@workglow/ai-provider 0.0.52
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +201 -0
- package/README.md +488 -0
- package/dist/ggml/model/GgmlLocalModel.d.ts +7 -0
- package/dist/ggml/model/GgmlLocalModel.d.ts.map +1 -0
- package/dist/ggml/server.d.ts +2 -0
- package/dist/ggml/server.d.ts.map +1 -0
- package/dist/hf-transformers/common/HFT_CallbackStatus.d.ts +36 -0
- package/dist/hf-transformers/common/HFT_CallbackStatus.d.ts.map +1 -0
- package/dist/hf-transformers/common/HFT_Constants.d.ts +18 -0
- package/dist/hf-transformers/common/HFT_Constants.d.ts.map +1 -0
- package/dist/hf-transformers/common/HFT_JobRunFns.d.ts +45 -0
- package/dist/hf-transformers/common/HFT_JobRunFns.d.ts.map +1 -0
- package/dist/hf-transformers/index.d.ts +11 -0
- package/dist/hf-transformers/index.d.ts.map +1 -0
- package/dist/hf-transformers/registry/HFT_Client_RegisterJobFns.d.ts +7 -0
- package/dist/hf-transformers/registry/HFT_Client_RegisterJobFns.d.ts.map +1 -0
- package/dist/hf-transformers/registry/HFT_Inline_RegisterJobFns.d.ts +7 -0
- package/dist/hf-transformers/registry/HFT_Inline_RegisterJobFns.d.ts.map +1 -0
- package/dist/hf-transformers/registry/HFT_Worker_RegisterJobFns.d.ts +8 -0
- package/dist/hf-transformers/registry/HFT_Worker_RegisterJobFns.d.ts.map +1 -0
- package/dist/index.d.ts +3 -0
- package/dist/index.d.ts.map +1 -0
- package/dist/index.js +342 -0
- package/dist/index.js.map +19 -0
- package/dist/openai/provider/OpenAI_TaskRun.d.ts +2 -0
- package/dist/openai/provider/OpenAI_TaskRun.d.ts.map +1 -0
- package/dist/tf-mediapipe/common/TFMP_Constants.d.ts +7 -0
- package/dist/tf-mediapipe/common/TFMP_Constants.d.ts.map +1 -0
- package/dist/tf-mediapipe/common/TFMP_JobRunFns.d.ts +17 -0
- package/dist/tf-mediapipe/common/TFMP_JobRunFns.d.ts.map +1 -0
- package/dist/tf-mediapipe/index.d.ts +11 -0
- package/dist/tf-mediapipe/index.d.ts.map +1 -0
- package/dist/tf-mediapipe/registry/TFMP_Client_RegisterJobFns.d.ts +7 -0
- package/dist/tf-mediapipe/registry/TFMP_Client_RegisterJobFns.d.ts.map +1 -0
- package/dist/tf-mediapipe/registry/TFMP_Inline_RegisterJobFns.d.ts +7 -0
- package/dist/tf-mediapipe/registry/TFMP_Inline_RegisterJobFns.d.ts.map +1 -0
- package/dist/tf-mediapipe/registry/TFMP_Worker_RegisterJobFns.d.ts +8 -0
- package/dist/tf-mediapipe/registry/TFMP_Worker_RegisterJobFns.d.ts.map +1 -0
- package/dist/types.d.ts +7 -0
- package/dist/types.d.ts.map +1 -0
- package/package.json +67 -0
package/LICENSE
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright 2025 Steven Roussey
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|
package/README.md
ADDED
|
@@ -0,0 +1,488 @@
|
|
|
1
|
+
# @workglow/ai-provider
|
|
2
|
+
|
|
3
|
+
AI provider implementations for Workglow AI task pipelines.
|
|
4
|
+
|
|
5
|
+
## Overview
|
|
6
|
+
|
|
7
|
+
The `@workglow/ai-provider` package provides concrete implementations of AI providers that can be used with Workglow's task execution system. It includes support for various AI services and local model execution frameworks.
