@chainfuse/types 1.7.3 → 2.1.0

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.
@@ -1,637 +0,0 @@
1
- import type { JSONSchema7 } from 'json-schema';
2
- import { workersAiCatalog } from '../ai-tools/workers-ai-catalog.js';
3
- export interface Coordinate {
4
- lat: number;
5
- lon: number;
6
- }
7
- type ToolJsonSchemaDefinition = ToolJsonSchema | boolean;
8
- export interface ToolJsonSchema extends Omit<JSONSchema7, '$id' | '$ref' | '$schema' | '$defs' | 'title' | 'readOnly' | 'writeOnly'> {
9
- properties?: Record<string, ToolJsonSchemaDefinition>;
10
- }
11
- export interface ToolJsonRoot extends Omit<ToolJsonSchema, 'type'> {
12
- type: 'object';
13
- }
14
- export declare enum enabledAzureLlmProviders {
15
- Azure_OpenAi_Gpt3 = "azure_openai_gpt3",
16
- Azure_OpenAi_Gpt4o_mini = "azure_openai_gpt4o_mini",
17
- Azure_OpenAi_Gpt4 = "azure_openai_gpt4",
18
- Azure_OpenAi_Gpt4o = "azure_openai_gpt4o"
19
- }
20
- export declare enum enabledAzureLlmEmbeddingProviders {
21
- Azure_OpenAi_Embed3_Large = "azure_openai_embed3_large",
22
- Azure_OpenAi_Embed3_Small = "azure_openai_embed3_small"
23
- }
24
- export type cloudflareModelTypes = keyof typeof workersAiCatalog.modelGroups;
25
- export type cloudflareModelPossibilitiesRaw<M extends cloudflareModelTypes = cloudflareModelTypes> = (typeof workersAiCatalog.modelGroups)[M]['models'][number];
26
- export type cloudflareModelPossibilities<M extends cloudflareModelTypes = cloudflareModelTypes> = cloudflareModelPossibilitiesRaw<M>['name'];
27
- type cloudflareModelProperties<Model> = Model extends {
28
- properties: infer Props;
29
- } ? keyof Props : never;
30
- type cloudflareModelPossibilitiesProperties<M extends cloudflareModelTypes = cloudflareModelTypes> = cloudflareModelProperties<cloudflareModelPossibilitiesRaw<M>>;
31
- export type cloudflareFilteredModelPossibilitiesRaw<M extends cloudflareModelTypes = cloudflareModelTypes, K extends cloudflareModelPossibilitiesProperties<M> = cloudflareModelPossibilitiesProperties<M>, V extends cloudflareModelPossibilitiesRaw<M>['properties'][K] = any> = cloudflareModelPossibilitiesRaw<M> extends infer Model ? (Model extends {
32
- properties: Record<K, V>;
33
- } ? Model : never) : never;
34
- export type cloudflareFilteredModelPossibilities<M extends cloudflareModelTypes = cloudflareModelTypes, K extends cloudflareModelPossibilitiesProperties<M> = cloudflareModelPossibilitiesProperties<M>, V extends cloudflareModelPossibilitiesRaw<M>['properties'][K] = any> = cloudflareFilteredModelPossibilitiesRaw<M, K, V>['name'];
35
- export declare const enabledCloudflareLlmSummaryProviders: cloudflareModelPossibilities<'Summarization'>[];
36
- export declare const enabledCloudflareLlmClassificationProviders: cloudflareModelPossibilities<'Text Classification'>[];
37
- export declare const enabledCloudflareLlmEmbeddingProviders: cloudflareModelPossibilities<'Text Embeddings'>[];
38
- export declare const enabledCloudflareLlmProviders: cloudflareModelPossibilities<'Text Generation'>[];
39
- export declare const enabledCloudflareLlmFunctionProviders: "@hf/nousresearch/hermes-2-pro-mistral-7b"[];
40
- export type aiProviders<M extends Exclude<cloudflareModelTypes, 'Text Embeddings'> = Exclude<cloudflareModelTypes, 'Text Embeddings'>> = enabledAzureLlmProviders | cloudflareModelPossibilities<M>;
41
- export type aiEmbeddingProviders = enabledAzureLlmEmbeddingProviders | cloudflareModelPossibilities<'Text Embeddings'>;
42
- export type aiFunctionProviders = enabledAzureLlmProviders | cloudflareFilteredModelPossibilities<'Text Generation', 'function_calling', true>;
43
- export declare const possibilities_mc_generic: readonly [...{
44
- name: "Azure_OpenAi_Gpt3" | "Azure_OpenAi_Gpt4o_mini" | "Azure_OpenAi_Gpt4" | "Azure_OpenAi_Gpt4o";
45
- }[], {
46
- readonly id: "44774b85-08c8-4bb8-8d2a-b06ebc538a79";
47
- readonly source: 2;
48
- readonly name: "@hf/nousresearch/hermes-2-pro-mistral-7b";
49
- readonly description: "Hermes 2 Pro on Mistral 7B is the new flagship 7B Hermes! Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.";
50
- readonly tags: readonly [];
51
- readonly properties: {
52
- readonly beta: true;
53
- readonly context_window: 24000;
54
- readonly function_calling: true;
55
- readonly info: "https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B";
