@reverbia/sdk 1.0.0-next.20251117144849 → 1.0.0-next.20251119123747
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/dist/client/index.cjs +8 -0
- package/dist/client/index.d.mts +9 -3
- package/dist/client/index.d.ts +9 -3
- package/dist/client/index.mjs +7 -0
- package/dist/types.gen-Ar4CxyYC.d.mts +433 -0
- package/dist/types.gen-Ar4CxyYC.d.ts +433 -0
- package/dist/vercel/index.d.mts +1 -1
- package/dist/vercel/index.d.ts +1 -1
- package/package.json +2 -2
- package/dist/types.gen-DENXHZhp.d.mts +0 -235
- package/dist/types.gen-DENXHZhp.d.ts +0 -235
package/dist/client/index.cjs
CHANGED
|
@@ -20,6 +20,7 @@ var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: tru
|
|
|
20
20
|
// src/client/index.ts
|
|
21
21
|
var client_exports = {};
|
|
22
22
|
__export(client_exports, {
|
|
23
|
+
getApiV1Models: () => getApiV1Models,
|
|
23
24
|
getHealth: () => getHealth,
|
|
24
25
|
postApiV1ChatCompletions: () => postApiV1ChatCompletions,
|
|
25
26
|
postApiV1Embeddings: () => postApiV1Embeddings
|
|
@@ -861,6 +862,12 @@ var postApiV1Embeddings = (options) => {
|
|
|
861
862
|
}
|
|
862
863
|
});
|
|
863
864
|
};
|
|
865
|
+
var getApiV1Models = (options) => {
|
|
866
|
+
return (options?.client ?? client).get({
|
|
867
|
+
url: "/api/v1/models",
|
|
868
|
+
...options
|
|
869
|
+
});
|
|
870
|
+
};
|
|
864
871
|
var getHealth = (options) => {
|
|
865
872
|
return (options?.client ?? client).get({
|
|
866
873
|
url: "/health",
|
|
@@ -869,6 +876,7 @@ var getHealth = (options) => {
|
|
|
869
876
|
};
|
|
870
877
|
// Annotate the CommonJS export names for ESM import in node:
|
|
871
878
|
0 && (module.exports = {
|
|
879
|
+
getApiV1Models,
|
|
872
880
|
getHealth,
|
|
873
881
|
postApiV1ChatCompletions,
|
|
874
882
|
postApiV1Embeddings
|
package/dist/client/index.d.mts
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
|
-
import { P as PostApiV1ChatCompletionsData, a as PostApiV1ChatCompletionsResponses, b as PostApiV1ChatCompletionsErrors, c as PostApiV1EmbeddingsData, d as PostApiV1EmbeddingsResponses, e as PostApiV1EmbeddingsErrors, G as
|
|
2
|
-
export { C as ClientOptions,
|
|
1
|
+
import { P as PostApiV1ChatCompletionsData, a as PostApiV1ChatCompletionsResponses, b as PostApiV1ChatCompletionsErrors, c as PostApiV1EmbeddingsData, d as PostApiV1EmbeddingsResponses, e as PostApiV1EmbeddingsErrors, G as GetApiV1ModelsData, f as GetApiV1ModelsResponses, g as GetApiV1ModelsErrors, h as GetHealthData, i as GetHealthResponses, j as GetHealthErrors } from '../types.gen-Ar4CxyYC.mjs';
|
|
2
|
+
export { C as ClientOptions, J as GetApiV1ModelsError, K as GetApiV1ModelsResponse, M as GetHealthError, N as GetHealthResponse, H as HandlersHealthResponse, L as LlmapiChatCompletionExtraFields, k as LlmapiChatCompletionRequest, l as LlmapiChatCompletionResponse, m as LlmapiChatCompletionUsage, n as LlmapiChoice, o as LlmapiEmbeddingData, p as LlmapiEmbeddingExtraFields, q as LlmapiEmbeddingRequest, r as LlmapiEmbeddingResponse, s as LlmapiEmbeddingUsage, t as LlmapiMessage, u as LlmapiModel, v as LlmapiModelArchitecture, w as LlmapiModelPerRequestLimits, x as LlmapiModelPricing, y as LlmapiModelTopProvider, z as LlmapiModelsListExtraFields, A as LlmapiModelsListResponse, B as LlmapiRole, D as PostApiV1ChatCompletionsError, E as PostApiV1ChatCompletionsResponse, F as PostApiV1EmbeddingsError, I as PostApiV1EmbeddingsResponse, R as ResponseErrorResponse } from '../types.gen-Ar4CxyYC.mjs';
|
|
3
3
|
|
|
4
4
|
type AuthToken = string | undefined;
|
|
5
5
|
interface Auth {
|
|
@@ -315,6 +315,12 @@ declare const postApiV1ChatCompletions: <ThrowOnError extends boolean = false>(o
|
|
|
315
315
|
* Generates embeddings using the configured gateway.
