images.go 27.3 KB
Newer Older
mashun1's avatar
v1  
mashun1 committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
package server

import (
	"bytes"
	"cmp"
	"context"
	"crypto/sha256"
	"encoding/hex"
	"encoding/json"
	"errors"
	"fmt"
	"io"
	"log"
	"log/slog"
xuxzh1's avatar
update  
xuxzh1 committed
15
	"net"
mashun1's avatar
v1  
mashun1 committed
16
17
18
19
20
	"net/http"
	"net/url"
	"os"
	"path/filepath"
	"runtime"
xuxzh1's avatar
init  
xuxzh1 committed
21
	"slices"
mashun1's avatar
v1  
mashun1 committed
22
23
24
25
	"strconv"
	"strings"

	"github.com/ollama/ollama/api"
xuxzh1's avatar
init  
xuxzh1 committed
26
	"github.com/ollama/ollama/envconfig"
mashun1's avatar
v1  
mashun1 committed
27
	"github.com/ollama/ollama/format"
xuxzh1's avatar
update  
xuxzh1 committed
28
	"github.com/ollama/ollama/llama"
mashun1's avatar
v1  
mashun1 committed
29
30
	"github.com/ollama/ollama/llm"
	"github.com/ollama/ollama/parser"
xuxzh1's avatar
init  
xuxzh1 committed
31
	"github.com/ollama/ollama/template"
mashun1's avatar
v1  
mashun1 committed
32
33
34
35
	"github.com/ollama/ollama/types/model"
	"github.com/ollama/ollama/version"
)

xuxzh1's avatar
init  
xuxzh1 committed
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
var (
	errCapabilities         = errors.New("does not support")
	errCapabilityCompletion = errors.New("completion")
	errCapabilityTools      = errors.New("tools")
	errCapabilityInsert     = errors.New("insert")
)

type Capability string

const (
	CapabilityCompletion = Capability("completion")
	CapabilityTools      = Capability("tools")
	CapabilityInsert     = Capability("insert")
)

mashun1's avatar
v1  
mashun1 committed
51
52
53
54
55
type registryOptions struct {
	Insecure bool
	Username string
	Password string
	Token    string
xuxzh1's avatar
init  
xuxzh1 committed
56
57

	CheckRedirect func(req *http.Request, via []*http.Request) error
mashun1's avatar
v1  
mashun1 committed
58
59
60
61
62
63
64
65
66
67
68
69
70
71
}

type Model struct {
	Name           string `json:"name"`
	Config         ConfigV2
	ShortName      string
	ModelPath      string
	ParentModel    string
	AdapterPaths   []string
	ProjectorPaths []string
	System         string
	License        []string
	Digest         string
	Options        map[string]interface{}
xuxzh1's avatar
init  
xuxzh1 committed
72
73
74
	Messages       []api.Message

	Template *template.Template
mashun1's avatar
v1  
mashun1 committed
75
76
}

xuxzh1's avatar
init  
xuxzh1 committed
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
// CheckCapabilities checks if the model has the specified capabilities returning an error describing
// any missing or unknown capabilities
func (m *Model) CheckCapabilities(caps ...Capability) error {
	var errs []error
	for _, cap := range caps {
		switch cap {
		case CapabilityCompletion:
			f, err := os.Open(m.ModelPath)
			if err != nil {
				slog.Error("couldn't open model file", "error", err)
				continue
			}
			defer f.Close()

			// TODO(mxyng): decode the GGML into model to avoid doing this multiple times
			ggml, _, err := llm.DecodeGGML(f, 0)
			if err != nil {
				slog.Error("couldn't decode ggml", "error", err)
				continue
			}

			if _, ok := ggml.KV()[fmt.Sprintf("%s.pooling_type", ggml.KV().Architecture())]; ok {
				errs = append(errs, errCapabilityCompletion)
			}
		case CapabilityTools:
			if !slices.Contains(m.Template.Vars(), "tools") {
				errs = append(errs, errCapabilityTools)
			}
		case CapabilityInsert:
			vars := m.Template.Vars()
			if !slices.Contains(vars, "suffix") {
				errs = append(errs, errCapabilityInsert)
			}
		default:
			slog.Error("unknown capability", "capability", cap)
			return fmt.Errorf("unknown capability: %s", cap)
		}
	}

	if err := errors.Join(errs...); err != nil {
		return fmt.Errorf("%w %w", errCapabilities, errors.Join(errs...))
	}

	return nil
mashun1's avatar
v1  
mashun1 committed
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
}

func (m *Model) String() string {
	var modelfile parser.File

	modelfile.Commands = append(modelfile.Commands, parser.Command{
		Name: "model",
		Args: m.ModelPath,
	})

	for _, adapter := range m.AdapterPaths {
		modelfile.Commands = append(modelfile.Commands, parser.Command{
			Name: "adapter",
			Args: adapter,
		})
	}

	for _, projector := range m.ProjectorPaths {
		modelfile.Commands = append(modelfile.Commands, parser.Command{
			Name: "model",
			Args: projector,
		})
	}

xuxzh1's avatar
init  
xuxzh1 committed
145
	if m.Template != nil {
mashun1's avatar
v1  
mashun1 committed
146
147
		modelfile.Commands = append(modelfile.Commands, parser.Command{
			Name: "template",
xuxzh1's avatar
init  
xuxzh1 committed
148
			Args: m.Template.String(),
mashun1's avatar
v1  
mashun1 committed
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
		})
	}

