mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-10-30 14:40:16 +01:00
5517d6e692
* server : implement json-schema-to-grammar.mjs by follow python impl * server : add grammar support in chat.mjs * server : implement grammer param in the UI * server : generate .hpp * server : remove trailing whitespaces * server : generate .hpp * server : fix sort of prop pairs * server : optimize regex & iteration
120 lines
3.4 KiB
JavaScript
120 lines
3.4 KiB
JavaScript
import * as readline from 'node:readline'
|
|
import { stdin, stdout } from 'node:process'
|
|
import { readFileSync } from 'node:fs'
|
|
import { SchemaConverter } from './public/json-schema-to-grammar.mjs'
|
|
|
|
const args = process.argv.slice(2);
|
|
const grammarJsonSchemaFile = args.find(
|
|
(_, index) => args[index - 1] === "--grammar-json-schema"
|
|
);
|
|
const grammarFile = args.find((_, index) => args[index - 1] === "--grammar");
|
|
|
|
// Example usage: function,arguments
|
|
const grammarJsonSchemaPropOrder = args.find(
|
|
(_, index) => args[index - 1] === "--grammar-json-schema-prop-order"
|
|
);
|
|
const propOrder = grammarJsonSchemaPropOrder
|
|
? grammarJsonSchemaPropOrder
|
|
.split(",")
|
|
.reduce((acc, cur, index) => ({ ...acc, [cur]: index }), {})
|
|
: {};
|
|
|
|
let grammar = null
|
|
if (grammarJsonSchemaFile) {
|
|
const schema = JSON.parse(readFileSync(grammarJsonSchemaFile, 'utf-8'))
|
|
const converter = new SchemaConverter(propOrder)
|
|
converter.visit(schema, '')
|
|
grammar = converter.formatGrammar()
|
|
}
|
|
if (grammarFile) {
|
|
grammar = readFileSync(grammarFile, 'utf-8')
|
|
}
|
|
|
|
const API_URL = 'http://127.0.0.1:8080'
|
|
|
|
const chat = [
|
|
{
|
|
human: "Hello, Assistant.",
|
|
assistant: "Hello. How may I help you today?"
|
|
},
|
|
{
|
|
human: "Please tell me the largest city in Europe.",
|
|
assistant: "Sure. The largest city in Europe is Moscow, the capital of Russia."
|
|
},
|
|
]
|
|
|
|
const instruction = `A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.`
|
|
|
|
function format_prompt(question) {
|
|
return `${instruction}\n${
|
|
chat.map(m =>`### Human: ${m.human}\n### Assistant: ${m.assistant}`).join("\n")
|
|
}\n### Human: ${question}\n### Assistant:`
|
|
}
|
|
|
|
async function tokenize(content) {
|
|
const result = await fetch(`${API_URL}/tokenize`, {
|
|
method: 'POST',
|
|
body: JSON.stringify({ content })
|
|
})
|
|
|
|
if (!result.ok) {
|
|
return []
|
|
}
|
|
|
|
return await result.json().tokens
|
|
}
|
|
|
|
const n_keep = await tokenize(instruction).length
|
|
|
|
async function chat_completion(question) {
|
|
const result = await fetch(`${API_URL}/completion`, {
|
|
method: 'POST',
|
|
body: JSON.stringify({
|
|
prompt: format_prompt(question),
|
|
temperature: 0.2,
|
|
top_k: 40,
|
|
top_p: 0.9,
|
|
n_keep: n_keep,
|
|
n_predict: 256,
|
|
stop: ["\n### Human:"], // stop completion after generating this
|
|
grammar,
|
|
stream: true,
|
|
})
|
|
})
|
|
|
|
if (!result.ok) {
|
|
return
|
|
}
|
|
|
|
let answer = ''
|
|
|
|
for await (var chunk of result.body) {
|
|
const t = Buffer.from(chunk).toString('utf8')
|
|
if (t.startsWith('data: ')) {
|
|
const message = JSON.parse(t.substring(6))
|
|
answer += message.content
|
|
process.stdout.write(message.content)
|
|
if (message.stop) {
|
|
if (message.truncated) {
|
|
chat.shift()
|
|
}
|
|
break
|
|
}
|
|
}
|
|
}
|
|
|
|
process.stdout.write('\n')
|
|
chat.push({ human: question, assistant: answer.trimStart() })
|
|
}
|
|
|
|
const rl = readline.createInterface({ input: stdin, output: stdout });
|
|
|
|
const readlineQuestion = (rl, query, options) => new Promise((resolve, reject) => {
|
|
rl.question(query, options, resolve)
|
|
});
|
|
|
|
while(true) {
|
|
const question = await readlineQuestion(rl, '> ')
|
|
await chat_completion(question)
|
|
}
|