|
|
8
|
+
|
|
9
|
+
## Features
|
|
10
|
+
|
|
11
|
+
- **HuggingFace Transformers**: Support for ONNX models via HuggingFace Transformers.js
|
|
12
|
+
- **TensorFlow MediaPipe**: Integration with Google's MediaPipe for text processing tasks
|
|
13
|
+
- [FUTURE] **OpenAI Integration**: Support for OpenAI API services
|
|
14
|
+
- [FUTURE] **GGML Support**: Local model execution with GGML format models
|
|
15
|
+
- **Multi-Platform**: Works in browser, Node.js, and Bun environments
|
|
16
|
+
- **Worker Support**: Offload AI computation to web workers for better performance
|
|
17
|
+
- **Type Safety**: Full TypeScript support with comprehensive type definitions
|
|
18
|
+
|
|
19
|
+
## Installation
|
|
20
|
+
|
|
21
|
+
```bash
|
|
22
|
+
npm install @workglow/ai-provider
|
|
23
|
+
# or
|
|
24
|
+
bun add @workglow/ai-provider
|
|
25
|
+
```
|
|
26
|
+
|
|
27
|
+
## Peer Dependencies
|
|
28
|
+
|
|
29
|
+
Depending on which providers you use, you may need to install additional peer dependencies:
|
|
30
|
+
|
|
31
|
+
```bash
|
|
32
|
+
# For HuggingFace Transformers support
|
|
33
|
+
npm install @sroussey/transformers
|
|
34
|
+
|
|
35
|
+
# For MediaPipe support
|
|
36
|
+
npm install @mediapipe/tasks-text
|
|
37
|
+
```
|
|
38
|
+
|
|
39
|
+
## Quick Start
|
|
40
|
+
|
|
41
|
+
### 1. Basic Setup
|
|
42
|
+
|
|
43
|
+
```typescript
|
|
44
|
+
import {
|
|
45
|
+
HF_TRANSFORMERS_ONNX,
|
|
46
|
+
TENSORFLOW_MEDIAPIPE,
|
|
47
|
+
register_HFT_InlineJobFns,
|
|
48
|
+
register_TFMP_InlineJobFns,
|
|
49
|
+
} from "@workglow/ai-provider";
|
|
50
|
+
import { getTaskQueueRegistry } from "@workglow/task-graph";
|
|
51
|
+
import { AiJob } from "@workglow/ai";
|
|
52
|
+
import { JobQueue, ConcurrencyLimiter } from "@workglow/job-queue";
|
|
53
|
+
import { InMemoryQueueStorage } from "@workglow/storage";
|
|
54
|
+
|
|
55
|
+
// Register AI providers
|
|
56
|
+
await register_HFT_InlineJobFns();
|
|
57
|
+
register_TFMP_InlineJobFns();
|
|
58
|
+
|
|
59
|
+
// Set up job queues
|
|
60
|
+
const queueRegistry = getTaskQueueRegistry();
|
|
61
|
+
|
|
62
|
+
queueRegistry.registerQueue(
|
|
63
|
+
new JobQueue(HF_TRANSFORMERS_ONNX, AiJob, {
|
|
64
|
+
limiter: new ConcurrencyLimiter(1, 100),
|
|
65
|
+
storage: new InMemoryQueueStorage(HF_TRANSFORMERS_ONNX),
|
|
66
|
+
})
|
|
67
|
+
);
|
|
68
|
+
|
|
69
|
+
queueRegistry.registerQueue(
|
|
70
|
+
new JobQueue(TENSORFLOW_MEDIAPIPE, AiJob, {
|
|
71
|
+
limiter: new ConcurrencyLimiter(1, 100),
|
|
72
|
+
storage: new InMemoryQueueStorage(TENSORFLOW_MEDIAPIPE),
|
|
73
|
+
})
|
|
74
|
+
);
|
|
75
|
+
```
|
|
76
|
+
|
|
77
|
+
### 2. Using AI Tasks in Workflows
|
|
78
|
+
|
|
79
|
+
```typescript
|
|
80
|
+
import {
|
|
81
|
+
TextGenerationTask,