56
- };
57
- }];
58
- export type type_mc_generic = aiFunctionProviders;
59
- export declare const possibilities_mc_summary: readonly [...{
60
- name: "Azure_OpenAi_Gpt3" | "Azure_OpenAi_Gpt4o_mini" | "Azure_OpenAi_Gpt4" | "Azure_OpenAi_Gpt4o";
61
- }[], {
62
- readonly id: "19bd38eb-bcda-4e53-bec2-704b4689b43a";
63
- readonly source: 1;
64
- readonly name: "@cf/facebook/bart-large-cnn";
65
- readonly description: "BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. You can use this model for text summarization.";
66
- readonly tags: readonly [];
67
- readonly properties: {
68
- readonly beta: true;
69
- };
70
- }];
71
- export type type_mc_summary = aiProviders<'Summarization'>;
72
- export declare const possibilities_mc_extraction: readonly [...{
73
- name: "Azure_OpenAi_Gpt3" | "Azure_OpenAi_Gpt4o_mini" | "Azure_OpenAi_Gpt4" | "Azure_OpenAi_Gpt4o";
74
- }[], {
75
- readonly id: "44774b85-08c8-4bb8-8d2a-b06ebc538a79";
76
- readonly source: 2;
77
- readonly name: "@hf/nousresearch/hermes-2-pro-mistral-7b";
78
- readonly description: "Hermes 2 Pro on Mistral 7B is the new flagship 7B Hermes! Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.";
79
- readonly tags: readonly [];
80
- readonly properties: {
81
- readonly beta: true;
82
- readonly context_window: 24000;
83
- readonly function_calling: true;
84
- readonly info: "https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B";
85
- };
86
- }];
87
- export type type_mc_extraction = aiFunctionProviders;
88
- export declare const possibilities_mc_tagging: readonly [...{
89
- name: "Azure_OpenAi_Gpt3" | "Azure_OpenAi_Gpt4o_mini" | "Azure_OpenAi_Gpt4" | "Azure_OpenAi_Gpt4o";
90
- }[], {
91
- readonly id: "44774b85-08c8-4bb8-8d2a-b06ebc538a79";
92
- readonly source: 2;
93
- readonly name: "@hf/nousresearch/hermes-2-pro-mistral-7b";
94
- readonly description: "Hermes 2 Pro on Mistral 7B is the new flagship 7B Hermes! Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.";
95
- readonly tags: readonly [];
96
- readonly properties: {
97
- readonly beta: true;
98
- readonly context_window: 24000;
99
- readonly function_calling: true;
100
- readonly info: "https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B";
101
- };
102
- }];
103
- export type type_mc_tagging = aiFunctionProviders;
104
- export declare const possibilities_mc_sentiment: readonly [...{
105
- name: "Azure_OpenAi_Gpt3" | "Azure_OpenAi_Gpt4o_mini" | "Azure_OpenAi_Gpt4" | "Azure_OpenAi_Gpt4o";
106
- }[], {
107
- readonly id: "44774b85-08c8-4bb8-8d2a-b06ebc538a79";
108
- readonly source: 2;
109
- readonly name: "@hf/nousresearch/hermes-2-pro-mistral-7b";
110
- readonly description: "Hermes 2 Pro on Mistral 7B is the new flagship 7B Hermes! Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.";
111
- readonly tags: readonly [];
112
- readonly properties: {
113
- readonly beta: true;
114
- readonly context_window: 24000;
115
- readonly function_calling: true;
116
- readonly info: "https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B";
117
- };
118
- }];
119
- export type type_mc_sentiment = aiFunctionProviders;
120
- export declare const possibilities_mc_safety: readonly [...{
121
- name: "Azure_OpenAi_Gpt3" | "Azure_OpenAi_Gpt4o_mini" | "Azure_OpenAi_Gpt4" | "Azure_OpenAi_Gpt4o";
122
- }[], {
123
- readonly id: "f8703a00-ed54-4f98-bdc3-cd9a813286f3";
124
- readonly source: 1;
125
- readonly name: "@cf/qwen/qwen1.5-0.5b-chat";
126
- readonly description: "Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.";
127
- readonly tags: readonly [];
128
- readonly properties: {
129
- readonly beta: true;
130
- readonly context_window: 32000;
131
- readonly info: "https://huggingface.co/qwen/qwen1.5-0.5b-chat";
132
- };
133
- }, {
134
- readonly id: "e8e8abe4-a372-4c13-815f-4688ba655c8e";
135
- readonly source: 1;
136
- readonly name: "@cf/google/gemma-2b-it-lora";
137
- readonly description: "This is a Gemma-2B base model that Cloudflare dedicates for inference with LoRA adapters. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.";
138
- readonly tags: readonly [];
139
- readonly properties: {
140
- readonly beta: true;
141
- readonly context_window: 8192;
142
- readonly lora: true;
143
- };
144
- }, {
145
- readonly id: "e5ca943b-720f-4e66-aa8f-40e3d2770933";