|
|
316
316
|
*/
|
|
317
317
|
declare const postApiV1Embeddings: <ThrowOnError extends boolean = false>(options: Options<PostApiV1EmbeddingsData, ThrowOnError>) => RequestResult<PostApiV1EmbeddingsResponses, PostApiV1EmbeddingsErrors, ThrowOnError>;
|
|
318
|
+
/**
|
|
319
|
+
* List available models
|
|
320
|
+
*
|
|
321
|
+
* Returns a list of all available models from the configured gateway with optional filters.
|
|
322
|
+
*/
|
|
323
|
+
declare const getApiV1Models: <ThrowOnError extends boolean = false>(options?: Options<GetApiV1ModelsData, ThrowOnError>) => RequestResult<GetApiV1ModelsResponses, GetApiV1ModelsErrors, ThrowOnError>;
|
|
318
324
|
/**
|
|
319
325
|
* Health check
|
|
320
326
|
*
|
|
@@ -322,4 +328,4 @@ declare const postApiV1Embeddings: <ThrowOnError extends boolean = false>(option
|
|
|
322
328
|
*/
|
|
323
329
|
declare const getHealth: <ThrowOnError extends boolean = false>(options?: Options<GetHealthData, ThrowOnError>) => RequestResult<GetHealthResponses, GetHealthErrors, ThrowOnError>;
|
|
324
330
|
|
|
325
|
-
export { GetHealthData, GetHealthErrors, GetHealthResponses, type Options, PostApiV1ChatCompletionsData, PostApiV1ChatCompletionsErrors, PostApiV1ChatCompletionsResponses, PostApiV1EmbeddingsData, PostApiV1EmbeddingsErrors, PostApiV1EmbeddingsResponses, getHealth, postApiV1ChatCompletions, postApiV1Embeddings };
|
|
331
|
+
export { GetApiV1ModelsData, GetApiV1ModelsErrors, GetApiV1ModelsResponses, GetHealthData, GetHealthErrors, GetHealthResponses, type Options, PostApiV1ChatCompletionsData, PostApiV1ChatCompletionsErrors, PostApiV1ChatCompletionsResponses, PostApiV1EmbeddingsData, PostApiV1EmbeddingsErrors, PostApiV1EmbeddingsResponses, getApiV1Models, getHealth, postApiV1ChatCompletions, postApiV1Embeddings };
|
package/dist/client/index.d.ts
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
|
-
import { P as PostApiV1ChatCompletionsData, a as PostApiV1ChatCompletionsResponses, b as PostApiV1ChatCompletionsErrors, c as PostApiV1EmbeddingsData, d as PostApiV1EmbeddingsResponses, e as PostApiV1EmbeddingsErrors, G as
|
|
2
|
-
export { C as ClientOptions,
|
|
1
|
+
import { P as PostApiV1ChatCompletionsData, a as PostApiV1ChatCompletionsResponses, b as PostApiV1ChatCompletionsErrors, c as PostApiV1EmbeddingsData, d as PostApiV1EmbeddingsResponses, e as PostApiV1EmbeddingsErrors, G as GetApiV1ModelsData, f as GetApiV1ModelsResponses, g as GetApiV1ModelsErrors, h as GetHealthData, i as GetHealthResponses, j as GetHealthErrors } from '../types.gen-Ar4CxyYC.js';
|
|
2
|
+
export { C as ClientOptions, J as GetApiV1ModelsError, K as GetApiV1ModelsResponse, M as GetHealthError, N as GetHealthResponse, H as HandlersHealthResponse, L as LlmapiChatCompletionExtraFields, k as LlmapiChatCompletionRequest, l as LlmapiChatCompletionResponse, m as LlmapiChatCompletionUsage, n as LlmapiChoice, o as LlmapiEmbeddingData, p as LlmapiEmbeddingExtraFields, q as LlmapiEmbeddingRequest, r as LlmapiEmbeddingResponse, s as LlmapiEmbeddingUsage, t as LlmapiMessage, u as LlmapiModel, v as LlmapiModelArchitecture, w as LlmapiModelPerRequestLimits, x as LlmapiModelPricing, y as LlmapiModelTopProvider, z as LlmapiModelsListExtraFields, A as LlmapiModelsListResponse, B as LlmapiRole, D as PostApiV1ChatCompletionsError, E as PostApiV1ChatCompletionsResponse, F as PostApiV1EmbeddingsError, I as PostApiV1EmbeddingsResponse, R as ResponseErrorResponse } from '../types.gen-Ar4CxyYC.js';
|
|
3
3
|
|
|
4
4
|
type AuthToken = string | undefined;
|
|
5
5
|
interface Auth {
|
|
@@ -315,6 +315,12 @@ declare const postApiV1ChatCompletions: <ThrowOnError extends boolean = false>(o
|
|
|
315
315
|
* Generates embeddings using the configured gateway.