	if m.System != "" {
		modelfile.Commands = append(modelfile.Commands, parser.Command{
			Name: "system",
			Args: m.System,
		})
	}

	for k, v := range m.Options {
		switch v := v.(type) {
		case []any:
			for _, s := range v {
				modelfile.Commands = append(modelfile.Commands, parser.Command{
					Name: k,
					Args: fmt.Sprintf("%v", s),
				})
			}
		default:
			modelfile.Commands = append(modelfile.Commands, parser.Command{
				Name: k,
				Args: fmt.Sprintf("%v", v),
			})
		}
	}

	for _, license := range m.License {
		modelfile.Commands = append(modelfile.Commands, parser.Command{
			Name: "license",
			Args: license,
		})
	}

	for _, msg := range m.Messages {
		modelfile.Commands = append(modelfile.Commands, parser.Command{
			Name: "message",
xuxzh1's avatar
init  
xuxzh1 committed
186
			Args: fmt.Sprintf("%s: %s", msg.Role, msg.Content),
mashun1's avatar
v1  
mashun1 committed
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
		})
	}

	return modelfile.String()
}

type ConfigV2 struct {
	ModelFormat   string   `json:"model_format"`
	ModelFamily   string   `json:"model_family"`
	ModelFamilies []string `json:"model_families"`
	ModelType     string   `json:"model_type"`
	FileType      string   `json:"file_type"`

	// required by spec
	Architecture string `json:"architecture"`
	OS           string `json:"os"`
	RootFS       RootFS `json:"rootfs"`
}

type RootFS struct {
	Type    string   `json:"type"`
	DiffIDs []string `json:"diff_ids"`
}

xuxzh1's avatar
init  
xuxzh1 committed
211
func GetManifest(mp ModelPath) (*Manifest, string, error) {
mashun1's avatar
v1  
mashun1 committed
212
213
214
215
216
	fp, err := mp.GetManifestPath()
	if err != nil {
		return nil, "", err
	}

xuxzh1's avatar
update  
xuxzh1 committed
217
	f, err := os.Open(fp)
mashun1's avatar
v1  
mashun1 committed
218
	if err != nil {
xuxzh1's avatar
update  
xuxzh1 committed
219
		return nil, "", err
mashun1's avatar
v1  
mashun1 committed
220
	}
xuxzh1's avatar
update  
xuxzh1 committed
221
	defer f.Close()
mashun1's avatar
v1  
mashun1 committed
222

xuxzh1's avatar
update  
xuxzh1 committed
223
	sha256sum := sha256.New()
mashun1's avatar
v1  
mashun1 committed
224

xuxzh1's avatar
update  
xuxzh1 committed
225
226
	var manifest Manifest
	if err := json.NewDecoder(io.TeeReader(f, sha256sum)).Decode(&manifest); err != nil {
mashun1's avatar
v1  
mashun1 committed
227
228
229
		return nil, "", err
	}

xuxzh1's avatar
update  
xuxzh1 committed
230
	return &manifest, hex.EncodeToString(sha256sum.Sum(nil)), nil
mashun1's avatar
v1  
mashun1 committed
231
232
233
234
235
236
237
238
239
240
241
242
243
}

func GetModel(name string) (*Model, error) {
	mp := ParseModelPath(name)
	manifest, digest, err := GetManifest(mp)
	if err != nil {
		return nil, err
	}

	model := &Model{
		Name:      mp.GetFullTagname(),
		ShortName: mp.GetShortTagname(),
		Digest:    digest,
xuxzh1's avatar
init  
xuxzh1 committed
244
		Template:  template.DefaultTemplate,
mashun1's avatar
v1  
mashun1 committed
245
246
	}

xuxzh1's avatar
init  
xuxzh1 committed
247
248
249
250
251
	if manifest.Config.Digest != "" {
		filename, err := GetBlobsPath(manifest.Config.Digest)
		if err != nil {
			return nil, err
		}
mashun1's avatar
v1  
mashun1 committed
252

xuxzh1's avatar
init  
xuxzh1 committed
253
254
255
256
257
		configFile, err := os.Open(filename)
		if err != nil {
			return nil, err
		}
		defer configFile.Close()
mashun1's avatar
v1  
mashun1 committed
258

xuxzh1's avatar
init  
xuxzh1 committed
259
260
261
		if err := json.NewDecoder(configFile).Decode(&model.Config); err != nil {
			return nil, err
		}
mashun1's avatar
v1  
mashun1 committed
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
	}

	for _, layer := range manifest.Layers {
		filename, err := GetBlobsPath(layer.Digest)
		if err != nil {
			return nil, err
		}

		switch layer.MediaType {
		case "application/vnd.ollama.image.model":
			model.ModelPath = filename
			model.ParentModel = layer.From
		case "application/vnd.ollama.image.embed":
			// Deprecated in versions  > 0.1.2
			// TODO: remove this warning in a future version
			slog.Info("WARNING: model contains embeddings, but embeddings in modelfiles have been deprecated and will be ignored.")
		case "application/vnd.ollama.image.adapter":
			model.AdapterPaths = append(model.AdapterPaths, filename)
		case "application/vnd.ollama.image.projector":
			model.ProjectorPaths = append(model.ProjectorPaths, filename)
xuxzh1's avatar
init  
xuxzh1 committed
282
283
		case "application/vnd.ollama.image.prompt",
			"application/vnd.ollama.image.template":
mashun1's avatar
v1  
mashun1 committed
284
285
286
287
288
			bts, err := os.ReadFile(filename)
			if err != nil {
				return nil, err
			}