146
- readonly source: 2;
147
- readonly name: "@hf/nexusflow/starling-lm-7b-beta";
148
- readonly description: "We introduce Starling-LM-7B-beta, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). Starling-LM-7B-beta is trained from Openchat-3.5-0106 with our new reward model Nexusflow/Starling-RM-34B and policy optimization method Fine-Tuning Language Models from Human Preferences (PPO).";
149
- readonly tags: readonly [];
150
- readonly properties: {
151
- readonly beta: true;
152
- readonly context_window: 4096;
153
- readonly info: "https://huggingface.co/Nexusflow/Starling-LM-7B-beta";
154
- readonly max_batch_prefill_tokens: 8192;
155
- readonly max_input_length: 3072;
156
- readonly max_total_tokens: 4096;
157
- };
158
- }, {
159
- readonly id: "e11d8f45-7b08-499a-9eeb-71d4d3c8cbf9";
160
- readonly source: 1;
161
- readonly name: "@cf/meta/llama-3-8b-instruct";
162
- readonly description: "Generation over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.";
163
- readonly tags: readonly [];
164
- readonly properties: {
165
- readonly context_window: 7968;
166
- readonly info: "https://llama.meta.com";
167
- readonly terms: "https://llama.meta.com/llama3/license/#";
168
- };
169
- }, {
170
- readonly id: "d9dc8363-66f4-4bb0-8641-464ee7bfc131";
171
- readonly source: 1;
172
- readonly name: "@cf/meta/llama-3.2-3b-instruct";
173
- readonly description: "The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.";
174
- readonly tags: readonly [];
175
- readonly properties: {
176
- readonly context_window: 128000;
177
- readonly terms: "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE";
178
- };
179
- }, {
180
- readonly id: "d9b7a55c-cefa-4208-8ab3-11497a2b046c";
181
- readonly source: 2;
182
- readonly name: "@hf/thebloke/llamaguard-7b-awq";
183
- readonly description: "Llama Guard is a model for classifying the safety of LLM prompts and responses, using a taxonomy of safety risks.\n";
184
- readonly tags: readonly [];
185
- readonly properties: {
186
- readonly beta: true;
187
- readonly context_window: 4096;
188
- };
189
- }, {
190
- readonly id: "d2ba5c6b-bbb7-49d6-b466-900654870cd6";
191
- readonly source: 2;
192
- readonly name: "@hf/thebloke/neural-chat-7b-v3-1-awq";
193
- readonly description: "This model is a fine-tuned 7B parameter LLM on the Intel Gaudi 2 processor from the mistralai/Mistral-7B-v0.1 on the open source dataset Open-Orca/SlimOrca.";
194
- readonly tags: readonly [];
195
- readonly properties: {
196
- readonly beta: true;
197
- readonly context_window: 4096;
198
- };
199
- }, {
200
- readonly id: "cc80437b-9a8d-4f1a-9c77-9aaf0d226922";
201
- readonly source: 1;
202
- readonly name: "@cf/meta/llama-guard-3-8b";
203
- readonly description: "Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.";
204
- readonly tags: readonly [];
205
- readonly properties: {};
206
- }, {
207
- readonly id: "ca54bcd6-0d98-4739-9b3b-5c8b4402193d";
208
- readonly source: 1;
209
- readonly name: "@cf/meta/llama-2-7b-chat-fp16";
210
- readonly description: "Full precision (fp16) generative text model with 7 billion parameters from Meta";
211
- readonly tags: readonly [];
212
- readonly properties: {
213
- readonly beta: true;
214
- readonly context_window: 4096;
215
- readonly info: "https://ai.meta.com/llama/";
216
- readonly terms: "https://ai.meta.com/resources/models-and-libraries/llama-downloads/";
217
- };
218
- }, {
219
- readonly id: "c907d0f9-d69d-4e93-b501-4daeb4fd69eb";
220
- readonly source: 1;
221
- readonly name: "@cf/mistral/mistral-7b-instruct-v0.1";
222
- readonly description: "Instruct fine-tuned version of the Mistral-7b generative text model with 7 billion parameters";
223
- readonly tags: readonly [];
224
- readonly properties: {
225
- readonly beta: true;
226
- readonly context_window: 2824;
227
- readonly info: "https://mistral.ai/news/announcing-mistral-7b/";
228
- readonly lora: true;
229
- };
230
- }, {
231
- readonly id: "c58c317b-0c15-4bda-abb6-93e275f282d9";
232
- readonly source: 1;
233
- readonly name: "@cf/mistral/mistral-7b-instruct-v0.2-lora";
234
- readonly description: "The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.";
235
- readonly tags: readonly [];
236
- readonly properties: {
237
- readonly beta: true;
238
- readonly context_window: 15000;