|
|
316
316
|
*/
|
|
317
317
|
declare const postApiV1Embeddings: <ThrowOnError extends boolean = false>(options: Options<PostApiV1EmbeddingsData, ThrowOnError>) => RequestResult<PostApiV1EmbeddingsResponses, PostApiV1EmbeddingsErrors, ThrowOnError>;
|
|
318
|
+
/**
|
|
319
|
+
* List available models
|
|
320
|
+
*
|
|
321
|
+
* Returns a list of all available models from the configured gateway with optional filters.
|
|
322
|
+
*/
|
|
323
|
+
declare const getApiV1Models: <ThrowOnError extends boolean = false>(options?: Options<GetApiV1ModelsData, ThrowOnError>) => RequestResult<GetApiV1ModelsResponses, GetApiV1ModelsErrors, ThrowOnError>;
|
|
318
324
|
/**
|
|
319
325
|
* Health check
|
|
320
326
|
*
|
|
@@ -322,4 +328,4 @@ declare const postApiV1Embeddings: <ThrowOnError extends boolean = false>(option
|
|
|
322
328
|
*/
|
|
323
329
|
declare const getHealth: <ThrowOnError extends boolean = false>(options?: Options<GetHealthData, ThrowOnError>) => RequestResult<GetHealthResponses, GetHealthErrors, ThrowOnError>;
|
|
324
330
|
|
|
325
|
-
export { GetHealthData, GetHealthErrors, GetHealthResponses, type Options, PostApiV1ChatCompletionsData, PostApiV1ChatCompletionsErrors, PostApiV1ChatCompletionsResponses, PostApiV1EmbeddingsData, PostApiV1EmbeddingsErrors, PostApiV1EmbeddingsResponses, getHealth, postApiV1ChatCompletions, postApiV1Embeddings };
|
|
331
|
+
export { GetApiV1ModelsData, GetApiV1ModelsErrors, GetApiV1ModelsResponses, GetHealthData, GetHealthErrors, GetHealthResponses, type Options, PostApiV1ChatCompletionsData, PostApiV1ChatCompletionsErrors, PostApiV1ChatCompletionsResponses, PostApiV1EmbeddingsData, PostApiV1EmbeddingsErrors, PostApiV1EmbeddingsResponses, getApiV1Models, getHealth, postApiV1ChatCompletions, postApiV1Embeddings };
|
package/dist/client/index.mjs
CHANGED
|
@@ -833,6 +833,12 @@ var postApiV1Embeddings = (options) => {
|
|
|
833
833
|
}
|
|
834
834
|
});
|
|
835
835
|
};
|
|
836
|
+
var getApiV1Models = (options) => {
|
|
837
|
+
return (options?.client ?? client).get({
|
|
838
|
+
url: "/api/v1/models",
|
|
839
|
+
...options
|
|
840
|
+
});
|
|
841
|
+
};
|
|
836
842
|
var getHealth = (options) => {
|
|
837
843
|
return (options?.client ?? client).get({
|
|
838
844
|
url: "/health",
|
|
@@ -840,6 +846,7 @@ var getHealth = (options) => {
|
|
|
840
846
|
});
|
|
841
847
|
};
|
|
842
848
|
export {
|
|
849
|
+
getApiV1Models,
|
|
843
850
|
getHealth,
|
|
844
851
|
postApiV1ChatCompletions,
|
|
845
852
|
postApiV1Embeddings
|
|
@@ -0,0 +1,433 @@
|
|
|
1
|
+
type ClientOptions = {
|
|
2
|
+
baseUrl: `${string}://${string}` | (string & {});
|
|
3
|
+
};
|
|
4
|
+
type HandlersHealthResponse = {
|
|
5
|
+
/**
|
|
6
|
+
* Status indicates the service health status
|
|
7
|
+
*/
|
|
8
|
+
status?: string;
|
|
9
|
+
/**
|
|
10
|
+
* Timestamp is the Unix timestamp of the response
|
|
11
|
+
*/
|
|
12
|
+
timestamp?: number;
|
|
13
|
+
