Skip to content

Commit f1ad48f

Browse files
committed
Resolve merge conflicts in docs/index.md - keep current branch content
2 parents d1acb9f + 448f518 commit f1ad48f

File tree

1 file changed

+66
-139
lines changed

1 file changed

+66
-139
lines changed

docs/index.md

Lines changed: 66 additions & 139 deletions
Original file line numberDiff line numberDiff line change
@@ -13,13 +13,11 @@ date: 2025-04-10
1313
*A systematic approach to building self-improving AI systems*
1414

1515
!!! abstract "About This Book"
16-
This book provides a structured approach to evolving Retrieval-Augmented Generation (RAG) from a technical implementation into a continuously improving product. You'll learn to combine product thinking with data science principles to create AI systems that deliver increasing value over time.
17-
18-
Most teams focus on the latest models and algorithms while missing the fundamentals: understanding their data, measuring performance, and systematically improving based on user feedback. This resource shows you the proven approach used by companies like Zapier, Glean, and Exa.
16+
This book provides a structured approach to evolving Retrieval-Augmented Generation (RAG) from a technical implementation into a continuously improving product. You'll learn to combine product thinking with data science principles to create AI systems that deliver increasing value over time.
1917

2018
## The RAG Improvement Flywheel
2119

22-
At the core of this book is the RAG improvement flywheel - a continuous cycle that transforms user interactions into product enhancements:
20+
At the core of this book is the RAG improvement flywheel - a continuous cycle that transforms user interactions into product enhancements.
2321