xuxzh1's avatar
init  
xuxzh1 committed
289
			model.Template, err = template.Parse(string(bts))
mashun1's avatar
v1  
mashun1 committed
290
291
292
			if err != nil {
				return nil, err
			}
xuxzh1's avatar
init  
xuxzh1 committed
293
		case "application/vnd.ollama.image.system":
mashun1's avatar
v1  
mashun1 committed
294
295
296
297
298
			bts, err := os.ReadFile(filename)
			if err != nil {
				return nil, err
			}

xuxzh1's avatar
init  
xuxzh1 committed
299
			model.System = string(bts)
mashun1's avatar
v1  
mashun1 committed
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
		case "application/vnd.ollama.image.params":
			params, err := os.Open(filename)
			if err != nil {
				return nil, err
			}
			defer params.Close()

			// parse model options parameters into a map so that we can see which fields have been specified explicitly
			if err = json.NewDecoder(params).Decode(&model.Options); err != nil {
				return nil, err
			}
		case "application/vnd.ollama.image.messages":
			msgs, err := os.Open(filename)
			if err != nil {
				return nil, err
			}
			defer msgs.Close()

			if err = json.NewDecoder(msgs).Decode(&model.Messages); err != nil {
				return nil, err
			}
		case "application/vnd.ollama.image.license":
			bts, err := os.ReadFile(filename)
			if err != nil {
				return nil, err
			}
			model.License = append(model.License, string(bts))
		}
	}

	return model, nil
}

func realpath(rel, from string) string {
	abspath, err := filepath.Abs(from)
	if err != nil {
		return from
	}

	home, err := os.UserHomeDir()
	if err != nil {
		return abspath
	}

	if from == "~" {
		return home
	} else if strings.HasPrefix(from, "~/") {
		return filepath.Join(home, from[2:])
	}

	if _, err := os.Stat(filepath.Join(rel, from)); err == nil {
		// this is a file relative to the Modelfile
		return filepath.Join(rel, from)
	}

	return abspath
}

xuxzh1's avatar
init  
xuxzh1 committed
358
func CreateModel(ctx context.Context, name model.Name, modelFileDir, quantization string, modelfile *parser.File, fn func(resp api.ProgressResponse)) (err error) {
mashun1's avatar
v1  
mashun1 committed
359
360
361
362
363
364
365
366
367
368
369
	config := ConfigV2{
		OS:           "linux",
		Architecture: "amd64",
		RootFS: RootFS{
			Type: "layers",
		},
	}

	var messages []*api.Message
	parameters := make(map[string]any)

xuxzh1's avatar
init  
xuxzh1 committed
370
	var layers []Layer
xuxzh1's avatar
update  
xuxzh1 committed
371
	var baseLayers []*layerGGML
mashun1's avatar
v1  
mashun1 committed
372
373
	for _, c := range modelfile.Commands {
		mediatype := fmt.Sprintf("application/vnd.ollama.image.%s", c.Name)
xuxzh1's avatar
update  
xuxzh1 committed
374
		command := c.Name
mashun1's avatar
v1  
mashun1 committed
375

xuxzh1's avatar
update  
xuxzh1 committed
376
		switch command {
mashun1's avatar
v1  
mashun1 committed
377
		case "model", "adapter":
xuxzh1's avatar
update  
xuxzh1 committed
378
			if name := model.ParseName(c.Args); name.IsValid() && command == "model" {
mashun1's avatar
v1  
mashun1 committed
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
				baseLayers, err = parseFromModel(ctx, name, fn)
				if err != nil {
					return err
				}
			} else if strings.HasPrefix(c.Args, "@") {
				digest := strings.TrimPrefix(c.Args, "@")
				if ib, ok := intermediateBlobs[digest]; ok {
					p, err := GetBlobsPath(ib)
					if err != nil {
						return err
					}

					if _, err := os.Stat(p); errors.Is(err, os.ErrNotExist) {
						// pass
					} else if err != nil {
						return err
					} else {
						fn(api.ProgressResponse{Status: fmt.Sprintf("using cached layer %s", ib)})
						digest = ib
					}
				}

				blobpath, err := GetBlobsPath(digest)
				if err != nil {
					return err
				}

				blob, err := os.Open(blobpath)
				if err != nil {
					return err
				}
				defer blob.Close()

xuxzh1's avatar
update  
xuxzh1 committed
412
				baseLayers, err = parseFromFile(ctx, command, baseLayers, blob, digest, fn)
mashun1's avatar
v1  
mashun1 committed
413
414
415
416
417
418
				if err != nil {
					return err
				}
			} else if file, err := os.Open(realpath(modelFileDir, c.Args)); err == nil {
				defer file.Close()

xuxzh1's avatar
update  
xuxzh1 committed
419
				baseLayers, err = parseFromFile(ctx, command, baseLayers, file, "", fn)
mashun1's avatar
v1  
mashun1 committed
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
				if err != nil {
					return err
				}
			} else {
				return fmt.Errorf("invalid model reference: %s", c.Args)
			}