/**
|
|
14
|
+
* Version is the current API version
|
|
15
|
+
*/
|
|
16
|
+
version?: string;
|
|
17
|
+
};
|
|
18
|
+
/**
|
|
19
|
+
* ExtraFields contains additional metadata
|
|
20
|
+
*/
|
|
21
|
+
type LlmapiChatCompletionExtraFields = {
|
|
22
|
+
/**
|
|
23
|
+
* Latency is the request latency in milliseconds
|
|
24
|
+
*/
|
|
25
|
+
latency?: number;
|
|
26
|
+
/**
|
|
27
|
+
* ModelRequested is the model that was requested
|
|
28
|
+
*/
|
|
29
|
+
model_requested?: string;
|
|
30
|
+
/**
|
|
31
|
+
* Provider is the LLM provider used (e.g., "openai", "anthropic")
|
|
32
|
+
*/
|
|
33
|
+
provider?: string;
|
|
34
|
+
/**
|
|
35
|
+
* RequestType is always "chat_completion"
|
|
36
|
+
*/
|
|
37
|
+
request_type?: string;
|
|
38
|
+
};
|
|
39
|
+
type LlmapiChatCompletionRequest = {
|
|
40
|
+
/**
|
|
41
|
+
* Messages is the conversation history
|
|
42
|
+
*/
|
|
43
|
+
messages?: Array<LlmapiMessage>;
|
|
44
|
+
/**
|
|
45
|
+
* Model is the model identifier
|
|
46
|
+
*/
|
|
47
|
+
model?: string;
|
|
48
|
+
/**
|
|
49
|
+
* Stream indicates if response should be streamed
|
|
50
|
+
*/
|
|
51
|
+
stream?: boolean;
|
|
52
|
+
};
|
|
53
|
+
type LlmapiChatCompletionResponse = {
|
|
54
|
+
/**
|
|
55
|
+
* Choices contains the completion choices
|
|
56
|
+
*/
|
|
57
|
+
choices?: Array<LlmapiChoice>;
|
|
58
|
+
extra_fields?: LlmapiChatCompletionExtraFields;
|
|
59
|
+
/**
|
|
60
|
+
* ID is the completion ID
|
|
61
|
+
*/
|
|
62
|
+
id?: string;
|
|
63
|
+
/**
|
|
64
|
+
* Model is the model used
|
|
65
|
+
*/
|
|
66
|
+
model?: string;
|
|
67
|
+
usage?: LlmapiChatCompletionUsage;
|
|
68
|
+
};
|
|
69
|
+
/**
|
|
70
|
+
* Usage contains token usage information
|
|
71
|
+
*/
|
|
72
|
+
type LlmapiChatCompletionUsage = {
|
|
73
|
+
/**
|
|
74
|
+
* CompletionTokens is the number of tokens in the completion
|
|
75
|
+
*/
|
|
76
|
+
completion_tokens?: number;
|
|
77
|
+
/**
|
|
78
|
+
* PromptTokens is the number of tokens in the prompt
|
|
79
|
+
*/
|
|
80
|
+
prompt_tokens?: number;
|
|
81
|
+
/**
|
|
82
|
+
* TotalTokens is the total number of tokens used
|
|
83
|
+
*/
|
|
84
|
+
total_tokens?: number;
|
|
85
|
+
};
|
|
86
|
+
type LlmapiChoice = {
|
|
87
|
+
/**
|
|
88
|
+
* FinishReason indicates why the completion stopped
|
|
89
|
+
*/
|
|
90
|
+
finish_reason?: string;
|
|
91
|
+
/**
|
|
92
|
+
* Index is the choice index
|
|
93
|
+
*/
|
|
94
|
+
index?: number;
|
|
95
|
+
message?: LlmapiMessage;
|
|
96
|
+
};
|
|
97
|
+
type LlmapiEmbeddingData = {
|
|
98
|
+
/**
|
|
99
|
+
* Embedding vector
|
|
100
|
+
*/
|
|
101
|
+
embedding?: Array<number>;
|
|
102
|
+
/**
|
|
103
|
+
* Index of the embedding
|
|
104
|
+
*/
|
|
105
|
+
index?: number;
|
|
106
|
+
/**
|
|
107
|
+
* Object type identifier
|
|
108
|
+
*/
|
|
109
|
+
object?: string;
|
|
110
|
+
};
|
|
111
|
+
/**
|
|
112
|
+
* ExtraFields contains additional metadata
|
|
113
|
+
*/
|
|
114
|