|
|
82
|
+
TextEmbeddingTask,
|
|
83
|
+
TextTranslationTask,
|
|
84
|
+
TextSummaryTask,
|
|
85
|
+
} from "@workglow/ai";
|
|
86
|
+
import { Workflow } from "@workglow/task-graph";
|
|
87
|
+
|
|
88
|
+
const workflow = new Workflow();
|
|
89
|
+
|
|
90
|
+
// Add AI tasks to your workflow
|
|
91
|
+
const result = await workflow
|
|
92
|
+
.add(
|
|
93
|
+
new TextGenerationTask({
|
|
94
|
+
model: "Xenova/gpt2",
|
|
95
|
+
prompt: "The future of AI is",
|
|
96
|
+
})
|
|
97
|
+
)
|
|
98
|
+
.add(
|
|
99
|
+
new TextEmbeddingTask({
|
|
100
|
+
model: "Xenova/all-MiniLM-L6-v2",
|
|
101
|
+
text: "Hello world",
|
|
102
|
+
})
|
|
103
|
+
)
|
|
104
|
+
.run();
|
|
105
|
+
```
|
|
106
|
+
|
|
107
|
+
## Available Providers
|
|
108
|
+
|
|
109
|
+
### HuggingFace Transformers (`HF_TRANSFORMERS_ONNX`)
|
|
110
|
+
|
|
111
|
+
Supports ONNX models from HuggingFace Hub with the following task types:
|
|
112
|
+
|
|
113
|
+
#### Supported Tasks
|
|
114
|
+
|
|
115
|
+
- **TextGenerationTask**: Generate text from prompts
|
|
116
|
+
- **TextEmbeddingTask**: Generate vector embeddings for text
|
|
117
|
+
- **TextTranslationTask**: Translate text between languages
|
|
118
|
+
- **TextSummaryTask**: Summarize long text
|
|
119
|
+
- **TextRewriterTask**: Rewrite text with a given prompt
|
|
120
|
+
- **TextQuestionAnswerTask**: Answer questions based on context
|
|
121
|
+
- **DownloadModelTask**: Pre-download and cache models
|
|
122
|
+
|
|
123
|
+
#### Model Configuration
|
|
124
|
+
|
|
125
|
+
Models support various quantization options:
|
|
126
|
+
|
|
127
|
+
```typescript
|
|
128
|
+
import { QUANTIZATION_DATA_TYPES } from "@workglow/ai-provider";
|
|
129
|
+
|
|
130
|
+
// Quantization options
|
|
131
|
+
// "auto" - Auto-detect based on environment
|
|
132
|
+
// "fp32" - 32-bit floating point
|
|
133
|
+
// "fp16" - 16-bit floating point
|
|
134
|
+
// "q8" - 8-bit quantized
|
|
135
|
+
// "int8" - 8-bit integer
|
|
136
|
+
// "uint8" - 8-bit unsigned integer
|
|
137
|
+
// "q4" - 4-bit quantized
|
|
138
|
+
// "bnb4" - BitsAndBytes 4-bit
|
|
139
|
+
// "q4f16" - fp16 model with int4 block weight quantization
|
|
140
|
+
```
|
|
141
|
+
|
|
142
|
+
#### Task Examples
|
|
143
|
+
|
|
144
|
+
**Text Generation:**
|
|
145
|
+
|
|
146
|
+
```typescript
|
|
147
|
+
import { TextGenerationTask } from "@workglow/ai";
|
|
148
|
+
|
|
149
|
+
const task = new TextGenerationTask({
|
|
150
|
+
model: "Xenova/gpt2",
|
|
151
|
+
prompt: "Once upon a time",
|
|
152
|
+
maxTokens: 50,
|
|
153
|
+
temperature: 0.7,
|
|
154
|
+
topP: 0.9,
|
|
155
|
+
frequencyPenalty: 0,
|
|
156
|
+
presencePenalty: 0,
|
|
157
|
+
});
|
|
158
|
+
|
|
159
|
+
const result = await task.execute();
|
|
160
|
+