			for _, baseLayer := range baseLayers {
				if quantization != "" &&
					baseLayer.MediaType == "application/vnd.ollama.image.model" &&
					baseLayer.GGML != nil &&
					baseLayer.GGML.Name() == "gguf" {
					want, err := llm.ParseFileType(quantization)
					if err != nil {
						return err
					}

					ft := baseLayer.GGML.KV().FileType()
					if !slices.Contains([]string{"F16", "F32"}, ft.String()) {
						return errors.New("quantization is only supported for F16 and F32 models")
					} else if want != ft {
						fn(api.ProgressResponse{Status: fmt.Sprintf("quantizing %s model to %s", ft, quantization)})

						blob, err := GetBlobsPath(baseLayer.Digest)
						if err != nil {
							return err
						}

						temp, err := os.CreateTemp(filepath.Dir(blob), quantization)
						if err != nil {
							return err
						}
						defer temp.Close()
						defer os.Remove(temp.Name())

xuxzh1's avatar
update  
xuxzh1 committed
455
						if err := llama.Quantize(blob, temp.Name(), uint32(want)); err != nil {
mashun1's avatar
v1  
mashun1 committed
456
457
458
							return err
						}

xuxzh1's avatar
init  
xuxzh1 committed
459
						layer, err := NewLayer(temp, baseLayer.MediaType)
mashun1's avatar
v1  
mashun1 committed
460
461
462
463
						if err != nil {
							return err
						}

xuxzh1's avatar
init  
xuxzh1 committed
464
465
466
467
468
469
470
						if _, err := temp.Seek(0, io.SeekStart); err != nil {
							return err
						}

						ggml, _, err := llm.DecodeGGML(temp, 0)
						if err != nil {
							return err
mashun1's avatar
v1  
mashun1 committed
471
472
						}

xuxzh1's avatar
init  
xuxzh1 committed
473
474
						baseLayer.Layer = layer
						baseLayer.GGML = ggml
mashun1's avatar
v1  
mashun1 committed
475
476
477
478
479
480
481
482
483
484
485
486
487
488
					}
				}

				if baseLayer.GGML != nil {
					config.ModelFormat = cmp.Or(config.ModelFormat, baseLayer.GGML.Name())
					config.ModelFamily = cmp.Or(config.ModelFamily, baseLayer.GGML.KV().Architecture())
					config.ModelType = cmp.Or(config.ModelType, format.HumanNumber(baseLayer.GGML.KV().ParameterCount()))
					config.FileType = cmp.Or(config.FileType, baseLayer.GGML.KV().FileType().String())
					config.ModelFamilies = append(config.ModelFamilies, baseLayer.GGML.KV().Architecture())
				}

				layers = append(layers, baseLayer.Layer)
			}
		case "license", "template", "system":
xuxzh1's avatar
init  
xuxzh1 committed
489
490
491
492
			if c.Name == "template" {
				if _, err := template.Parse(c.Args); err != nil {
					return fmt.Errorf("%w: %s", errBadTemplate, err)
				}
mashun1's avatar
v1  
mashun1 committed
493
494
495
496
			}

			if c.Name != "license" {
				// replace
xuxzh1's avatar
init  
xuxzh1 committed
497
498
499
500
501
502
503
504
505
506
				layers = slices.DeleteFunc(layers, func(layer Layer) bool {
					if layer.MediaType != mediatype {
						return false
					}

					if err := layer.Remove(); err != nil {
						return false
					}

					return true
mashun1's avatar
v1  
mashun1 committed
507
508
509
				})
			}

xuxzh1's avatar
init  
xuxzh1 committed
510
511
512
513
514
515
			blob := strings.NewReader(c.Args)
			layer, err := NewLayer(blob, mediatype)
			if err != nil {
				return err
			}

mashun1's avatar
v1  
mashun1 committed
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
			layers = append(layers, layer)
		case "message":
			role, content, ok := strings.Cut(c.Args, ": ")
			if !ok {
				return fmt.Errorf("invalid message: %s", c.Args)
			}

			messages = append(messages, &api.Message{Role: role, Content: content})
		default:
			ps, err := api.FormatParams(map[string][]string{c.Name: {c.Args}})
			if err != nil {
				return err
			}

			for k, v := range ps {
				if ks, ok := parameters[k].([]string); ok {
					parameters[k] = append(ks, v.([]string)...)
				} else if vs, ok := v.([]string); ok {
					parameters[k] = vs
				} else {
					parameters[k] = v
				}
			}
		}
	}

	var err2 error
xuxzh1's avatar
init  
xuxzh1 committed
543
	layers = slices.DeleteFunc(layers, func(layer Layer) bool {
mashun1's avatar
v1  
mashun1 committed
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
		switch layer.MediaType {
		case "application/vnd.ollama.image.message":
			// if there are new messages, remove the inherited ones
			if len(messages) > 0 {
				return true
			}

			return false
		case "application/vnd.ollama.image.params":
			// merge inherited parameters with new ones
			r, err := layer.Open()
			if err != nil {
				err2 = err
				return false
			}
			defer r.Close()

			var ps map[string]any
			if err := json.NewDecoder(r).Decode(&ps); err != nil {
				err2 = err
				return false
			}

