llama.cpp/examples/server/chat.mjs
Randall Fitzgerald 794db3e7b9
Server Example Refactor and Improvements (#1570)
A major rewrite for the server example.

Note that if you have built something on the previous server API, it will probably be incompatible.
Check out the examples for how a typical chat app could work.

This took a lot of effort, there are 24 PR's closed in the submitter's repo alone, over 160 commits and a lot of comments and testing.

Summary of the changes:

- adds missing generation parameters: tfs_z, typical_p, repeat_last_n, repeat_penalty, presence_penalty, frequency_penalty, mirostat, penalize_nl, seed, ignore_eos
- applies missing top k sampler
- removes interactive mode/terminal-like behavior, removes exclude parameter
- moves threads and batch size to server command-line parameters
- adds LoRA loading and matches command line parameters with main example
- fixes stopping on EOS token and with the specified token amount with n_predict 
- adds server timeouts, host, and port settings
- adds expanded generation complete response; adds generation settings, stop reason, prompt truncated, model used, and final text
- sets defaults for unspecified parameters between requests
- removes /next-token endpoint and as_loop parameter, adds stream parameter and server-sent events for streaming
- adds CORS headers to responses
- adds request logging, exception printing and optional verbose logging
- adds better stopping words handling when matching multiple tokens and while streaming, or when it finishes on a partial stop string
- adds printing an error when it can't bind to the host/port specified
- fixes multi-byte character handling and replaces invalid UTF-8 characters on responses
- prints timing and build info on startup
- adds logit bias to request parameters
- removes embedding mode
- updates documentation; adds streaming Node.js and Bash examples
- fixes code formatting
- sets server threads to 1 since the current global state doesn't work well with simultaneous requests
- adds truncation of the input prompt and better context reset
- removes token limit from the input prompt
- significantly simplified the logic and removed a lot of variables

---------

Co-authored-by: anon998 <131767832+anon998@users.noreply.github.com>
Co-authored-by: Henri Vasserman <henv@hot.ee>
Co-authored-by: Felix Hellmann <privat@cirk2.de>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Co-authored-by: Lesaun Harvey <Lesaun@gmail.com>
2023-06-17 14:53:04 +03:00

89 lines
2.4 KiB
JavaScript

import * as readline from 'node:readline'
import { stdin, stdout } from 'node:process'
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
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)
}