239
- readonly lora: true;
240
- };
241
- }, {
242
- readonly id: "bf6ddd21-6477-4681-bbbe-24c3d5423e78";
243
- readonly source: 1;
244
- readonly name: "@cf/tinyllama/tinyllama-1.1b-chat-v1.0";
245
- readonly description: "The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. This is the chat model finetuned on top of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T.";
246
- readonly tags: readonly [];
247
- readonly properties: {
248
- readonly beta: true;
249
- readonly context_window: 2048;
250
- readonly info: "https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0";
251
- };
252
- }, {
253
- readonly id: "b97d7069-48d9-461c-80dd-445d20a632eb";
254
- readonly source: 2;
255
- readonly name: "@hf/mistral/mistral-7b-instruct-v0.2";
256
- readonly description: "The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2. Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1: 32k context window (vs 8k context in v0.1), rope-theta = 1e6, and no Sliding-Window Attention.";
257
- readonly tags: readonly [];
258
- readonly properties: {
259
- readonly beta: true;
260
- readonly context_window: 3072;
261
- readonly info: "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2";
262
- readonly lora: true;
263
- readonly max_batch_prefill_tokens: 8192;
264
- readonly max_input_length: 3072;
265
- readonly max_total_tokens: 4096;
266
- };
267
- }, {
268
- readonly id: "b7fe7ad2-aeaf-47d2-8bfa-7a5ae22a2ab4";
269
- readonly source: 1;
270
- readonly name: "@cf/fblgit/una-cybertron-7b-v2-bf16";
271
- readonly description: "Cybertron 7B v2 is a 7B MistralAI based model, best on it's series. It was trained with SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets.";
272
- readonly tags: readonly [];
273
- readonly properties: {
274
- readonly beta: true;
275
- readonly context_window: 15000;
276
- };
277
- }, {
278
- readonly id: "ad01ab83-baf8-4e7b-8fed-a0a219d4eb45";
279
- readonly source: 1;
280
- readonly name: "@cf/deepseek-ai/deepseek-r1-distill-qwen-32b";
281
- readonly description: "DeepSeek-R1-Distill-Qwen-32B is a model distilled from DeepSeek-R1 based on Qwen2.5. It outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.";
282
- readonly tags: readonly [];
283
- readonly properties: {
284
- readonly context_window: 80000;
285
- readonly terms: "https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE";
286
- };
287
- }, {
288
- readonly id: "9d2ab560-065e-4d0d-a789-d4bc7468d33e";
289
- readonly source: 1;
290
- readonly name: "@cf/thebloke/discolm-german-7b-v1-awq";
291
- readonly description: "DiscoLM German 7b is a Mistral-based large language model with a focus on German-language applications. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.";
292
- readonly tags: readonly [];
293
- readonly properties: {
294
- readonly beta: true;
295
- readonly context_window: 4096;
296
- readonly info: "https://huggingface.co/TheBloke/DiscoLM_German_7b_v1-AWQ";
297
- };
298
- }, {
299
- readonly id: "9c95c39d-45b3-4163-9631-22f0c0dc3b14";
300
- readonly source: 1;
301
- readonly name: "@cf/meta/llama-2-7b-chat-int8";
302
- readonly description: "Quantized (int8) generative text model with 7 billion parameters from Meta";
303
- readonly tags: readonly [];
304
- readonly properties: {
305
- readonly context_window: 8192;
306
- };
307
- }, {
308
- readonly id: "9b9c87c6-d4b7-494c-b177-87feab5904db";
309
- readonly source: 1;
310
- readonly name: "@cf/meta/llama-3.1-8b-instruct-fp8";
311
- readonly description: "Llama 3.1 8B quantized to FP8 precision";
312
- readonly tags: readonly [];
313
- readonly properties: {
314
- readonly context_window: 32000;
315
- readonly terms: "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE";
316
- };
317
- }, {
318
- readonly id: "980ec5e9-33c2-483a-a2d8-cd092fdf273f";
319
- readonly source: 2;
320
- readonly name: "@hf/thebloke/mistral-7b-instruct-v0.1-awq";
321
- readonly description: "Mistral 7B Instruct v0.1 AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Mistral variant.";
322
- readonly tags: readonly [];
323
- readonly properties: {
324
- readonly beta: true;
325
- readonly context_window: 4096;
326
- readonly info: "https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ";
327
- };
328
- }, {
329
- readonly id: "90a20ae7-7cf4-4eb3-8672-8fc4ee580635";