+
type LlmapiEmbeddingExtraFields = {
|
|
115
|
+
/**
|
|
116
|
+
* ChunkIndex is the chunk index (0 for single requests)
|
|
117
|
+
*/
|
|
118
|
+
chunk_index?: number;
|
|
119
|
+
/**
|
|
120
|
+
* Latency is the request latency in milliseconds
|
|
121
|
+
*/
|
|
122
|
+
latency?: number;
|
|
123
|
+
/**
|
|
124
|
+
* ModelRequested is the model that was requested
|
|
125
|
+
*/
|
|
126
|
+
model_requested?: string;
|
|
127
|
+
/**
|
|
128
|
+
* Provider is the LLM provider used (e.g., "openai", "anthropic")
|
|
129
|
+
*/
|
|
130
|
+
provider?: string;
|
|
131
|
+
/**
|
|
132
|
+
* RequestType is always "embedding"
|
|
133
|
+
*/
|
|
134
|
+
request_type?: string;
|
|
135
|
+
};
|
|
136
|
+
type LlmapiEmbeddingRequest = {
|
|
137
|
+
/**
|
|
138
|
+
* Dimensions is the number of dimensions the resulting output embeddings should have (optional)
|
|
139
|
+
*/
|
|
140
|
+
dimensions?: number;
|
|
141
|
+
/**
|
|
142
|
+
* EncodingFormat is the format to return the embeddings in (optional: "float" or "base64")
|
|
143
|
+
*/
|
|
144
|
+
encoding_format?: string;
|
|
145
|
+
/**
|
|
146
|
+
* Input text or tokens to embed (can be string, []string, []int, or [][]int)
|
|
147
|
+
*/
|
|
148
|
+
input?: unknown;
|
|
149
|
+
/**
|
|
150
|
+
* Model identifier in 'provider/model' format
|
|
151
|
+
*/
|
|
152
|
+
model?: string;
|
|
153
|
+
};
|
|
154
|
+
type LlmapiEmbeddingResponse = {
|
|
155
|
+
/**
|
|
156
|
+
* Data contains the embeddings
|
|
157
|
+
*/
|
|
158
|
+
data?: Array<LlmapiEmbeddingData>;
|
|
159
|
+
extra_fields?: LlmapiEmbeddingExtraFields;
|
|
160
|
+
/**
|
|
161
|
+
* Model is the model used
|
|
162
|
+
*/
|
|
163
|
+
model?: string;
|
|
164
|
+
/**
|
|
165
|
+
* Object is always "list"
|
|
166
|
+
*/
|
|
167
|
+
object?: string;
|
|
168
|
+
usage?: LlmapiEmbeddingUsage;
|
|
169
|
+
};
|
|
170
|
+
/**
|
|
171
|
+
* Usage contains token usage information
|
|
172
|
+
*/
|
|
173
|
+
type LlmapiEmbeddingUsage = {
|
|
174
|
+
/**
|
|
175
|
+
* PromptTokens is the number of tokens in the prompt
|
|
176
|
+
*/
|
|
177
|
+
prompt_tokens?: number;
|
|
178
|
+
/**
|
|
179
|
+
* TotalTokens is the total number of tokens used
|
|
180
|
+
*/
|
|
181
|
+
total_tokens?: number;
|
|
182
|
+
};
|
|
183
|
+
/**
|
|
184
|
+
* Message is the generated message
|
|
185
|
+
*/
|
|
186
|
+
type LlmapiMessage = {
|
|
187
|
+
/**
|
|
188
|
+
* Content is the message content
|
|
189
|
+
*/
|
|
190
|
+
content?: string;
|
|
191
|
+
role?: LlmapiRole;
|
|
192
|
+
};
|
|
193
|
+
type LlmapiModel = {
|
|
194
|
+
architecture?: LlmapiModelArchitecture;
|
|
195
|
+
/**
|
|
196
|
+
* CanonicalSlug is the canonical slug for the model
|
|
197
|
+
*/
|
|
198
|
+
canonical_slug?: string;
|
|
199
|
+
/**
|
|
200
|
+
* ContextLength is the maximum context length in tokens
|
|
201
|
+
*/
|
|
202
|
+
context_length?: number;
|
|
203
|
+
/**
|
|
204
|
+
* Created is the Unix timestamp of when the model was created