2422
```mermaid
2523
graph TD
@@ -36,159 +34,64 @@ graph TD
3634
```
3735

3836
!!! tip "Beyond Technical Implementation"
39-
This book goes beyond teaching you how to implement RAG. It shows you how to think about RAG as a product that continuously evolves to meet user needs and deliver business value.
40-
41-
## Table of Contents
42-
43-
### Workshop Series
44-
45-
| Chapter | Title | Focus Area | Key Outcomes |
46-
|---------|-------|------------|-------------|
47-
| [Introduction](workshops/chapter0.md) | Beyond Implementation to Improvement | Product Mindset | Shift from technical to product thinking |
48-
| [Chapter 1](workshops/chapter1.md) | Starting the Flywheel | Evaluation & Metrics | Build synthetic data and evaluation frameworks |
49-
| [Chapter 2](workshops/chapter2.md) | From Evaluation to Enhancement | Fine-tuning & Training | Convert evaluations into training data |
50-
| [Chapter 3.1](workshops/chapter3-1.md) | Feedback Collection | User Experience | Design feedback mechanisms that users actually use |
51-
| [Chapter 3.2](workshops/chapter3-2.md) | Streaming & Performance | User Experience | Implement streaming and reduce perceived latency |
52-
| [Chapter 3.3](workshops/chapter3-3.md) | Quality Improvements | User Experience | Citations, chain-of-thought, and validation |
53-
| [Chapter 4.1](workshops/chapter4-1.md) | Topic Modeling | User Analysis | Find patterns in user feedback and queries |
54-
| [Chapter 4.2](workshops/chapter4-2.md) | Prioritization | User Analysis | Turn insights into strategic action plans |
55-
| [Chapter 5.1](workshops/chapter5-1.md) | Specialized Retrieval | Architecture | Build specialized capabilities for different content |
56-
| [Chapter 5.2](workshops/chapter5-2.md) | Multimodal Search | Architecture | Handle documents, images, tables, and SQL |
57-
| [Chapter 6.1](workshops/chapter6-1.md) | Query Routing | Architecture | Route queries to specialized components |
58-
| [Chapter 6.2](workshops/chapter6-2.md) | Tool Implementation | Architecture | Build interfaces and routers |
59-
| [Chapter 6.3](workshops/chapter6-3.md) | Continuous Improvement | Architecture | Measure and improve systematically |
60-
61-
### Expert Talks
62-
63-
| Speaker | Company | Topic | Key Insight |
64-
|---------|---------|-------|-------------|
65-
| [Skylar Payne](talks/rag-antipatterns-skylar-payne.md) | Independent | RAG Anti-patterns | 90% of teams adding complexity see worse performance |
66-
| [Ayush](talks/fine-tuning-rerankers-embeddings-ayush-lancedb.md) | LanceDB | Fine-tuning | Re-rankers provide 15-20% improvement with minimal latency |
67-
| [Vitor](talks/zapier-vitor-evals.md) | Zapier | Feedback Systems | Simple UX changes increased feedback 4x |
68-
| [Kelly Hong](talks/embedding-performance-generative-evals-kelly-hong.md) | Independent | Evaluation | Custom benchmarks often contradict public ones |
69-
| [Ben & Sidhant](talks/online-evals-production-monitoring-ben-sidhant.md) | Independent | Production Monitoring | Traditional error monitoring doesn't work for AI |
70-
| [Manav](talks/glean-manav.md) | Glean | Enterprise Search | Custom embeddings achieve 20% improvements |
71-
| [Anton](talks/chromadb-anton-chunking.md) | ChromaDB | Chunking | Chunking remains critical even with infinite context |
72-
| [Colin](talks/colin-rag-agents.md) | Independent | Agentic RAG | Simple tools often outperform sophisticated embeddings |
73-
| [Adit](talks/reducto-docs-adit.md) | Reducto | Document Processing | Hybrid CV + VLM pipelines outperform pure approaches |
74-
| [Will Bryk](talks/semantic-search-exa-will-bryk.md) | Exa | Semantic Search | AI systems need fundamentally different search engines |
75-
| [John Berryman](talks/john-lexical-search.md) | Independent | Lexical Search | Semantic search struggles with exact matching |
76-
| [Daniel](talks/superlinked-encoder-stacking.md) | Superlinked | Multi-modal | Mixture of specialized encoders beats text-only |
77-
| [Michael](talks/rag-without-apis-browser-michael-struwig.md) | OpenBB | Browser RAG | Browser-as-data-layer for secure access |
78-
| [Anton](talks/query-routing-anton.md) | ChromaDB | Query Routing | Separate indexes often outperform filtered large ones |
79-
80-
## Quick Wins: High-Impact RAG Improvements
81-
82-
Based on real-world implementations, here are proven improvements you can implement quickly:
83-
84-
!!! success "Top 5 Quick Wins"
85-
1. **Change Feedback Copy** : Replace "How did we do?" with "Did we answer your question?"
86-
2. **Use Markdown Tables** : Format structured data as markdown tables instead of JSON/CSV or XML when tables are complex and multiple columns / headers are needed.
87-
3. **Add Streaming Progress** : Show "Searching... Analyzing... Generating..." with progress
88-
4. **Implement Page-Level Chunking** : For documentation, respect page boundaries, and use page-level chunking. Humans tend to create semantically coherent chunks at the page level.
89-
90-
!!! tip "Medium-Term Improvements (2-4 weeks)"
91-
- **Fine-tune embeddings**: $1.50 and 40 minutes for 6-10% improvement
92-
- **Add re-ranker**: 15-20% retrieval improvement
93-
- **Build specialized tools**: 10x better for specific use cases
94-
- **Implement contextual retrieval**: 30% better context understanding
95-
- **Create Slack feedback integration**: 5x more enterprise feedback
96-
97-
## Workshop Series
98-
99-
### Foundation: Metrics & Evaluation
100-
101-
**[Introduction: Beyond Implementation to Improvement](workshops/chapter0.md)**
102-
Shifting from technical implementation to product-focused continuous improvement. Understanding RAG as a recommendation engine wrapped around language models and the improvement flywheel.
103-
104-
**[Chapter 1: Kickstarting the Data Flywheel with Synthetic Data](workshops/chapter1.md)**
105-
Common pitfalls in AI development, leading vs. lagging metrics, understanding precision and recall for retrieval evaluation, and synthetic data generation techniques.
106-
107-
**[Chapter 2: Converting Evaluations into Training Data for Fine-Tuning](workshops/chapter2.md)**
108-
Why generic embeddings fall short, converting evaluation examples into effective few-shot prompts, contrastive learning, and re-rankers as cost-effective enhancement strategies.
109-
110-
### User Experience & Feedback
111-
112-
**[Chapter 3.1: Feedback Collection - Building Your Improvement Flywheel](workshops/chapter3-1.md)**
113-
Making feedback visible and engaging (increasing rates from <1% to >30%), proven copy patterns, segmented feedback, and enterprise feedback collection.
37+
This book goes beyond teaching you how to implement RAG. It shows you how to think about RAG as a product that continuously evolves to meet user needs and deliver business value.
11438

