AI engineering: building applications with foundation models
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Sebastopol, CA
O'Reilly
[2025]
|
| Schlagworte: | |
| Online-Zugang: | Inhaltsverzeichnis |
| Beschreibung: | xxi, 509 Seiten Illustrationen, Diagramme |
| ISBN: | 9781098166304 |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV050100168 | ||
| 003 | DE-604 | ||
| 005 | 20250205 | ||
| 007 | t| | ||
| 008 | 241217s2025 xx a||| |||| 00||| eng d | ||
| 020 | |a 9781098166304 |9 978-1-098-16630-4 | ||
| 035 | |a (OCoLC)1492136105 | ||
| 035 | |a (DE-599)BVBBV050100168 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-473 |a DE-Aug4 |a DE-1050 |a DE-29T |a DE-523 | ||
| 084 | |a ST 300 |0 (DE-625)143650: |2 rvk | ||
| 100 | 1 | |a Huyen, Chip |e Verfasser |0 (DE-588)1261904311 |4 aut | |
| 245 | 1 | 0 | |a AI engineering |b building applications with foundation models |c Chip Huyen |
| 264 | 1 | |a Sebastopol, CA |b O'Reilly |c [2025] | |
| 300 | |a xxi, 509 Seiten |b Illustrationen, Diagramme | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 650 | 4 | |a bicssc / Enterprise software | |
| 650 | 4 | |a bicssc / Operational research | |
| 650 | 4 | |a bicssc / Mathematical theory of computation | |
| 650 | 4 | |a bicssc / Machine learning | |
| 650 | 4 | |a bisacsh / COMPUTERS / Business & Productivity Software / Business Intelligence | |
| 650 | 4 | |a bisacsh / COMPUTERS / Machine Theory | |
| 650 | 4 | |a bisacsh / COMPUTERS / Data Science / Machine Learning | |
| 776 | 0 | 8 | |i Erscheint auch als |n Online-Ausgabe |z 978-1-09-816627-4 |
| 856 | 4 | 2 | |m Digitalisierung Bibliothek HTW Berlin |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=035437329&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-035437329 | |
Datensatz im Suchindex
| _version_ | 1823864251260862464 |
|---|---|
| adam_text |
TABLE
OF CONTENTS
PREFACE
XI
1.
INTRODUCTION TO BUILDING
AL APPLICATIONS WITH FOUNDATION
MODELS
1
THE RISE OF
AI ENGINEERING
2
FROM LANGUAGE MODELS
TO LARGE LANGUAGE MODELS
2
FROM
LARGE LANGUAGE
MODELS TO FOUNDATION
MODELS
8
FROM
FOUNDATION MODELS TO
AI ENGINEERING
12
FOUNDATION
MODEL
USE CASES
16
CODING
20
IMAGE AND VIDEO
PRODUCTION
22
WRITING
22
EDUCATION
24
CONVERSATIONAL
BOTS
26
INFORMATION
AGGREGATION
26
DATA
ORGANIZATION
27
WORKFLOW
AUTOMATION
28
PLANNING
AI
APPLICATIONS
28
USE
CASE EVALUATION
29
SETTING
EXPECTATIONS
32
MILESTONE
PLANNING
33
MAINTENANCE
34
THE
AI ENGINEERING STACK
35
THREE
LAYERS OF THE
AI STACK
37
AI
ENGINEERING VERSUS
ML ENGINEERING
39
AI
ENGINEERING
VERSUS FULL-STACK
ENGINEERING
46
SUMMARY
47
V
2.
UNDERSTANDING
FOUNDATION MODELS
49
TRAINING
DATA
50
MULTILINGUAL MODELS
51
DOMAIN-SPECIFIC
MODELS
56
MODELING
58
MODEL ARCHITECTURE
58
MODEL SIZE
67
POST-TRAINING
78
SUPERVISED
FINETUNING
80
PREFERENCE FINETUNING
83
SAMPLING
88
SAMPLING
FUNDAMENTALS
88
SAMPLING
STRATEGIES
90
TEST
TIME COMPUTE
96
STRUCTURED
OUTPUTS
99
THE
PROBABILISTIC NATURE OF AI
105
SUMMARY
111
3.
