1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
|
import { Ollama } from "ollama";
import OpenAI from "openai";
import serverConfig from "./config";
import logger from "./logger";
export interface InferenceResponse {
response: string;
totalTokens: number | undefined;
}
export interface InferenceOptions {
json: boolean;
}
const defaultInferenceOptions: InferenceOptions = {
json: true,
};
export interface InferenceClient {
inferFromText(
prompt: string,
opts: InferenceOptions,
): Promise<InferenceResponse>;
inferFromImage(
prompt: string,
contentType: string,
image: string,
opts: InferenceOptions,
): Promise<InferenceResponse>;
}
export class InferenceClientFactory {
static build(): InferenceClient | null {
if (serverConfig.inference.openAIApiKey) {
return new OpenAIInferenceClient();
}
if (serverConfig.inference.ollamaBaseUrl) {
return new OllamaInferenceClient();
}
return null;
}
}
class OpenAIInferenceClient implements InferenceClient {
openAI: OpenAI;
constructor() {
this.openAI = new OpenAI({
apiKey: serverConfig.inference.openAIApiKey,
baseURL: serverConfig.inference.openAIBaseUrl,
});
}
async inferFromText(
prompt: string,
opts: InferenceOptions = defaultInferenceOptions,
): Promise<InferenceResponse> {
const chatCompletion = await this.openAI.chat.completions.create({
messages: [{ role: "user", content: prompt }],
model: serverConfig.inference.textModel,
response_format: opts.json ? { type: "json_object" } : undefined,
});
const response = chatCompletion.choices[0].message.content;
if (!response) {
throw new Error(`Got no message content from OpenAI`);
}
return { response, totalTokens: chatCompletion.usage?.total_tokens };
}
async inferFromImage(
prompt: string,
contentType: string,
image: string,
opts: InferenceOptions = defaultInferenceOptions,
): Promise<InferenceResponse> {
const chatCompletion = await this.openAI.chat.completions.create({
model: serverConfig.inference.imageModel,
response_format: opts.json ? { type: "json_object" } : undefined,
messages: [
{
role: "user",
content: [
{ type: "text", text: prompt },
{
type: "image_url",
image_url: {
url: `data:${contentType};base64,${image}`,
detail: "low",
},
},
],
},
],
max_tokens: 2000,
});
const response = chatCompletion.choices[0].message.content;
if (!response) {
throw new Error(`Got no message content from OpenAI`);
}
return { response, totalTokens: chatCompletion.usage?.total_tokens };
}
}
class OllamaInferenceClient implements InferenceClient {
ollama: Ollama;
constructor() {
this.ollama = new Ollama({
host: serverConfig.inference.ollamaBaseUrl,
});
}
async runModel(
model: string,
prompt: string,
image?: string,
opts: InferenceOptions = defaultInferenceOptions,
) {
const chatCompletion = await this.ollama.chat({
model: model,
format: opts.json ? "json" : undefined,
stream: true,
keep_alive: serverConfig.inference.ollamaKeepAlive,
options: {
num_ctx: serverConfig.inference.contextLength,
},
messages: [
{ role: "user", content: prompt, images: image ? [image] : undefined },
],
});
let totalTokens = 0;
let response = "";
try {
for await (const part of chatCompletion) {
response += part.message.content;
if (!isNaN(part.eval_count)) {
totalTokens += part.eval_count;
}
if (!isNaN(part.prompt_eval_count)) {
totalTokens += part.prompt_eval_count;
}
}
} catch (e) {
// There seem to be some bug in ollama where you can get some successful response, but still throw an error.
// Using stream + accumulating the response so far is a workaround.
// https://github.com/ollama/ollama-js/issues/72
totalTokens = NaN;
logger.warn(
`Got an exception from ollama, will still attempt to deserialize the response we got so far: ${e}`,
);
}
return { response, totalTokens };
}
async inferFromText(
prompt: string,
opts: InferenceOptions = defaultInferenceOptions,
): Promise<InferenceResponse> {
return await this.runModel(
serverConfig.inference.textModel,
prompt,
undefined,
opts,
);
}
async inferFromImage(
prompt: string,
_contentType: string,
image: string,
opts: InferenceOptions = defaultInferenceOptions,
): Promise<InferenceResponse> {
return await this.runModel(
serverConfig.inference.imageModel,
prompt,
image,
opts,
);
}
}
|