115-
**[Chapter 3.2: Overcoming Latency - Streaming and Interstitials](workshops/chapter3-2.md)**
116-
Psychology of waiting, implementing streaming responses for 30-40% higher feedback collection, skeleton screens and meaningful interstitials.
39+
## Chapters
11740

118-
**[Chapter 3.3: Quality of Life Improvements](workshops/chapter3-3.md)**
119-
Interactive citations, chain of thought reasoning for 8-15% accuracy improvements, validation patterns as safety nets, and strategic rejection.
41+
### [Introduction: Beyond Implementation to Improvement](workshops/chapter0.md)
12042

121-
### Analysis & Specialization
43+
Understand why systematic improvement matters and how to approach RAG as a product rather than just a technical implementation.
12244

123-
**[Chapter 4.1: Topic Modeling and Analysis](workshops/chapter4-1.md)**
124-
Moving from individual feedback to systematic pattern identification, topics vs. capabilities, and transforming "make the AI better" into specific priorities.
45+
### [Chapter 1: Starting the Flywheel](workshops/chapter1.md)
12546

126-
**[Chapter 4.2: Prioritization and Roadmapping](workshops/chapter4-2.md)**
127-
Impact/effort prioritization using 2x2 frameworks, failure mode analysis, and building strategic roadmaps based on user behavior patterns.
47+
Learn how to overcome the cold-start problem, establish meaningful metrics, and create a data foundation that drives product decisions.
12848

129-
### Advanced Architecture
49+
### [Chapter 2: From Evaluation to Enhancement](workshops/chapter2.md)
13050

131-
**[Chapter 5.1: Understanding Specialized Retrieval](workshops/chapter5-1.md)**
132-
Why monolithic approaches reach limits, two complementary strategies (extracting metadata vs. creating synthetic text), and two-level measurement.
51+
Transform evaluation insights into concrete product improvements through fine-tuning, re-ranking, and targeted enhancements.
13352

134-
**[Chapter 5.2: Implementing Multimodal Search](workshops/chapter5-2.md)**
135-
Advanced document retrieval, image search challenges, table search dual approach, SQL generation using RAG playbook, and RAPTOR hierarchical summarization.
53+
### [Chapter 3: The User Experience of AI](workshops/chapter3-1.md)
13654

137-
**[Chapter 6.1: Query Routing Foundations](workshops/chapter6-1.md)**
138-
The API mindset, organizational structure, evolution from monolithic to modular architecture, and performance formula.
55+
Design interfaces that both delight users and gather valuable feedback, creating a virtuous cycle of improvement.
13956

140-
**[Chapter 6.2: Tool Interfaces and Implementation](workshops/chapter6-2.md)**
141-
Designing tool interfaces, router implementation using structured outputs, dynamic example selection, and tool portfolio design.
57+
### [Chapter 4: Understanding Your Users](workshops/chapter4-1.md)
14258

143-
**[Chapter 6.3: Performance Measurement and Improvement](workshops/chapter6-3.md)**
144-
Measuring tool selection effectiveness, dual-mode UI, user feedback as training data, and creating improvement flywheel.
59+
Segment users and queries to identify high-value opportunities and create targeted improvement strategies.
14560

146-
## How to Use This Resource
61+
### [Chapter 5: Building Specialized Capabilities](workshops/chapter5-1.md)
14762

148-
**For Beginners**: Start with the [Introduction](workshops/chapter0.md) to understand the product mindset, then work through the chapters sequentially.
63+
Develop purpose-built solutions for different user needs spanning documents, images, tables, and structured data.
14964

150-
**For Quick Wins**: Jump to the [Quick Wins section](#quick-wins-high-impact-rag-improvements) above for immediate improvements you can implement today.
65+
### [Chapter 6: Unified Product Architecture](workshops/chapter6-1.md)
15166

152-
**For Specific Problems**: Check the [FAQ](office-hours/faq.md) for answers to common questions, or browse talks by topic in the table above.
67+
Create a cohesive product experience that intelligently routes to specialized components while maintaining a seamless user experience.
15368

154-
**For Complete Implementation**: Follow the full workshop series from Chapter 1 through 6.3 to build a comprehensive self-improving RAG system.
69+
### [Key Takeaways: Product Principles for AI Applications](misc/what-i-want-you-to-takeaway.md)
15570