EVALUATION
METHODOLOGY
113
CHALLENGES
OF EVALUATING FOUNDATION MODELS
114
UNDERSTANDING
LANGUAGE MODELING METRICS
118
ENTROPY
119
CROSS
ENTROPY
120
BITS-PER-CHARACTER
AND BITS-PER-BYTE
121
PERPLEXITY
121
PERPLEXITY
INTERPRETATION AND USE CASES
122
EXACT
EVALUATION
125
FUNCTIONAL
CORRECTNESS
126
SIMILARITY MEASUREMENTS AGAINST REFERENCE DATA
127
INTRODUCTION
TO EMBEDDING
134
AI
AS A JUDGE
136
WHY
AI AS A JUDGE?
137
HOW
TO USE AI AS A JUDGE
138
LIMITATIONS
OF AI AS A JUDGE
141
WHAT
MODELS CAN ACT
AS JUDGES?
145
RANKING MODELS
WITH COMPARATIVE EVALUATION
148
CHALLENGES
OF COMPARATIVE EVALUATION
152
THE
FUTURE OF COMPARATIVE
EVALUATION
155
SUMMARY
156
VI
I
TABLE
OF CONTENTS
4.
EVALUATE
AL SYSTEMS
159
EVALUATION
CRITERIA
160
DOMAIN-SPECIFIC
CAPABILITY
161
GENERATION
CAPABILITY
163
INSTRUCTION-FOLLOWING
CAPABILITY
172
COST
AND LATENCY
177
MODEL SELECTION
179
MODEL
SELECTION WORKFLOW
179
MODEL BUILD VERSUS
BUY
181
NAVIGATE
PUBLIC
BENCHMARKS
191
DESIGN
YOUR
EVALUATION PIPELINE
200
STEP
1. EVALUATE ALL COMPONENTS IN A SYSTEM
200
STEP
2.
CREATE AN EVALUATION GUIDELINE
202
STEP
3. DEFINE
EVALUATION METHODS AND DATA
204
SUMMARY
208
5.
PROMPT
ENGINEERING
211
INTRODUCTION
TO PROMPTING
212
IN-CONTEXT
LEARNING:
ZERO-SHOT AND FEW-SHOT
213
SYSTEM
PROMPT AND
USER PROMPT
215
CONTEXT
LENGTH AND CONTEXT EFFICIENCY
218
PROMPT
ENGINEERING BEST
PRACTICES
220
WRITE
CLEAR AND EXPLICIT INSTRUCTIONS
220
PROVIDE
SUFFICIENT CONTEXT
223
BREAK
COMPLEX
TASKS INTO SIMPLER SUBTASKS
224
GIVE
THE MODEL TIME TO THINK
227
ITERATE
ON YOUR PROMPTS
229
EVALUATE
PROMPT ENGINEERING TOOLS
230
ORGANIZE
AND VERSION
PROMPTS
233
DEFENSIVE
PROMPT ENGINEERING
235
PROPRIETARY
PROMPTS AND
REVERSE PROMPT ENGINEERING
236
JAILBREAKING
AND PROMPT INJECTION
238
INFORMATION
EXTRACTION
243
DEFENSES
AGAINST PROMPT ATTACKS
248
SUMMARY
251
6.
RAG
AND AGENTS
253
RAG
253
RAG
ARCHITECTURE
256
RETRIEVAL
ALGORITHMS
257
RETRIEVAL
OPTIMIZATION
268
TABLE
OF CONTENTS
I
VII
T
I
RAG
BEYOND
TEXTS
273
AGENTS
275
AGENT
OVERVIEW
276
TOOLS
278
PLANNING
281
AGENT
FAILURE
MODES AND
EVALUATION
298
MEMORY
300
SUMMARY
305
7.