			for k, v := range ps {
				if _, ok := parameters[k]; !ok {
					parameters[k] = v
				}
			}

			return true
		default:
			return false
		}
	})

	if err2 != nil {
		return err2
	}

	if len(messages) > 0 {
		var b bytes.Buffer
		if err := json.NewEncoder(&b).Encode(messages); err != nil {
			return err
		}

		layer, err := NewLayer(&b, "application/vnd.ollama.image.messages")
		if err != nil {
			return err
		}

		layers = append(layers, layer)
	}

	if len(parameters) > 0 {
		var b bytes.Buffer
		if err := json.NewEncoder(&b).Encode(parameters); err != nil {
			return err
		}

		layer, err := NewLayer(&b, "application/vnd.ollama.image.params")
		if err != nil {
			return err
		}

		layers = append(layers, layer)
	}

	digests := make([]string, len(layers))
	for i, layer := range layers {
		digests[i] = layer.Digest
	}

	config.RootFS.DiffIDs = digests

	var b bytes.Buffer
	if err := json.NewEncoder(&b).Encode(config); err != nil {
		return err
	}

xuxzh1's avatar
init  
xuxzh1 committed
623
	configLayer, err := NewLayer(&b, "application/vnd.docker.container.image.v1+json")
mashun1's avatar
v1  
mashun1 committed
624
625
626
627
	if err != nil {
		return err
	}

xuxzh1's avatar
init  
xuxzh1 committed
628
	for _, layer := range append(layers, configLayer) {
mashun1's avatar
v1  
mashun1 committed
629
630
631
632
633
		if layer.status != "" {
			fn(api.ProgressResponse{Status: layer.status})
		}
	}

xuxzh1's avatar
init  
xuxzh1 committed
634
	old, _ := ParseNamedManifest(name)
mashun1's avatar
v1  
mashun1 committed
635
636

	fn(api.ProgressResponse{Status: "writing manifest"})
xuxzh1's avatar
init  
xuxzh1 committed
637
	if err := WriteManifest(name, configLayer, layers); err != nil {
mashun1's avatar
v1  
mashun1 committed
638
639
640
		return err
	}

xuxzh1's avatar
init  
xuxzh1 committed
641
642
	if !envconfig.NoPrune() && old != nil {
		if err := old.RemoveLayers(); err != nil {
mashun1's avatar
v1  
mashun1 committed
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
			return err
		}
	}

	fn(api.ProgressResponse{Status: "success"})
	return nil
}

func CopyModel(src, dst model.Name) error {
	if !dst.IsFullyQualified() {
		return model.Unqualified(dst)
	}
	if !src.IsFullyQualified() {
		return model.Unqualified(src)
	}

	if src.Filepath() == dst.Filepath() {
		return nil
	}

	manifests, err := GetManifestPath()
	if err != nil {
		return err
	}

	dstpath := filepath.Join(manifests, dst.Filepath())
	if err := os.MkdirAll(filepath.Dir(dstpath), 0o755); err != nil {
		return err
	}

	srcpath := filepath.Join(manifests, src.Filepath())
	srcfile, err := os.Open(srcpath)
	if err != nil {
		return err
	}
	defer srcfile.Close()

	dstfile, err := os.Create(dstpath)
	if err != nil {
		return err
	}
	defer dstfile.Close()

	_, err = io.Copy(dstfile, srcfile)
	return err
}

xuxzh1's avatar
update  
xuxzh1 committed
690
691
692
func deleteUnusedLayers(deleteMap map[string]struct{}) error {
	// Ignore corrupt manifests to avoid blocking deletion of layers that are freshly orphaned
	manifests, err := Manifests(true)
mashun1's avatar
v1  
mashun1 committed
693
694
695
696
	if err != nil {
		return err
	}

xuxzh1's avatar
update  
xuxzh1 committed
697
	for _, manifest := range manifests {
mashun1's avatar
v1  
mashun1 committed
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
		for _, layer := range manifest.Layers {
			delete(deleteMap, layer.Digest)
		}

		delete(deleteMap, manifest.Config.Digest)
	}

	// only delete the files which are still in the deleteMap
	for k := range deleteMap {
		fp, err := GetBlobsPath(k)
		if err != nil {
			slog.Info(fmt.Sprintf("couldn't get file path for '%s': %v", k, err))
			continue
		}
		if err := os.Remove(fp); err != nil {
			slog.Info(fmt.Sprintf("couldn't remove file '%s': %v", fp, err))
			continue
		}
	}

	return nil
}

func PruneLayers() error {
	deleteMap := make(map[string]struct{})
	p, err := GetBlobsPath("")
	if err != nil {
		return err
	}

	blobs, err := os.ReadDir(p)
	if err != nil {
		slog.Info(fmt.Sprintf("couldn't read dir '%s': %v", p, err))
		return err
	}

	for _, blob := range blobs {
		name := blob.Name()
		name = strings.ReplaceAll(name, "-", ":")