156-
## Key Insights Across All Content
71+
Core principles that will guide your approach to building AI products regardless of how the technology evolves.
15772

158-
**Most Important Finding**: Teams that iterate fastest on data examination consistently outperform those focused on algorithmic sophistication.
73+
## Talks and Presentations
15974

160-
**Most Underutilized Techniques**: Fine-tuning embeddings and re-rankers are more accessible and impactful than most teams realize.
75+
Explore insights from industry experts and practitioners through our collection of talks, lightning lessons, and presentations:
16176

162-
**Biggest Mistake**: 90% of teams add complexity that makes their RAG systems worse. Start simple, measure everything, improve systematically.
77+
### [Featured Talks](talks/index.md)
16378

164-
**Critical Success Factors**:
165-
- Establish evaluation frameworks before building
166-
- Design feedback collection into your UX from day one
167-
- Understand your users and their query patterns
168-
- Build specialized tools for different content types
169-
- Create unified routing that feels seamless to users
79+
- **[Fine-tuning Re-rankers and Embedding Models for Better RAG Performance](talks/fine-tuning-rerankers-embeddings-ayush-lancedb.md)** - Practical approaches to enhancing retrieval quality (Ayush from LanceDB)
80+
- **[RAG Anti-patterns in the Wild](talks/rag-antipatterns-skylar-payne.md)** - Common mistakes and how to fix them (Skylar Payne)
81+
- **[Semantic Search Over the Web with Exa](talks/semantic-search-exa-will-bryk.md)** - Building AI-first search engines (Will Bryk)
82+
- **[Understanding Embedding Performance through Generative Evals](talks/embedding-performance-generative-evals-kelly-hong.md)** - Custom evaluation methodologies (Kelly Hong)
83+
- **[Online Evals and Production Monitoring](talks/online-evals-production-monitoring-ben-sidhant.md)** - Monitoring AI systems at scale (Ben Hylak & Sidhant Bendre)
17084

171-
## Frequently Asked Questions
172-
173-
Top questions from office hours:
174-
175-
- **"Is knowledge graph RAG production ready?"** Probably not. [See why →](office-hours/faq.md#is-knowledge-graph-rag-production-ready-by-now-do-you-recommend-it)
176-
- **"How do we handle time-based queries?"** Use PostgreSQL with pgvector-scale. [Learn more →](office-hours/faq.md#how-do-we-introduce-a-concept-of-time-and-vector-search-to-answer-questions-like-whats-the-latest-news-without-needing-to-move-to-a-graph-database)
177-
- **"Should we use DSPy for prompt optimization?"** It depends. [See when →](office-hours/faq.md#what-is-your-take-on-dspy-should-we-use-it)
178-
- **"Would you recommend ColBERT models?"** Test against your baseline first. [See approach →](office-hours/faq.md#would-you-recommend-using-colbert-models-or-other-specialized-retrieval-approaches)
179-
180-
[Browse All FAQ](office-hours/faq.md){ .md-button } [View Office Hours](office-hours/){ .md-button }
85+
[View all talks →](talks/index.md)
18186

18287
## For Product Leaders, Engineers, and Data Scientists
18388

18489
!!! info "What You'll Learn"
185-
18690
**For Product Leaders**
18791
- How to establish metrics that align with business outcomes
18892
- Frameworks for prioritizing AI product improvements
18993
- Approaches to building product roadmaps for RAG applications
19094
- Methods for communicating AI improvements to stakeholders
191-
19295
**For Engineers**
19396
- Implementation patterns that facilitate rapid iteration
19497
- Architectural decisions that enable continuous improvement
@@ -201,32 +104,56 @@ Top questions from office hours:
201104
- Frameworks for measuring retrieval effectiveness
202105
- Approaches to continuous learning from user interactions
203106

204-
## Navigate by Topic
205-
206-
**Evaluation & Metrics**: [Chapter 1](workshops/chapter1.md)[Kelly Hong Talk](talks/embedding-performance-generative-evals-kelly-hong.md)[Vitor Zapier Talk](talks/zapier-vitor-evals.md)
207-
208-
**Fine-tuning & Training**: [Chapter 2](workshops/chapter2.md)[Ayush LanceDB Talk](talks/fine-tuning-rerankers-embeddings-ayush-lancedb.md)[Manav Glean Talk](talks/glean-manav.md)
107+
## Quick Wins: High-Impact RAG Improvements
209108