|
|
205
|
+
*/
|
|
206
|
+
created?: number;
|
|
207
|
+
/**
|
|
208
|
+
* DefaultParameters contains default parameter values
|
|
209
|
+
*/
|
|
210
|
+
default_parameters?: {
|
|
211
|
+
[key: string]: unknown;
|
|
212
|
+
};
|
|
213
|
+
/**
|
|
214
|
+
* Description describes the model and its capabilities
|
|
215
|
+
*/
|
|
216
|
+
description?: string;
|
|
217
|
+
/**
|
|
218
|
+
* HuggingFaceID is the Hugging Face model identifier
|
|
219
|
+
*/
|
|
220
|
+
hugging_face_id?: string;
|
|
221
|
+
/**
|
|
222
|
+
* ID is the model identifier (e.g., "openai/gpt-4")
|
|
223
|
+
*/
|
|
224
|
+
id?: string;
|
|
225
|
+
/**
|
|
226
|
+
* MaxInputTokens is the maximum input tokens
|
|
227
|
+
*/
|
|
228
|
+
max_input_tokens?: number;
|
|
229
|
+
/**
|
|
230
|
+
* MaxOutputTokens is the maximum output tokens
|
|
231
|
+
*/
|
|
232
|
+
max_output_tokens?: number;
|
|
233
|
+
/**
|
|
234
|
+
* Name is the human-readable model name (optional)
|
|
235
|
+
*/
|
|
236
|
+
name?: string;
|
|
237
|
+
/**
|
|
238
|
+
* OwnedBy is the organization that owns the model
|
|
239
|
+
*/
|
|
240
|
+
owned_by?: string;
|
|
241
|
+
per_request_limits?: LlmapiModelPerRequestLimits;
|
|
242
|
+
pricing?: LlmapiModelPricing;
|
|
243
|
+
/**
|
|
244
|
+
* SupportedMethods is a list of supported API methods
|
|
245
|
+
*/
|
|
246
|
+
supported_methods?: Array<string>;
|
|
247
|
+
/**
|
|
248
|
+
* SupportedParameters is a list of supported parameter names
|
|
249
|
+
*/
|
|
250
|
+
supported_parameters?: Array<string>;
|
|
251
|
+
top_provider?: LlmapiModelTopProvider;
|
|
252
|
+
};
|
|
253
|
+
/**
|
|
254
|
+
* Architecture describes the model's technical capabilities
|
|
255
|
+
*/
|
|
256
|
+
type LlmapiModelArchitecture = {
|
|
257
|
+
instruct_type?: string;
|
|
258
|
+
modality?: string;
|
|
259
|
+
prompt_formatting?: string;
|
|
260
|
+
tokenizer?: string;
|
|
261
|
+
};
|
|
262
|
+
/**
|
|
263
|
+
* PerRequestLimits contains rate limiting information
|
|
264
|
+
*/
|
|
265
|
+
type LlmapiModelPerRequestLimits = {
|
|
266
|
+
completion_tokens?: number;
|
|
267
|
+
prompt_tokens?: number;
|
|
268
|
+
};
|
|
269
|
+
/**
|
|
270
|
+
* Pricing contains the pricing structure for using this model
|
|
271
|
+
*/
|
|
272
|
+
type LlmapiModelPricing = {
|
|
273
|
+
completion?: string;
|
|
274
|
+
image?: string;
|
|
275
|
+
prompt?: string;
|
|
276
|
+
request?: string;
|
|
277
|
+
};
|
|
278
|
+
/**
|
|
279
|
+
* TopProvider contains configuration details for the primary provider
|
|
280
|
+
*/
|
|
281
|
+
type LlmapiModelTopProvider = {
|
|
282
|
+
context_length?: number;
|
|
283
|
+
is_moderated?: boolean;
|
|
284
|
+
max_completion_tokens?: number;
|
|
285
|
+
};
|
|
286
|
+
/**
|
|
287
|
+
* ExtraFields contains additional metadata
|
|
288
|
+
*/
|
|
289
|
+
type LlmapiModelsListExtraFields = {
|
|
290
|
+
/**
|
|
291
|
+