// result.text: string - Generated text
|
|
161
|
+
```
|
|
162
|
+
|
|
163
|
+
**Text Embedding:**
|
|
164
|
+
|
|
165
|
+
```typescript
|
|
166
|
+
import { TextEmbeddingTask } from "@workglow/ai";
|
|
167
|
+
|
|
168
|
+
const task = new TextEmbeddingTask({
|
|
169
|
+
model: "Xenova/all-MiniLM-L6-v2",
|
|
170
|
+
text: "This is a sample text for embedding",
|
|
171
|
+
});
|
|
172
|
+
|
|
173
|
+
const result = await task.execute();
|
|
174
|
+
// result.vector: TypedArray - Vector embedding
|
|
175
|
+
```
|
|
176
|
+
|
|
177
|
+
**Text Translation:**
|
|
178
|
+
|
|
179
|
+
```typescript
|
|
180
|
+
import { TextTranslationTask } from "@workglow/ai";
|
|
181
|
+
|
|
182
|
+
const task = new TextTranslationTask({
|
|
183
|
+
model: "Xenova/t5-small",
|
|
184
|
+
text: "Hello world",
|
|
185
|
+
source_lang: "en",
|
|
186
|
+
target_lang: "fr",
|
|
187
|
+
});
|
|
188
|
+
|
|
189
|
+
const result = await task.execute();
|
|
190
|
+
// result.text: string - Translated text
|
|
191
|
+
// result.target_lang: string - Target language
|
|
192
|
+
```
|
|
193
|
+
|
|
194
|
+
**Text Summary:**
|
|
195
|
+
|
|
196
|
+
```typescript
|
|
197
|
+
import { TextSummaryTask } from "@workglow/ai";
|
|
198
|
+
|
|
199
|
+
const task = new TextSummaryTask({
|
|
200
|
+
model: "Xenova/distilbart-cnn-6-6",
|
|
201
|
+
text: "Long text to summarize...",
|
|
202
|
+
});
|
|
203
|
+
|
|
204
|
+
const result = await task.execute();
|
|
205
|
+
// result.text: string - Summary text
|
|
206
|
+
```
|
|
207
|
+
|
|
208
|
+
**Text Rewriter:**
|
|
209
|
+
|
|
210
|
+
```typescript
|
|
211
|
+
import { TextRewriterTask } from "@workglow/ai";
|
|
212
|
+
|
|
213
|
+
const task = new TextRewriterTask({
|
|
214
|
+
model: "Xenova/gpt2",
|
|
215
|
+
text: "The weather is nice today",
|
|
216
|
+
prompt: "Rewrite this as a pirate would say it",
|
|
217
|
+
});
|
|
218
|
+
|
|
219
|
+
const result = await task.execute();
|
|
220
|
+
// result.text: string - Rewritten text
|
|
221
|
+
```
|
|
222
|
+
|
|
223
|
+
**Question Answering:**
|
|
224
|
+
|
|
225
|
+
```typescript
|
|
226
|
+
import { TextQuestionAnswerTask } from "@workglow/ai";
|
|
227
|
+
|
|
228
|
+
const task = new TextQuestionAnswerTask({
|
|
229
|
+
model: "Xenova/distilbert-base-uncased-distilled-squad",
|
|
230
|
+
context: "The capital of France is Paris. It is known for the Eiffel Tower.",
|
|
231
|
+
question: "What is the capital of France?",
|
|
232
|
+
});
|
|
233
|
+
|
|
234
|
+
const result = await task.execute();
|
|
235
|
+
// result.text: string - Answer text
|
|
236
|
+
```
|
|
237
|
+
|
|
238
|
+
### TensorFlow MediaPipe (`TENSORFLOW_MEDIAPIPE`)
|
|
239
|
+
|
|
240
|
+
Optimized for performance using Google's MediaPipe framework.