FINETUNING
307
FINETUNING
OVERVIEW
308
WHEN
TO
FINETUNE
311
REASONS
TO FINETUNE
311
REASONS
NOT TO
FINETUNE
312
FINETUNING
AND RAG
316
MEMORY
BOTTLENECKS
319
BACKPROPAGATION
AND
TRAINABLE
PARAMETERS
320
MEMORY
MATH
322
NUMERICAL
REPRESENTATIONS
325
QUANTIZATION
328
FINETUNING
TECHNIQUES
332
PARAMETER-EFFICIENT
FINETUNING
333
MODEL
MERGING AND
MULTI-TASK
FINETUNING
347
FINETUNING
TACTICS
357
SUMMARY
361
8.
DATASET
ENGINEERING
363
DATA
CURATION
365
DATA
QUALITY
368
DATA COVERAGE
370
DATA
QUANTITY
372
DATA
ACQUISITION
AND
ANNOTATION
377
DATA
AUGMENTATION
AND
SYNTHESIS
380
WHY
DATA
SYNTHESIS
381
TRADITIONAL
DATA
SYNTHESIS
TECHNIQUES
383
AI-POWERED
DATA
SYNTHESIS
386
MODEL
DISTILLATION
395
DATA
PROCESSING
396
INSPECT
DATA
397
DEDUPLICATE DATA
399
CLEAN
AND FILTER
DATA
401
VIII
I
TABLE
OF
CONTENTS
FORMAT
DATA
401
SUMMARY
403
9.
INFERENCE
OPTIMIZATION
405
UNDERSTANDING
INFERENCE OPTIMIZATION
406
INFERENCE
OVERVIEW
406
INFERENCE
PERFORMANCE
METRICS
412
AI
ACCELERATORS
419
INFERENCE
OPTIMIZATION
426
MODEL OPTIMIZATION
426
INFERENCE
SERVICE OPTIMIZATION
440
SUMMARY
447
10.
AL ENGINEERING ARCHITECTURE
AND USER FEEDBACK
449
AI
ENGINEERING
ARCHITECTURE
449
STEP
1. ENHANCE
CONTEXT
450
STEP
2. PUT IN GUARDRAILS
451
STEP
3.
ADD MODEL ROUTER AND
GATEWAY
456
STEP
4. REDUCE LATENCY
WITH CACHES
460
STEP
5. ADD AGENT PATTERNS
463
MONITORING
AND OBSERVABILITY
465
AI
PIPELINE ORCHESTRATION
472
USER
FEEDBACK
474
EXTRACTING CONVERSATIONAL
FEEDBACK
475
FEEDBACK
DESIGN
480
FEEDBACK
LIMITATIONS
490
SUMMARY
492
EPILOGUE
495
INDEX
497
TABLE
OF CONTENTS
I
IX |
| any_adam_object | 1 |
| author | Huyen, Chip |
| author_GND | (DE-588)1261904311 |
| author_facet | Huyen, Chip |
| author_role | aut |
| author_sort | Huyen, Chip |
| author_variant | c h ch |
| building | Verbundindex |
| bvnumber | BV050100168 |
| classification_rvk | ST 300 |
| ctrlnum | (OCoLC)1492136105 (DE-599)BVBBV050100168 |
| discipline | Informatik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>00000nam a2200000 c 4500</leader><controlfield tag="001">BV050100168</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20250205</controlfield><controlfield tag="007">t|</controlfield><controlfield tag="008">241217s2025 xx a||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781098166304</subfield><subfield code="9">978-1-098-16630-4</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1492136105</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV050100168</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-473</subfield><subfield code="a">DE-Aug4</subfield><subfield code="a">DE-1050</subfield><subfield code="a">DE-29T</subfield><subfield code="a">DE-523</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 300</subfield><subfield code="0">(DE-625)143650:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Huyen, Chip</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1261904311</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">AI engineering</subfield><subfield code="b">building applications with foundation models</subfield><subfield code="c">Chip Huyen</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Sebastopol, CA</subfield><subfield code="b">O'Reilly</subfield><subfield code="c">[2025]</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xxi, 509 Seiten</subfield><subfield code="b">Illustrationen, Diagramme</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bicssc / Enterprise software</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bicssc / Operational research</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bicssc / Mathematical theory of computation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bicssc / Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bisacsh / COMPUTERS / Business & Productivity Software / Business