330
- readonly source: 1;
331
- readonly name: "@cf/qwen/qwen1.5-7b-chat-awq";
332
- readonly description: "Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.";
333
- readonly tags: readonly [];
334
- readonly properties: {
335
- readonly beta: true;
336
- readonly context_window: 20000;
337
- readonly info: "https://huggingface.co/qwen/qwen1.5-7b-chat-awq";
338
- };
339
- }, {
340
- readonly id: "906a57fd-b018-4d6c-a43e-a296d4cc5839";
341
- readonly source: 1;
342
- readonly name: "@cf/meta/llama-3.2-1b-instruct";
343
- readonly description: "The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.";
344
- readonly tags: readonly [];
345
- readonly properties: {
346
- readonly context_window: 60000;
347
- readonly terms: "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE";
348
- };
349
- }, {
350
- readonly id: "85c5a3c6-24b0-45e7-b23a-023182578822";
351
- readonly source: 2;
352
- readonly name: "@hf/thebloke/llama-2-13b-chat-awq";
353
- readonly description: "Llama 2 13B Chat AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Llama 2 variant.";
354
- readonly tags: readonly [];
355
- readonly properties: {
356
- readonly beta: true;
357
- readonly context_window: 4096;
358
- readonly info: "https://huggingface.co/TheBloke/Llama-2-13B-chat-AWQ";
359
- };
360
- }, {
361
- readonly id: "7f180530-2e16-4116-9d26-f49fbed9d372";
362
- readonly source: 2;
363
- readonly name: "@hf/thebloke/deepseek-coder-6.7b-base-awq";
364
- readonly description: "Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese.";
365
- readonly tags: readonly [];
366
- readonly properties: {
367
- readonly beta: true;
368
- readonly context_window: 4096;
369
- readonly terms: "https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-AWQ";
370
- };
371
- }, {
372
- readonly id: "7ed8d8e8-6040-4680-843a-aef402d6b013";
373
- readonly source: 1;
374
- readonly name: "@cf/meta-llama/llama-2-7b-chat-hf-lora";
375
- readonly description: "This is a Llama2 base model that Cloudflare dedicated for inference with LoRA adapters. Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. ";
376
- readonly tags: readonly [];
377
- readonly properties: {
378
- readonly beta: true;
379
- readonly context_window: 8192;
380
- readonly lora: true;
381
- };
382
- }, {
383
- readonly id: "7a143886-c9bb-4a1c-be95-377b1973bc3b";
384
- readonly source: 1;
385
- readonly name: "@cf/meta/llama-3.3-70b-instruct-fp8-fast";
386
- readonly description: "Llama 3.3 70B quantized to fp8 precision, optimized to be faster.";
387
- readonly tags: readonly [];
388
- readonly properties: {
389
- readonly context_window: 24000;
390
- readonly terms: "https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE";
391
- };
392
- }, {
393
- readonly id: "673c56cc-8553-49a1-b179-dd549ec9209a";
394
- readonly source: 2;
395
- readonly name: "@hf/thebloke/openhermes-2.5-mistral-7b-awq";
396
- readonly description: "OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.";
397
- readonly tags: readonly [];
398
- readonly properties: {
399
- readonly beta: true;
400
- readonly context_window: 4096;
401
- };
402
- }, {
403
- readonly id: "60474554-f03b-4ff4-8ecc-c1b7c71d7b29";
404
- readonly source: 2;
405
- readonly name: "@hf/thebloke/deepseek-coder-6.7b-instruct-awq";
406
- readonly description: "Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese.";
407
- readonly tags: readonly [];
408
- readonly properties: {
409
- readonly beta: true;
410
- readonly context_window: 4096;
411
- readonly terms: "https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-AWQ";
412
- };
413
- }, {
414
- readonly id: "4c3a544e-da47-4336-9cea-c7cbfab33f16";
415
- readonly source: 1;
416
- readonly name: "@cf/deepseek-ai/deepseek-math-7b-instruct";
417
- readonly description: "DeepSeekMath-Instruct 7B is a mathematically instructed tuning model derived from DeepSeekMath-Base 7B. DeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens.";
418
- readonly tags: readonly [];
419
- readonly properties: {
420
- readonly beta: true;
421
- readonly context_window: 4096;
422
- readonly info: "https://huggingface.co/deepseek-ai/deepseek-math-7b-instruct";
423
- readonly terms: "https://github.com/deepseek-ai/DeepSeek-Math/blob/main/LICENSE-MODEL";
424
- };
425
- }, {
426
- readonly id: "48dd2443-0c61-43b2-8894-22abddf1b081";