		_, err := GetBlobsPath(name)
		if err != nil {
			if errors.Is(err, ErrInvalidDigestFormat) {
				// remove invalid blobs (e.g. partial downloads)
				if err := os.Remove(filepath.Join(p, blob.Name())); err != nil {
					slog.Error("couldn't remove blob", "blob", blob.Name(), "error", err)
				}
			}

			continue
		}

		deleteMap[name] = struct{}{}
	}

	slog.Info(fmt.Sprintf("total blobs: %d", len(deleteMap)))

xuxzh1's avatar
update  
xuxzh1 committed
755
	if err := deleteUnusedLayers(deleteMap); err != nil {
xuxzh1's avatar
init  
xuxzh1 committed
756
757
		slog.Error(fmt.Sprintf("couldn't remove unused layers: %v", err))
		return nil
mashun1's avatar
v1  
mashun1 committed
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
	}

	slog.Info(fmt.Sprintf("total unused blobs removed: %d", len(deleteMap)))

	return nil
}

func PruneDirectory(path string) error {
	info, err := os.Lstat(path)
	if err != nil {
		return err
	}

	if info.IsDir() && info.Mode()&os.ModeSymlink == 0 {
		entries, err := os.ReadDir(path)
		if err != nil {
			return err
		}

		for _, entry := range entries {
			if err := PruneDirectory(filepath.Join(path, entry.Name())); err != nil {
				return err
			}
		}

		entries, err = os.ReadDir(path)
		if err != nil {
			return err
		}

		if len(entries) > 0 {
			return nil
		}

		return os.Remove(path)
	}

	return nil
}

func PushModel(ctx context.Context, name string, regOpts *registryOptions, fn func(api.ProgressResponse)) error {
	mp := ParseModelPath(name)
	fn(api.ProgressResponse{Status: "retrieving manifest"})

	if mp.ProtocolScheme == "http" && !regOpts.Insecure {
xuxzh1's avatar
init  
xuxzh1 committed
803
		return errors.New("insecure protocol http")
mashun1's avatar
v1  
mashun1 committed
804
805
806
807
808
809
810
811
	}

	manifest, _, err := GetManifest(mp)
	if err != nil {
		fn(api.ProgressResponse{Status: "couldn't retrieve manifest"})
		return err
	}

xuxzh1's avatar
init  
xuxzh1 committed
812
	var layers []Layer
mashun1's avatar
v1  
mashun1 committed
813
	layers = append(layers, manifest.Layers...)
xuxzh1's avatar
init  
xuxzh1 committed
814
815
816
	if manifest.Config.Digest != "" {
		layers = append(layers, manifest.Config)
	}
mashun1's avatar
v1  
mashun1 committed
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851

	for _, layer := range layers {
		if err := uploadBlob(ctx, mp, layer, regOpts, fn); err != nil {
			slog.Info(fmt.Sprintf("error uploading blob: %v", err))
			return err
		}
	}

	fn(api.ProgressResponse{Status: "pushing manifest"})
	requestURL := mp.BaseURL()
	requestURL = requestURL.JoinPath("v2", mp.GetNamespaceRepository(), "manifests", mp.Tag)

	manifestJSON, err := json.Marshal(manifest)
	if err != nil {
		return err
	}

	headers := make(http.Header)
	headers.Set("Content-Type", "application/vnd.docker.distribution.manifest.v2+json")
	resp, err := makeRequestWithRetry(ctx, http.MethodPut, requestURL, headers, bytes.NewReader(manifestJSON), regOpts)
	if err != nil {
		return err
	}
	defer resp.Body.Close()

	fn(api.ProgressResponse{Status: "success"})

	return nil
}

func PullModel(ctx context.Context, name string, regOpts *registryOptions, fn func(api.ProgressResponse)) error {
	mp := ParseModelPath(name)

	// build deleteMap to prune unused layers
	deleteMap := make(map[string]struct{})
xuxzh1's avatar
update  
xuxzh1 committed
852
853
854
855
856
857
858
859
	manifest, _, err := GetManifest(mp)
	if errors.Is(err, os.ErrNotExist) {
		// noop
	} else if err != nil {
		slog.Warn("pulling model with bad existing manifest", "name", name, "error", err)
	} else {
		for _, l := range manifest.Layers {
			deleteMap[l.Digest] = struct{}{}
mashun1's avatar
v1  
mashun1 committed
860
		}
xuxzh1's avatar
update  
xuxzh1 committed
861
862
		if manifest.Config.Digest != "" {
			deleteMap[manifest.Config.Digest] = struct{}{}
mashun1's avatar
v1  
mashun1 committed
863
864
865
866
		}
	}

	if mp.ProtocolScheme == "http" && !regOpts.Insecure {
xuxzh1's avatar
init  
xuxzh1 committed
867
		return errors.New("insecure protocol http")
mashun1's avatar
v1  
mashun1 committed
868
869
870
871
872
873
874
875
876
	}

	fn(api.ProgressResponse{Status: "pulling manifest"})

	manifest, err = pullModelManifest(ctx, mp, regOpts)
	if err != nil {
		return fmt.Errorf("pull model manifest: %s", err)
	}

xuxzh1's avatar
init  
xuxzh1 committed
877
	var layers []Layer
mashun1's avatar
v1  
mashun1 committed
878
	layers = append(layers, manifest.Layers...)
xuxzh1's avatar
init  
xuxzh1 committed
879
880
881
	if manifest.Config.Digest != "" {
		layers = append(layers, manifest.Config)
	}
mashun1's avatar
v1  
mashun1 committed
882

