llama.cpp/examples/server/chat.sh
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

78 lines
1.8 KiB
Bash

#!/bin/bash
API_URL="${API_URL:-http://127.0.0.1:8080}"
CHAT=(
"Hello, Assistant."
"Hello. How may I help you today?"
"Please tell me the largest city in Europe."
"Sure. The largest city in Europe is Moscow, the capital of Russia."
)
INSTRUCTION="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions."
trim() {
shopt -s extglob
set -- "${1##+([[:space:]])}"
printf "%s" "${1%%+([[:space:]])}"
}
trim_trailing() {
shopt -s extglob
printf "%s" "${1%%+([[:space:]])}"
}
format_prompt() {
echo -n "${INSTRUCTION}"
printf "\n### Human: %s\n### Assistant: %s" "${CHAT[@]}" "$1"
}
tokenize() {
curl \
--silent \
--request POST \
--url "${API_URL}/tokenize" \
--data-raw "$(jq -ns --arg content "$1" '{content:$content}')" \
| jq '.tokens[]'
}
N_KEEP=$(tokenize "${INSTRUCTION}" | wc -l)
chat_completion() {
PROMPT="$(trim_trailing "$(format_prompt "$1")")"
DATA="$(echo -n "$PROMPT" | jq -Rs --argjson n_keep $N_KEEP '{
prompt: .,
temperature: 0.2,
top_k: 40,
top_p: 0.9,
n_keep: $n_keep,
n_predict: 256,
stop: ["\n### Human:"],
stream: true
}')"
ANSWER=''
while IFS= read -r LINE; do
if [[ $LINE = data:* ]]; then
CONTENT="$(echo "${LINE:5}" | jq -r '.content')"
printf "%s" "${CONTENT}"
ANSWER+="${CONTENT}"
fi
done < <(curl \
--silent \
--no-buffer \
--request POST \
--url "${API_URL}/completion" \
--data-raw "${DATA}")
printf "\n"
CHAT+=("$1" "$(trim "$ANSWER")")
}
while true; do
read -r -e -p "> " QUESTION
chat_completion "${QUESTION}"
done