427
- readonly source: 1;
428
- readonly name: "@cf/tiiuae/falcon-7b-instruct";
429
- readonly description: "Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets.";
430
- readonly tags: readonly [];
431
- readonly properties: {
432
- readonly beta: true;
433
- readonly context_window: 4096;
434
- readonly info: "https://huggingface.co/tiiuae/falcon-7b-instruct";
435
- };
436
- }, {
437
- readonly id: "44774b85-08c8-4bb8-8d2a-b06ebc538a79";
438
- readonly source: 2;
439
- readonly name: "@hf/nousresearch/hermes-2-pro-mistral-7b";
440
- readonly description: "Hermes 2 Pro on Mistral 7B is the new flagship 7B Hermes! Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.";
441
- readonly tags: readonly [];
442
- readonly properties: {
443
- readonly beta: true;
444
- readonly context_window: 24000;
445
- readonly function_calling: true;
446
- readonly info: "https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B";
447
- };
448
- }, {
449
- readonly id: "41975cc2-c82e-4e98-b7b8-88ffb186a545";
450
- readonly source: 1;
451
- readonly name: "@cf/meta/llama-3.1-8b-instruct";
452
- readonly description: "The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models. The Llama 3.1 instruction tuned text only models are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.";
453
- readonly tags: readonly [];
454
- readonly properties: {
455
- readonly context_window: 7968;
456
- readonly terms: "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE";
457
- };
458
- }, {
459
- readonly id: "3dcb4f2d-26a8-412b-b6e3-2a368beff66b";
460
- readonly source: 1;
461
- readonly name: "@cf/meta/llama-3.1-8b-instruct-awq";
462
- readonly description: "Quantized (int4) generative text model with 8 billion parameters from Meta.\n";
463
- readonly tags: readonly [];
464
- readonly properties: {
465
- readonly context_window: 8192;
466
- readonly terms: "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE";
467
- };
468
- }, {
469
- readonly id: "3976bab8-3810-4ad8-8580-ab1e22de7823";
470
- readonly source: 2;
471
- readonly name: "@hf/thebloke/zephyr-7b-beta-awq";
472
- readonly description: "Zephyr 7B Beta AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Zephyr model variant.";
473
- readonly tags: readonly [];
474
- readonly properties: {
475
- readonly beta: true;
476
- readonly context_window: 4096;
477
- readonly info: "https://huggingface.co/TheBloke/zephyr-7B-beta-AWQ";
478
- };
479
- }, {
480
- readonly id: "337170b7-bd2f-4631-9a57-688b579cf6d3";
481
- readonly source: 1;
482
- readonly name: "@cf/google/gemma-7b-it-lora";
483
- readonly description: " This is a Gemma-7B base model that Cloudflare dedicates for inference with LoRA adapters. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.";
484
- readonly tags: readonly [];
485
- readonly properties: {
486
- readonly beta: true;
487
- readonly context_window: 3500;
488
- readonly lora: true;
489
- };
490
- }, {
491
- readonly id: "3222ddb3-e211-4fd9-9a6d-79a80e47b3a6";
492
- readonly source: 1;
493
- readonly name: "@cf/qwen/qwen1.5-1.8b-chat";
494
- readonly description: "Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.";
495
- readonly tags: readonly [];
496
- readonly properties: {
497
- readonly beta: true;
498
- readonly context_window: 32000;
499
- readonly info: "https://huggingface.co/qwen/qwen1.5-1.8b-chat";
500
- };
501
- }, {
502
- readonly id: "31097538-a3ff-4e6e-bb56-ad0e1f428b61";
503
- readonly source: 1;
504
- readonly name: "@cf/meta/llama-3-8b-instruct-awq";
505
- readonly description: "Quantized (int4) generative text model with 8 billion parameters from Meta.";
506
- readonly tags: readonly [];
507
- readonly properties: {
508
- readonly context_window: 8192;
509
- readonly info: "https://llama.meta.com";
510
- readonly terms: "https://llama.meta.com/llama3/license/#";
511
- };
512
- }, {
513
- readonly id: "2cbc033b-ded8-4e02-bbb2-47cf05d5cfe5";
514
- readonly source: 1;
515
- readonly name: "@cf/meta/llama-3.2-11b-vision-instruct";
516
- readonly description: " The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image.";
517
- readonly tags: readonly [];
518
- readonly properties: {
519
- readonly terms: "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE";
520
- };
521
- }, {
522