210-
**User Experience**: [Chapter 3 Series](workshops/chapter3-1.md)[Streaming Guide](workshops/chapter3-2.md)[Quality Improvements](workshops/chapter3-3.md)
109+
Based on real-world implementations, here are proven improvements you can implement quickly:
211110

212-
**Architecture & Routing**: [Chapter 6 Series](workshops/chapter6-1.md)[Anton Query Routing](talks/query-routing-anton.md)[Multi-modal Retrieval](talks/superlinked-encoder-stacking.md)
111+
!!! success "Top 5 Quick Wins"
112+
1. **Change Feedback Copy**
113+
- Replace "How did we do?" with "Did we answer your question?"
114+
- **Impact**: 5x increase in feedback collection
115+
- **Effort**: 1 hour
116+
117+
2. **Use Markdown Tables**
118+
- Format structured data as markdown tables instead of JSON/CSV
119+
- If tables are complex, represent it in XML
120+
- **Impact**: 12% better lookup accuracy
121+
- **Effort**: 2-4 hours
122+
123+
3. **Add Streaming Progress**
124+
- Show "Searching... Analyzing... Generating..." with progress
125+
- Stream the response as it's being generated when possible
126+
- **Impact**: 45% reduction in perceived latency
127+
- **Effort**: 1 sprint
128+
129+
4. **Implement Page-Level Chunking**
130+
- For documentation, respect page boundaries, and use page-level chunking. Humans tend to create semantically coherent chunks at the page level.
131+
- **Impact**: 20-30% better retrieval for docs
132+
- **Effort**: 1 day
213133

214-
**Production & Monitoring**: [Ben & Sidhant Talk](talks/online-evals-production-monitoring-ben-sidhant.md)[RAG Anti-patterns](talks/rag-antipatterns-skylar-payne.md)
134+
!!! tip "Medium-Term Improvements (2-4 weeks)"
135+
- **Fine-tune embeddings**: $1.50 and 40 minutes for 6-10% improvement
136+
- **Add re-ranker**: 15-20% retrieval improvement
137+
- **Build specialized tools**: 10x better for specific use cases
138+
- **Implement contextual retrieval**: 30% better context understanding
139+
- **Create Slack feedback integration**: 5x more enterprise feedback
215140

141+
!!! info "Learn from the Experts"
142+
Before implementing, learn from these practical talks:
143+
- [**RAG Anti-patterns in the Wild**](talks/rag-antipatterns-skylar-payne.md) - Common mistakes across industries and how to fix them
144+
- [**Document Ingestion Best Practices**](talks/reducto-docs-adit.md) - Production-ready parsing for tables, PDFs, and complex documents
216145

217146
## About the Author
218147

219-
Jason Liu brings practical experience from his work at Facebook, Stitch Fix, and as a consultant for companies like HubSpot, Zapier, and many others. His background spans computer vision, recommendation systems, and RAG applications across diverse domains.
148+
Jason Liu brings practical experience from Facebook, Stitch Fix, and as a consultant for companies like HubSpot, Zapier, and many others. His background spans computer vision, recommendation systems, and RAG applications across diverse domains.
220149

221150
!!! quote "Author's Philosophy"
222-
"The most successful AI products aren't the ones with the most sophisticated models, but those built on disciplined processes for understanding users, measuring performance, and systematically improving. This resource will show you how to create not just a RAG application, but a product that becomes more valuable with every interaction."
223-
224-
---
151+
"The most successful AI products aren't the ones with the most sophisticated models, but those built on disciplined processes for understanding users, measuring performance, and systematically improving. This book will show you how to create not just a RAG application, but a product that becomes more valuable with every interaction."
225152

226153
## Getting Started
227154

228155
Begin your journey by reading the [Introduction](workshops/chapter0.md) or jump directly to [Chapter 1](workshops/chapter1.md) to start building your evaluation framework and data foundation.
229156

230157
If you want to get discounts and 6 day email source on the topic make sure to subscribe to
231158

232-
<script async data-uid="010fd9b52b" src="https://fivesixseven.kit.com/010fd9b52b/index.js"></script>
159+
<script async data-uid="010fd9b52b" src="https://fivesixseven.kit.com/010fd9b52b/index.js"></script>

0 commit comments

Comments
 (0)