* ChunkIndex is the chunk index (0 for single requests)
|
|
292
|
+
*/
|
|
293
|
+
chunk_index?: number;
|
|
294
|
+
/**
|
|
295
|
+
* Latency is the request latency in milliseconds
|
|
296
|
+
*/
|
|
297
|
+
latency?: number;
|
|
298
|
+
/**
|
|
299
|
+
* RequestType is always "list_models"
|
|
300
|
+
*/
|
|
301
|
+
request_type?: string;
|
|
302
|
+
};
|
|
303
|
+
type LlmapiModelsListResponse = {
|
|
304
|
+
/**
|
|
305
|
+
* Data contains the list of available models
|
|
306
|
+
*/
|
|
307
|
+
data?: Array<LlmapiModel>;
|
|
308
|
+
extra_fields?: LlmapiModelsListExtraFields;
|
|
309
|
+
/**
|
|
310
|
+
* NextPageToken is the token to retrieve the next page of results (omitted if no more pages)
|
|
311
|
+
*/
|
|
312
|
+
next_page_token?: string;
|
|
313
|
+
};
|
|
314
|
+
/**
|
|
315
|
+
* Role is the message role (system, user, assistant)
|
|
316
|
+
*/
|
|
317
|
+
type LlmapiRole = string;
|
|
318
|
+
type ResponseErrorResponse = {
|
|
319
|
+
error?: string;
|
|
320
|
+
};
|
|
321
|
+
type PostApiV1ChatCompletionsData = {
|
|
322
|
+
/**
|
|
323
|
+
* Chat completion request
|
|
324
|
+
*/
|
|
325
|
+
body: LlmapiChatCompletionRequest;
|
|
326
|
+
path?: never;
|
|
327
|
+
query?: never;
|
|
328
|
+
url: '/api/v1/chat/completions';
|
|
329
|
+
};
|
|
330
|
+
type PostApiV1ChatCompletionsErrors = {
|
|
331
|
+
/**
|
|
332
|
+
* Bad Request
|
|
333
|
+
*/
|
|
334
|
+
400: ResponseErrorResponse;
|
|
335
|
+
/**
|
|
336
|
+
* Internal Server Error
|
|
337
|
+
*/
|
|
338
|
+
500: ResponseErrorResponse;
|
|
339
|
+
};
|
|
340
|
+
type PostApiV1ChatCompletionsError = PostApiV1ChatCompletionsErrors[keyof PostApiV1ChatCompletionsErrors];
|
|
341
|
+
type PostApiV1ChatCompletionsResponses = {
|
|
342
|
+
/**
|
|
343
|
+
* OK
|
|
344
|
+
*/
|
|
345
|
+
200: LlmapiChatCompletionResponse;
|
|
346
|
+
};
|
|
347
|
+
type PostApiV1ChatCompletionsResponse = PostApiV1ChatCompletionsResponses[keyof PostApiV1ChatCompletionsResponses];
|
|
348
|
+
type PostApiV1EmbeddingsData = {
|
|
349
|
+
/**
|
|
350
|
+
* Embedding request
|
|
351
|
+
*/
|
|
352
|
+
body: LlmapiEmbeddingRequest;
|
|
353
|
+
path?: never;
|
|
354
|
+
query?: never;
|
|
355
|
+
url: '/api/v1/embeddings';
|
|
356
|
+
};
|
|
357
|
+
type PostApiV1EmbeddingsErrors = {
|
|
358
|
+
/**
|
|
359
|
+
* Bad Request
|
|
360
|
+
*/
|
|
361
|
+
400: ResponseErrorResponse;
|
|
362
|
+
/**
|
|
363
|
+
* Internal Server Error
|
|
364
|
+
*/
|
|
365
|
+
500: ResponseErrorResponse;
|
|
366
|
+
};
|
|
367
|
+
type PostApiV1EmbeddingsError = PostApiV1EmbeddingsErrors[keyof PostApiV1EmbeddingsErrors];
|
|
368
|
+
type PostApiV1EmbeddingsResponses = {
|
|
369
|
+
/**
|
|
370
|
+
* OK
|
|
371
|
+
*/
|
|
372
|
+
200: LlmapiEmbeddingResponse;
|
|
373
|
+
};
|
|
374
|
+
type PostApiV1EmbeddingsResponse = PostApiV1EmbeddingsResponses[keyof PostApiV1EmbeddingsResponses];
|
|
375
|
+
type GetApiV1ModelsData = {
|
|
376
|
+
body?: never;
|
|
377
|
+
path?: never;