- readonly id: "1dc9e589-df6b-4e66-ac9f-ceff42d64983";
523
- readonly source: 1;
524
- readonly name: "@cf/defog/sqlcoder-7b-2";
525
- readonly description: "This model is intended to be used by non-technical users to understand data inside their SQL databases. ";
526
- readonly tags: readonly [];
527
- readonly properties: {
528
- readonly beta: true;
529
- readonly context_window: 10000;
530
- readonly info: "https://huggingface.co/defog/sqlcoder-7b-2";
531
- readonly terms: "https://creativecommons.org/licenses/by-sa/4.0/deed.en";
532
- };
533
- }, {
534
- readonly id: "1d933df3-680f-4280-940d-da87435edb07";
535
- readonly source: 1;
536
- readonly name: "@cf/microsoft/phi-2";
537
- readonly description: "Phi-2 is a Transformer-based model with a next-word prediction objective, trained on 1.4T tokens from multiple passes on a mixture of Synthetic and Web datasets for NLP and coding.";
538
- readonly tags: readonly [];
539
- readonly properties: {
540
- readonly beta: true;
541
- readonly context_window: 2048;
542
- readonly info: "https://huggingface.co/microsoft/phi-2";
543
- };
544
- }, {
545
- readonly id: "1a7b6ad6-9987-4bd3-a329-20ee8de93296";
546
- readonly source: 2;
547
- readonly name: "@hf/meta-llama/meta-llama-3-8b-instruct";
548
- readonly description: "Generation over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.\t";
549
- readonly tags: readonly [];
550
- readonly properties: {
551
- readonly context_window: 8192;
552
- };
553
- }, {
554
- readonly id: "0f002249-7d86-4698-aabf-8529ed86cefb";
555
- readonly source: 2;
556
- readonly name: "@hf/google/gemma-7b-it";
557
- readonly description: "Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights, pre-trained variants, and instruction-tuned variants.";
558
- readonly tags: readonly [];
559
- readonly properties: {
560
- readonly beta: true;
561
- readonly context_window: 8192;
562
- readonly info: "https://ai.google.dev/gemma/docs";
563
- readonly lora: true;
564
- readonly terms: "https://ai.google.dev/gemma/terms";
565
- };
566
- }, {
567
- readonly id: "09d113a9-03c4-420e-b6f2-52ad4b3bed45";
568
- readonly source: 1;
569
- readonly name: "@cf/qwen/qwen1.5-14b-chat-awq";
570
- readonly description: "Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.";
571
- readonly tags: readonly [];
572
- readonly properties: {
573
- readonly beta: true;
574
- readonly context_window: 7500;
575
- readonly info: "https://huggingface.co/qwen/qwen1.5-14b-chat-awq";
576
- };
577
- }, {
578
- readonly id: "081054cd-a254-4349-855e-6dc0996277fa";
579
- readonly source: 1;
580
- readonly name: "@cf/openchat/openchat-3.5-0106";
581
- readonly description: "OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning.";
582
- readonly tags: readonly [];
583
- readonly properties: {
584
- readonly beta: true;
585
- readonly context_window: 8192;
586
- readonly info: "https://huggingface.co/openchat/openchat-3.5-0106";
587
- };
588
- }];
589
- export type type_mc_safety = aiProviders<'Text Generation'>;
590
- export declare const possibilities_mc_embedding: readonly [...{
591
- name: "Azure_OpenAi_Embed3_Large" | "Azure_OpenAi_Embed3_Small";
592
- }[], {
593
- readonly id: "eed32bc1-8775-4985-89ce-dd1405508ad8";
594
- readonly source: 1;
595
- readonly name: "@cf/baai/bge-m3";
596
- readonly description: "Multi-Functionality, Multi-Linguality, and Multi-Granularity embeddings model.";
597
- readonly tags: readonly [];
598
- readonly properties: {};
599
- }, {
600
- readonly id: "57fbd08a-a4c4-411c-910d-b9459ff36c20";
601
- readonly source: 1;
602
- readonly name: "@cf/baai/bge-small-en-v1.5";
603
- readonly description: "BAAI general embedding (Small) model that transforms any given text into a 384-dimensional vector";
604
- readonly tags: readonly [];
605
- readonly properties: {
606
- readonly beta: true;
607
- readonly info: "https://huggingface.co/BAAI/bge-base-en-v1.5";
608
- readonly max_input_tokens: 512;
609
- readonly output_dimensions: 384;
610
- };
611
- }, {
612
- readonly id: "429b9e8b-d99e-44de-91ad-706cf8183658";
613
- readonly source: 1;
614
- readonly name: "@cf/baai/bge-base-en-v1.5";
615
- readonly description: "BAAI general embedding (Base) model that transforms any given text into a 768-dimensional vector";
616
- readonly tags: readonly [];
617
