking Retrieval Configurations

Interactive experiment
Unit 09

What does this benchmark result tell you?

Benchmarking Retrieval Configurations

Interactive experiment
Unit 09

Judge faithfulness claim by claim

Evaluating Generated Answers

Interactive experiment
Unit 09

Where should the judge's passing mark be?

Evaluation Frameworks

Interactive experiment
Unit 09

Which tool fits?

Evaluation Frameworks

Interactive experiment
Unit 09

Same chunks, three embedding set-ups

Debugging Chunking and Embeddings

Interactive experiment
Unit 09

Chunking or embedding?

Debugging Chunking and Embeddings

Interactive experiment
Unit 09

Is it a ranking problem?

Debugging Retrieval

Interactive experiment
Unit 09

Which fix matches the log?

Debugging Retrieval

Interactive experiment
Unit 09

Trace each sentence to its evidence

Debugging Generation

Interactive experiment
Unit 09

Name the generation failure

Debugging Generation

Interactive experiment
Unit 09

Label the failure

Error Analysis

Interactive experiment
Unit 09

Where should we spend the next fortnight?

Error Analysis

Interactive experiment
Unit 09

Three changes, three gate reports

Regression Testing for RAG

Interactive experiment
Unit 10

Explore a trace

Tracing and Observability

Interactive experiment
Unit 10

What does this signal suggest?

Monitoring in Production

Interactive experiment
Unit 10

Fit the evidence into the budget

Context Compression and Token Budgeting

Interactive experiment
Unit 10

Does the index fit in memory?

Performance Tuning for Vector Search

Interactive experiment
Unit 10

Which setting would you change?

Performance Tuning for Vector Search

Interactive experiment
Unit 10

How long does the first full index take?

Scaling to Millions of Documents

Interactive experiment
Unit 10

Shards, replicas or workers?

Scaling to Millions of Documents

Interactive experiment
Unit 10

Set the cache threshold

Caching for RAG

Interactive experiment
Unit 10

What does a response cache save?

Caching for RAG

Interactive experiment
Unit 10

Monthly cost estimate

Cost Engineering

Interactive experiment
Unit 10

Which lever fits?

Cost Engineering

Interactive experiment
Unit 10

Choose a deployment

Deployment Architectures

Interactive experiment
Unit 10

Who sees what?

Permission-aware Retrieval

Interactive experiment
Unit 10

Safe or unsafe?

Permission-aware Retrieval

Interactive experiment
Unit 10

Spot the injected instructions

Securing RAG Applications

Interactive experiment
Unit 10

Match the risk to the defence

Securing RAG Applications

Interactive experiment
Unit 10

Launch, or not yet?

Production Readiness

Interactive experiment

Follow your curiosity.

↑ ↓ to explore · Enter to open · Escape to close