|
|
241
|
+
|
|
242
|
+
#### Supported Tasks
|
|
243
|
+
|
|
244
|
+
- **TextEmbeddingTask**: Generate vector embeddings for text
|
|
245
|
+
- **DownloadModelTask**: Pre-download and cache models
|
|
246
|
+
|
|
247
|
+
#### Example
|
|
248
|
+
|
|
249
|
+
```typescript
|
|
250
|
+
import { TextEmbeddingTask } from "@workglow/ai";
|
|
251
|
+
|
|
252
|
+
const task = new TextEmbeddingTask({
|
|
253
|
+
model: "path/to/mediapipe/model.tflite",
|
|
254
|
+
text: "Text to embed",
|
|
255
|
+
});
|
|
256
|
+
|
|
257
|
+
const result = await task.execute();
|
|
258
|
+
// result.vector: Float32Array - Vector embedding
|
|
259
|
+
```
|
|
260
|
+
|
|
261
|
+
## Advanced Usage
|
|
262
|
+
|
|
263
|
+
### Worker Setup
|
|
264
|
+
|
|
265
|
+
For better performance, especially in browser environments, run AI inference in web workers:
|
|
266
|
+
|
|
267
|
+
#### Main Thread Setup
|
|
268
|
+
|
|
269
|
+
```typescript
|
|
270
|
+
import { register_HFT_ClientJobFns, register_TFMP_ClientJobFns } from "@workglow/ai-provider";
|
|
271
|
+
|
|
272
|
+
// Register HuggingFace Transformers with worker
|
|
273
|
+
register_HFT_ClientJobFns(
|
|
274
|
+
new Worker(new URL("./hft-worker.ts", import.meta.url), { type: "module" })
|
|
275
|
+
);
|
|
276
|
+
|
|
277
|
+
// Register MediaPipe with worker
|
|
278
|
+
register_TFMP_ClientJobFns(
|
|
279
|
+
new Worker(new URL("./tfmp-worker.ts", import.meta.url), { type: "module" })
|
|
280
|
+
);
|
|
281
|
+
```
|
|
282
|
+
|
|
283
|
+
#### Worker Setup Files
|
|
284
|
+
|
|
285
|
+
**hft-worker.ts:**
|
|
286
|
+
|
|
287
|
+
```typescript
|
|
288
|
+
import { register_HFT_WorkerJobFns } from "@workglow/ai-provider";
|
|
289
|
+
|
|
290
|
+
// Register HuggingFace Transformers worker functions
|
|
291
|
+
register_HFT_WorkerJobFns();
|
|
292
|
+
```
|
|
293
|
+
|
|
294
|
+
**tfmp-worker.ts:**
|
|
295
|
+
|
|
296
|
+
```typescript
|
|
297
|
+
import { register_TFMP_WorkerJobFns } from "@workglow/ai-provider";
|
|
298
|
+
|
|
299
|
+
// Register MediaPipe worker functions
|
|
300
|
+
register_TFMP_WorkerJobFns();
|
|
301
|
+
```
|
|
302
|
+
|
|
303
|
+
### Model Management
|
|
304
|
+
|
|
305
|
+
```typescript
|
|
306
|
+
import { getGlobalModelRepository } from "@workglow/ai";
|
|
307
|
+
import { DownloadModelTask } from "@workglow/ai";
|
|
308
|
+
|
|
309
|
+
// Pre-download models
|
|
310
|
+
const downloadTask = new DownloadModelTask({
|
|
311
|
+
model: "Xenova/all-MiniLM-L6-v2",
|
|
312
|
+
});
|
|
313
|
+
|
|
314
|
+
await downloadTask.execute();
|
|
315
|
+
|
|
316
|
+
// Models are automatically cached for subsequent use
|
|
317
|
+
```
|
|
318
|
+
|
|
319
|
+
### Custom Job Queue Configuration
|
|
320
|
+
|
|
321
|
+
```typescript
|
|
322
|
+
import { JobQueue, ConcurrencyLimiter, DelayLimiter } from "@workglow/job-queue";
|
|
323
|
+
import { InMemoryQueueStorage } from "@workglow/storage";
|
|
324
|
+
|
|
325
|
+
// Configure queue with custom limits
|
|
326
|
+
const customQueue = new JobQueue(HF_TRANSFORMERS_ONNX, AiJob, {
|
|
327
|
+
limiter: new ConcurrencyLimiter(2, 1000), // 2 concurrent jobs, 1000ms timeout
|
|
328
|
+
storage: new InMemoryQueueStorage(HF_TRANSFORMERS_ONNX),
|
|
329
|
+
});
|
|
330
|
+
```
|
|
331
|
+
|
|
332
|
+
### Error Handling
|
|
333
|
+
|
|
334
|
+
```typescript