|
|
378
|
+
query?: {
|
|
379
|
+
/**
|
|
380
|
+
* Filter by provider (e.g., openai, anthropic)
|
|
381
|
+
*/
|
|
382
|
+
provider?: string;
|
|
383
|
+
/**
|
|
384
|
+
* Number of models to return per page
|
|
385
|
+
*/
|
|
386
|
+
page_size?: number;
|
|
387
|
+
/**
|
|
388
|
+
* Token to get next page of results
|
|
389
|
+
*/
|
|
390
|
+
page_token?: string;
|
|
391
|
+
};
|
|
392
|
+
url: '/api/v1/models';
|
|
393
|
+
};
|
|
394
|
+
type GetApiV1ModelsErrors = {
|
|
395
|
+
/**
|
|
396
|
+
* Bad Request
|
|
397
|
+
*/
|
|
398
|
+
400: ResponseErrorResponse;
|
|
399
|
+
/**
|
|
400
|
+
* Internal Server Error
|
|
401
|
+
*/
|
|
402
|
+
500: ResponseErrorResponse;
|
|
403
|
+
};
|
|
404
|
+
type GetApiV1ModelsError = GetApiV1ModelsErrors[keyof GetApiV1ModelsErrors];
|
|
405
|
+
type GetApiV1ModelsResponses = {
|
|
406
|
+
/**
|
|
407
|
+
* OK
|
|
408
|
+
*/
|
|
409
|
+
200: LlmapiModelsListResponse;
|
|
410
|
+
};
|
|
411
|
+
type GetApiV1ModelsResponse = GetApiV1ModelsResponses[keyof GetApiV1ModelsResponses];
|
|
412
|
+
type GetHealthData = {
|
|
413
|
+
body?: never;
|
|
414
|
+
path?: never;
|
|
415
|
+
query?: never;
|
|
416
|
+
url: '/health';
|
|
417
|
+
};
|
|
418
|
+
type GetHealthErrors = {
|
|
419
|
+
/**
|
|
420
|
+
* Internal Server Error
|
|
421
|
+
*/
|
|
422
|
+
500: ResponseErrorResponse;
|
|
423
|
+
};
|
|
424
|
+
type GetHealthError = GetHealthErrors[keyof GetHealthErrors];
|
|
425
|
+
type GetHealthResponses = {
|
|
426
|
+
/**
|
|
427
|
+
* OK
|
|
428
|
+
*/
|
|
429
|
+
200: HandlersHealthResponse;
|
|
430
|
+
};
|
|
431
|
+
type GetHealthResponse = GetHealthResponses[keyof GetHealthResponses];
|
|
432
|
+
|
|
433
|
+
export type { LlmapiModelsListResponse as A, LlmapiRole as B, ClientOptions as C, PostApiV1ChatCompletionsError as D, PostApiV1ChatCompletionsResponse as E, PostApiV1EmbeddingsError as F, GetApiV1ModelsData as G, HandlersHealthResponse as H, PostApiV1EmbeddingsResponse as I, GetApiV1ModelsError as J, GetApiV1ModelsResponse as K, LlmapiChatCompletionExtraFields as L, GetHealthError as M, GetHealthResponse as N, PostApiV1ChatCompletionsData as P, ResponseErrorResponse as R, PostApiV1ChatCompletionsResponses as a, PostApiV1ChatCompletionsErrors as b, PostApiV1EmbeddingsData as c, PostApiV1EmbeddingsResponses as d, PostApiV1EmbeddingsErrors as e, GetApiV1ModelsResponses as f, GetApiV1ModelsErrors as g, GetHealthData as h, GetHealthResponses as i, GetHealthErrors as j, LlmapiChatCompletionRequest as k, LlmapiChatCompletionResponse as l, LlmapiChatCompletionUsage as m, LlmapiChoice as n, LlmapiEmbeddingData as o, LlmapiEmbeddingExtraFields as p, LlmapiEmbeddingRequest as q, LlmapiEmbeddingResponse as r, LlmapiEmbeddingUsage as s, LlmapiMessage as t, LlmapiModel as u, LlmapiModelArchitecture as v, LlmapiModelPerRequestLimits as w, LlmapiModelPricing as x, LlmapiModelTopProvider as y, LlmapiModelsListExtraFields as z };
|