xuxzh1's avatar
init  
xuxzh1 committed
883
	skipVerify := make(map[string]bool)
mashun1's avatar
v1  
mashun1 committed
884
	for _, layer := range layers {
xuxzh1's avatar
init  
xuxzh1 committed
885
886
887
888
889
890
891
		cacheHit, err := downloadBlob(ctx, downloadOpts{
			mp:      mp,
			digest:  layer.Digest,
			regOpts: regOpts,
			fn:      fn,
		})
		if err != nil {
mashun1's avatar
v1  
mashun1 committed
892
893
			return err
		}
xuxzh1's avatar
init  
xuxzh1 committed
894
		skipVerify[layer.Digest] = cacheHit
mashun1's avatar
v1  
mashun1 committed
895
896
897
898
899
900
		delete(deleteMap, layer.Digest)
	}
	delete(deleteMap, manifest.Config.Digest)

	fn(api.ProgressResponse{Status: "verifying sha256 digest"})
	for _, layer := range layers {
xuxzh1's avatar
init  
xuxzh1 committed
901
902
903
		if skipVerify[layer.Digest] {
			continue
		}
mashun1's avatar
v1  
mashun1 committed
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
		if err := verifyBlob(layer.Digest); err != nil {
			if errors.Is(err, errDigestMismatch) {
				// something went wrong, delete the blob
				fp, err := GetBlobsPath(layer.Digest)
				if err != nil {
					return err
				}
				if err := os.Remove(fp); err != nil {
					// log this, but return the original error
					slog.Info(fmt.Sprintf("couldn't remove file with digest mismatch '%s': %v", fp, err))
				}
			}
			return err
		}
	}

	fn(api.ProgressResponse{Status: "writing manifest"})

	manifestJSON, err := json.Marshal(manifest)
	if err != nil {
		return err
	}

	fp, err := mp.GetManifestPath()
	if err != nil {
		return err
	}
	if err := os.MkdirAll(filepath.Dir(fp), 0o755); err != nil {
		return err
	}

	err = os.WriteFile(fp, manifestJSON, 0o644)
	if err != nil {
		slog.Info(fmt.Sprintf("couldn't write to %s", fp))
		return err
	}

xuxzh1's avatar
update  
xuxzh1 committed
941
942
943
	if !envconfig.NoPrune() && len(deleteMap) > 0 {
		fn(api.ProgressResponse{Status: "removing unused layers"})
		if err := deleteUnusedLayers(deleteMap); err != nil {
xuxzh1's avatar
init  
xuxzh1 committed
944
			fn(api.ProgressResponse{Status: fmt.Sprintf("couldn't remove unused layers: %v", err)})
mashun1's avatar
v1  
mashun1 committed
945
946
947
948
949
950
951
952
		}
	}

	fn(api.ProgressResponse{Status: "success"})

	return nil
}

xuxzh1's avatar
init  
xuxzh1 committed
953
func pullModelManifest(ctx context.Context, mp ModelPath, regOpts *registryOptions) (*Manifest, error) {
mashun1's avatar
v1  
mashun1 committed
954
955
956
957
958
959
960
961
962
963
	requestURL := mp.BaseURL().JoinPath("v2", mp.GetNamespaceRepository(), "manifests", mp.Tag)

	headers := make(http.Header)
	headers.Set("Accept", "application/vnd.docker.distribution.manifest.v2+json")
	resp, err := makeRequestWithRetry(ctx, http.MethodGet, requestURL, headers, nil, regOpts)
	if err != nil {
		return nil, err
	}
	defer resp.Body.Close()

xuxzh1's avatar
update  
xuxzh1 committed
964
	var m Manifest
mashun1's avatar
v1  
mashun1 committed
965
966
967
968
	if err := json.NewDecoder(resp.Body).Decode(&m); err != nil {
		return nil, err
	}

xuxzh1's avatar
update  
xuxzh1 committed
969
	return &m, err
mashun1's avatar
v1  
mashun1 committed
970
971
972
973
974
975
976
977
978
979
980
981
982
}

// GetSHA256Digest returns the SHA256 hash of a given buffer and returns it, and the size of buffer
func GetSHA256Digest(r io.Reader) (string, int64) {
	h := sha256.New()
	n, err := io.Copy(h, r)
	if err != nil {
		log.Fatal(err)
	}

	return fmt.Sprintf("sha256:%x", h.Sum(nil)), n
}

xuxzh1's avatar
init  
xuxzh1 committed
983
var errUnauthorized = errors.New("unauthorized: access denied")
mashun1's avatar
v1  
mashun1 committed
984
985

func makeRequestWithRetry(ctx context.Context, method string, requestURL *url.URL, headers http.Header, body io.ReadSeeker, regOpts *registryOptions) (*http.Response, error) {
xuxzh1's avatar
init  
xuxzh1 committed
986
	for range 2 {
mashun1's avatar
v1  
mashun1 committed
987
988
989
990
991
992
993
994
995
996
997
		resp, err := makeRequest(ctx, method, requestURL, headers, body, regOpts)
		if err != nil {
			if !errors.Is(err, context.Canceled) {
				slog.Info(fmt.Sprintf("request failed: %v", err))
			}

			return nil, err
		}

		switch {
		case resp.StatusCode == http.StatusUnauthorized:
xuxzh1's avatar
update  
xuxzh1 committed
998
999
			resp.Body.Close()