|
|
335
|
+
import { PermanentJobError, AbortSignalJobError } from "@workglow/job-queue";
|
|
336
|
+
|
|
337
|
+
try {
|
|
338
|
+
const task = new TextGenerationTask({
|
|
339
|
+
model: "invalid-model",
|
|
340
|
+
prompt: "Test",
|
|
341
|
+
});
|
|
342
|
+
|
|
343
|
+
await task.execute();
|
|
344
|
+
} catch (error) {
|
|
345
|
+
if (error instanceof PermanentJobError) {
|
|
346
|
+
console.error("Permanent error:", error.message);
|
|
347
|
+
} else if (error instanceof AbortSignalJobError) {
|
|
348
|
+
console.error("Task was aborted");
|
|
349
|
+
}
|
|
350
|
+
}
|
|
351
|
+
```
|
|
352
|
+
|
|
353
|
+
### Progress Tracking
|
|
354
|
+
|
|
355
|
+
```typescript
|
|
356
|
+
const task = new TextGenerationTask({
|
|
357
|
+
model: "Xenova/gpt2",
|
|
358
|
+
prompt: "Generate text...",
|
|
359
|
+
});
|
|
360
|
+
|
|
361
|
+
// Listen for progress updates
|
|
362
|
+
task.on("progress", (progress, message, details) => {
|
|
363
|
+
console.log(`Progress: ${progress}% - ${message}`, details);
|
|
364
|
+
});
|
|
365
|
+
|
|
366
|
+
await task.execute();
|
|
367
|
+
```
|
|
368
|
+
|
|
369
|
+
## Complete Working Example
|
|
370
|
+
|
|
371
|
+
```typescript
|
|
372
|
+
import { HF_TRANSFORMERS_ONNX, register_HFT_InlineJobFns } from "@workglow/ai-provider";
|
|
373
|
+
import { TextGenerationTask, TextEmbeddingTask, AiJob } from "@workglow/ai";
|
|
374
|
+
import { Workflow, getTaskQueueRegistry } from "@workglow/task-graph";
|
|
375
|
+
import { JobQueue, ConcurrencyLimiter } from "@workglow/job-queue";
|
|
376
|
+
import { InMemoryQueueStorage } from "@workglow/storage";
|
|
377
|
+
|
|
378
|
+
async function main() {
|
|
379
|
+
// 1. Register the AI provider
|
|
380
|
+
await register_HFT_InlineJobFns();
|
|
381
|
+
|
|
382
|
+
// 2. Set up job queue
|
|
383
|
+
const queueRegistry = getTaskQueueRegistry();
|
|
384
|
+
queueRegistry.registerQueue(
|
|
385
|
+
new JobQueue(HF_TRANSFORMERS_ONNX, AiJob, {
|
|
386
|
+
limiter: new ConcurrencyLimiter(1, 100),
|
|
387
|
+
storage: new InMemoryQueueStorage(HF_TRANSFORMERS_ONNX),
|
|
388
|
+
})
|
|
389
|
+
);
|
|
390
|
+
|
|
391
|
+
// 3. Create and run workflow
|
|
392
|
+
const workflow = new Workflow();
|
|
393
|
+
|
|
394
|
+
const result = await workflow
|
|
395
|
+
.add(
|
|
396
|
+
new TextGenerationTask({
|
|
397
|
+
model: "Xenova/gpt2",
|
|
398
|
+
prompt: "The benefits of AI include",
|
|
399
|
+
maxTokens: 50,
|
|
400
|
+
})
|
|
401
|
+
)
|
|
402
|
+
.add(
|
|
403
|
+
new TextEmbeddingTask({
|
|
404
|
+
model: "Xenova/all-MiniLM-L6-v2",
|
|
405
|
+
text: "AI is transforming the world",
|
|
406
|
+
})
|
|
407
|
+
)
|
|
408
|
+
.run();
|
|
409
|
+
|
|
410
|
+
console.log("Generated text:", result.outputs[0].text);
|
|
411
|
+
console.log("Embedding dimensions:", result.outputs[1].vector.length);
|
|
412
|
+
}
|
|
413
|
+
|
|
414
|
+
main().catch(console.error);
|
|
415
|
+
```
|
|
416
|
+
|
|
417
|
+
## Task Input/Output Schemas
|
|
418
|
+
|
|
419
|
+
### Common Types
|
|
420
|
+
|
|
421
|
+
```typescript
|
|
422
|
+
// Model reference (string)
|
|
423
|
+
model: string
|
|
424
|
+
|
|
425
|
+
// Text input/output
|
|
426
|
+
text: string
|
|
427
|
+
|
|
428
|
+
// Vector embedding (typed array)
|
|
429
|
+
vector: Float32Array | Float64Array | Int32Array | etc.