- readonly properties: {
618
- readonly beta: true;
619
- readonly info: "https://huggingface.co/BAAI/bge-base-en-v1.5";
620
- readonly max_input_tokens: 512;
621
- readonly output_dimensions: 768;
622
- };
623
- }, {
624
- readonly id: "01bc2fb0-4bca-4598-b985-d2584a3f46c0";
625
- readonly source: 1;
626
- readonly name: "@cf/baai/bge-large-en-v1.5";
627
- readonly description: "BAAI general embedding (Large) model that transforms any given text into a 1024-dimensional vector";
628
- readonly tags: readonly [];
629
- readonly properties: {
630
- readonly beta: true;
631
- readonly info: "https://huggingface.co/BAAI/bge-base-en-v1.5";
632
- readonly max_input_tokens: 512;
633
- readonly output_dimensions: 1024;
634
- };
635
- }];
636
- export type type_mc_embedding = aiEmbeddingProviders;
637
- export {};
@@ -1,27 +0,0 @@
1
- import { workersAiCatalog } from '../ai-tools/workers-ai-catalog.js';
2
- export var enabledAzureLlmProviders;
3
- (function (enabledAzureLlmProviders) {
4
- enabledAzureLlmProviders["Azure_OpenAi_Gpt3"] = "azure_openai_gpt3";
5
- enabledAzureLlmProviders["Azure_OpenAi_Gpt4o_mini"] = "azure_openai_gpt4o_mini";
6
- enabledAzureLlmProviders["Azure_OpenAi_Gpt4"] = "azure_openai_gpt4";
7
- enabledAzureLlmProviders["Azure_OpenAi_Gpt4o"] = "azure_openai_gpt4o";
8
- })(enabledAzureLlmProviders || (enabledAzureLlmProviders = {}));
9
- export var enabledAzureLlmEmbeddingProviders;
10
- (function (enabledAzureLlmEmbeddingProviders) {
11
- enabledAzureLlmEmbeddingProviders["Azure_OpenAi_Embed3_Large"] = "azure_openai_embed3_large";
12
- enabledAzureLlmEmbeddingProviders["Azure_OpenAi_Embed3_Small"] = "azure_openai_embed3_small";
13
- })(enabledAzureLlmEmbeddingProviders || (enabledAzureLlmEmbeddingProviders = {}));
14
- export const enabledCloudflareLlmSummaryProviders = workersAiCatalog.modelGroups.Summarization.models.map((model) => model.name);
15
- export const enabledCloudflareLlmClassificationProviders = workersAiCatalog.modelGroups['Text Classification'].models.map((model) => model.name);
16
- export const enabledCloudflareLlmEmbeddingProviders = workersAiCatalog.modelGroups['Text Embeddings'].models.map((model) => model.name);
17
- export const enabledCloudflareLlmProviders = workersAiCatalog.modelGroups['Text Generation'].models.map((model) => model.name);
18
- export const enabledCloudflareLlmFunctionProviders = workersAiCatalog.modelGroups['Text Generation'].models.filter((model) => 'function_calling' in model.properties && model.properties.function_calling).map((model) => model.name);
19
- const possibilities_base = [...Object.values(enabledAzureLlmProviders)];
20
- const possibilities_embeddings = [...Object.values(enabledAzureLlmEmbeddingProviders)];
21
- export const possibilities_mc_generic = [...possibilities_base.map((modelName) => ({ name: modelName })), ...workersAiCatalog.modelGroups['Text Generation'].models.filter((model) => 'function_calling' in model.properties && model.properties.function_calling)];
22
- export const possibilities_mc_summary = [...possibilities_base.map((modelName) => ({ name: modelName })), ...workersAiCatalog.modelGroups.Summarization.models];
23
- export const possibilities_mc_extraction = [...possibilities_base.map((modelName) => ({ name: modelName })), ...workersAiCatalog.modelGroups['Text Generation'].models.filter((model) => 'function_calling' in model.properties && model.properties.function_calling)];
24
- export const possibilities_mc_tagging = [...possibilities_base.map((modelName) => ({ name: modelName })), ...workersAiCatalog.modelGroups['Text Generation'].models.filter((model) => 'function_calling' in model.properties && model.properties.function_calling)];
25
- export const possibilities_mc_sentiment = [...possibilities_base.map((modelName) => ({ name: modelName })), ...workersAiCatalog.modelGroups['Text Generation'].models.filter((model) => 'function_calling' in model.properties && model.properties.function_calling)];
26
- export const possibilities_mc_safety = [...possibilities_base.map((modelName) => ({ name: modelName })), ...workersAiCatalog.modelGroups['Text Generation'].models];
27
- export const possibilities_mc_embedding = [...possibilities_embeddings.map((modelName) => ({ name: modelName })), ...workersAiCatalog.modelGroups['Text Embeddings'].models];