mashun1's avatar
v1  
mashun1 committed
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
			// Handle authentication error with one retry
			challenge := parseRegistryChallenge(resp.Header.Get("www-authenticate"))
			token, err := getAuthorizationToken(ctx, challenge)
			if err != nil {
				return nil, err
			}
			regOpts.Token = token
			if body != nil {
				_, err = body.Seek(0, io.SeekStart)
				if err != nil {
					return nil, err
				}
			}
		case resp.StatusCode == http.StatusNotFound:
xuxzh1's avatar
update  
xuxzh1 committed
1014
			resp.Body.Close()
mashun1's avatar
v1  
mashun1 committed
1015
1016
			return nil, os.ErrNotExist
		case resp.StatusCode >= http.StatusBadRequest:
xuxzh1's avatar
update  
xuxzh1 committed
1017
			defer resp.Body.Close()
mashun1's avatar
v1  
mashun1 committed
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
			responseBody, err := io.ReadAll(resp.Body)
			if err != nil {
				return nil, fmt.Errorf("%d: %s", resp.StatusCode, err)
			}
			return nil, fmt.Errorf("%d: %s", resp.StatusCode, responseBody)
		default:
			return resp, nil
		}
	}

	return nil, errUnauthorized
}

xuxzh1's avatar
update  
xuxzh1 committed
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
// testMakeRequestDialContext specifies the dial function for the http client in
// makeRequest. It can be used to resolve hosts in model names to local
// addresses for testing. For example, the model name ("example.com/my/model")
// can be directed to push/pull from "127.0.0.1:1234".
//
// This is not safe to set across goroutines. It should be set in
// the main test goroutine, and not by tests marked to run in parallel with
// t.Parallel().
//
// It should be cleared after use, otherwise it will affect other tests.
//
// Ideally we would have some set this up the stack, but the code is not
// structured in a way that makes this easy, so this will have to do for now.
var testMakeRequestDialContext func(ctx context.Context, network, addr string) (net.Conn, error)

mashun1's avatar
v1  
mashun1 committed
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
func makeRequest(ctx context.Context, method string, requestURL *url.URL, headers http.Header, body io.Reader, regOpts *registryOptions) (*http.Response, error) {
	if requestURL.Scheme != "http" && regOpts != nil && regOpts.Insecure {
		requestURL.Scheme = "http"
	}

	req, err := http.NewRequestWithContext(ctx, method, requestURL.String(), body)
	if err != nil {
		return nil, err
	}

	if headers != nil {
		req.Header = headers
	}

	if regOpts != nil {
		if regOpts.Token != "" {
			req.Header.Set("Authorization", "Bearer "+regOpts.Token)
		} else if regOpts.Username != "" && regOpts.Password != "" {
			req.SetBasicAuth(regOpts.Username, regOpts.Password)
		}
	}

	req.Header.Set("User-Agent", fmt.Sprintf("ollama/%s (%s %s) Go/%s", version.Version, runtime.GOARCH, runtime.GOOS, runtime.Version()))

	if s := req.Header.Get("Content-Length"); s != "" {
		contentLength, err := strconv.ParseInt(s, 10, 64)
		if err != nil {
			return nil, err
		}

		req.ContentLength = contentLength
	}

xuxzh1's avatar
update  
xuxzh1 committed
1079
	c := &http.Client{
xuxzh1's avatar
init  
xuxzh1 committed
1080
		CheckRedirect: regOpts.CheckRedirect,
mashun1's avatar
v1  
mashun1 committed
1081
	}
xuxzh1's avatar
update  
xuxzh1 committed
1082
1083
1084
1085
1086
1087
	if testMakeRequestDialContext != nil {
		tr := http.DefaultTransport.(*http.Transport).Clone()
		tr.DialContext = testMakeRequestDialContext
		c.Transport = tr
	}
	return c.Do(req)
mashun1's avatar
v1  
mashun1 committed
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
}

func getValue(header, key string) string {
	startIdx := strings.Index(header, key+"=")
	if startIdx == -1 {
		return ""
	}

	// Move the index to the starting quote after the key.
	startIdx += len(key) + 2
	endIdx := startIdx

	for endIdx < len(header) {
		if header[endIdx] == '"' {
			if endIdx+1 < len(header) && header[endIdx+1] != ',' { // If the next character isn't a comma, continue
				endIdx++
				continue
			}
			break
		}
		endIdx++
	}
	return header[startIdx:endIdx]
}

func parseRegistryChallenge(authStr string) registryChallenge {
	authStr = strings.TrimPrefix(authStr, "Bearer ")

	return registryChallenge{
		Realm:   getValue(authStr, "realm"),
		Service: getValue(authStr, "service"),
		Scope:   getValue(authStr, "scope"),
	}
}

var errDigestMismatch = errors.New("digest mismatch, file must be downloaded again")

func verifyBlob(digest string) error {
	fp, err := GetBlobsPath(digest)
	if err != nil {
		return err
	}

	f, err := os.Open(fp)
	if err != nil {
		return err
	}
	defer f.Close()

	fileDigest, _ := GetSHA256Digest(f)
	if digest != fileDigest {
		return fmt.Errorf("%w: want %s, got %s", errDigestMismatch, digest, fileDigest)
	}

	return nil
}