|
|
430
|
+
|
|
431
|
+
// Language codes (ISO 639-1)
|
|
432
|
+
source_lang: string // e.g., "en", "fr", "es"
|
|
433
|
+
target_lang: string
|
|
434
|
+
```
|
|
435
|
+
|
|
436
|
+
### Task Schemas Summary
|
|
437
|
+
|
|
438
|
+
| Task | Input | Output |
|
|
439
|
+
| -------------------------- | ----------------------------------------------------------------------------------------- | ----------------------- |
|
|
440
|
+
| **TextGenerationTask** | `{ model, prompt, maxTokens?, temperature?, topP?, frequencyPenalty?, presencePenalty? }` | `{ text }` |
|
|
441
|
+
| **TextEmbeddingTask** | `{ model, text }` | `{ vector }` |
|
|
442
|
+
| **TextTranslationTask** | `{ model, text, source_lang, target_lang }` | `{ text, target_lang }` |
|
|
443
|
+
| **TextSummaryTask** | `{ model, text }` | `{ text }` |
|
|
444
|
+
| **TextRewriterTask** | `{ model, text, prompt }` | `{ text }` |
|
|
445
|
+
| **TextQuestionAnswerTask** | `{ model, context, question }` | `{ text }` |
|
|
446
|
+
| **DownloadModelTask** | `{ model }` | `{ model }` |
|
|
447
|
+
|
|
448
|
+
## Popular Models
|
|
449
|
+
|
|
450
|
+
### HuggingFace Transformers Models
|
|
451
|
+
|
|
452
|
+
**Text Generation:**
|
|
453
|
+
|
|
454
|
+
- `Xenova/gpt2` - GPT-2 text generation
|
|
455
|
+
- `Xenova/distilgpt2` - Smaller GPT-2 variant
|
|
456
|
+
|
|
457
|
+
**Text Embedding:**
|
|
458
|
+
|
|
459
|
+
- `Xenova/all-MiniLM-L6-v2` - General purpose embeddings
|
|
460
|
+
- `Xenova/all-mpnet-base-v2` - High quality embeddings
|
|
461
|
+
|
|
462
|
+
**Translation:**
|
|
463
|
+
|
|
464
|
+
- `Xenova/t5-small` - Multilingual translation
|
|
465
|
+
- `Xenova/marian-mt-en-fr` - English to French
|
|
466
|
+
|
|
467
|
+
**Summarization:**
|
|
468
|
+
|
|
469
|
+
- `Xenova/distilbart-cnn-6-6` - News summarization
|
|
470
|
+
- `Xenova/t5-small` - General summarization
|
|
471
|
+
|
|
472
|
+
**Question Answering:**
|
|
473
|
+
|
|
474
|
+
- `Xenova/distilbert-base-uncased-distilled-squad` - SQuAD trained
|
|
475
|
+
|
|
476
|
+
## Dependencies
|
|
477
|
+
|
|
478
|
+
This package depends on:
|
|
479
|
+
|
|
480
|
+
- `@workglow/ai` - Core AI abstractions
|
|
481
|
+
- `@workglow/job-queue` - Job queue system
|
|
482
|
+
- `@workglow/storage` - Storage abstractions
|
|
483
|
+
- `@workglow/task-graph` - Task graph system
|
|
484
|
+
- `@workglow/util` - Utility functions
|
|
485
|
+
|
|
486
|
+
## License
|
|
487
|
+
|
|
488
|
+
Apache 2.0 - See [LICENSE](./LICENSE) for details.
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"GgmlLocalModel.d.ts","sourceRoot":"","sources":["../../../src/ggml/model/GgmlLocalModel.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,eAAO,MAAM,cAAc,mBAAmB,CAAC"}
|