Intelligence</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bisacsh / COMPUTERS / Machine Theory</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bisacsh / COMPUTERS / Data Science / Machine Learning</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Online-Ausgabe</subfield><subfield code="z">978-1-09-816627-4</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung Bibliothek HTW Berlin</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=035437329&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="943" ind1="1" ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-035437329</subfield></datafield></record></collection> |
| id | DE-604.BV050100168 |
| illustrated | Illustrated |
| indexdate | 2025-02-12T15:01:33Z |
| institution | BVB |
| isbn | 9781098166304 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-035437329 |
| oclc_num | 1492136105 |
| open_access_boolean | |
| owner | DE-473 DE-BY-UBG DE-Aug4 DE-1050 DE-29T DE-523 |
| owner_facet | DE-473 DE-BY-UBG DE-Aug4 DE-1050 DE-29T DE-523 |
| physical | xxi, 509 Seiten Illustrationen, Diagramme |
| publishDate | 2025 |
| publishDateSearch | 2025 |
| publishDateSort | 2025 |
| publisher | O'Reilly |
| record_format | marc |
| spelling | Huyen, Chip Verfasser (DE-588)1261904311 aut AI engineering building applications with foundation models Chip Huyen Sebastopol, CA O'Reilly [2025] xxi, 509 Seiten Illustrationen, Diagramme txt rdacontent n rdamedia nc rdacarrier bicssc / Enterprise software bicssc / Operational research bicssc / Mathematical theory of computation bicssc / Machine learning bisacsh / COMPUTERS / Business & Productivity Software / Business Intelligence bisacsh / COMPUTERS / Machine Theory bisacsh / COMPUTERS / Data Science / Machine Learning Erscheint auch als Online-Ausgabe 978-1-09-816627-4 Digitalisierung Bibliothek HTW Berlin application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=035437329&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Huyen, Chip AI engineering building applications with foundation models bicssc / Enterprise software bicssc / Operational research bicssc / Mathematical theory of computation bicssc / Machine learning bisacsh / COMPUTERS / Business & Productivity Software / Business Intelligence bisacsh / COMPUTERS / Machine Theory bisacsh / COMPUTERS / Data Science / Machine Learning |
| title | AI engineering building applications with foundation models |
| title_auth | AI engineering building applications with foundation models |
| title_exact_search | AI engineering building applications with foundation models |
| title_full | AI engineering building applications with foundation models Chip Huyen |
| title_fullStr | AI engineering building applications with foundation models Chip Huyen |
| title_full_unstemmed | AI engineering building applications with foundation models Chip Huyen |
| title_short | AI engineering |
| title_sort | ai engineering building applications with foundation models |
| title_sub | building applications with foundation models |
| topic | bicssc / Enterprise software bicssc / Operational research bicssc / Mathematical theory of computation bicssc / Machine learning bisacsh / COMPUTERS / Business & Productivity Software / Business Intelligence bisacsh / COMPUTERS / Machine Theory bisacsh / COMPUTERS / Data Science / Machine Learning |
| topic_facet | bicssc / Enterprise software bicssc / Operational research bicssc / Mathematical theory of computation bicssc / Machine learning bisacsh / COMPUTERS / Business & Productivity Software / Business Intelligence bisacsh / COMPUTERS / Machine Theory bisacsh / COMPUTERS / Data Science / Machine Learning |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=035437329&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT huyenchip aiengineeringbuildingapplicationswithfoundationmodels |