examples : add server example with REST API (#1443)
* Added httplib support * Added readme for server example * fixed some bugs * Fix the build error on Macbook * changed json11 to nlohmann-json * removed some whitespaces * remove trailing whitespace * added support custom prompts and more functions * some corrections and added as cmake option
This commit is contained in:
Steward Garcia
GitHub
parent
7780e4f479
commit
7e4ea5beff
|
|
@ -72,6 +72,7 @@ option(LLAMA_CLBLAST "llama: use CLBlast"
|
|||
|
||||
option(LLAMA_BUILD_TESTS "llama: build tests" ${LLAMA_STANDALONE})
|
||||
option(LLAMA_BUILD_EXAMPLES "llama: build examples" ${LLAMA_STANDALONE})
|
||||
option(LLAMA_BUILD_SERVER "llama: build server example" OFF)
|
||||
|
||||
#
|
||||
# Build info header
|
||||
|
|
|
|||
|
|
@ -37,4 +37,7 @@ else()
|
|||
add_subdirectory(save-load-state)
|
||||
add_subdirectory(benchmark)
|
||||
add_subdirectory(baby-llama)
|
||||
if(LLAMA_BUILD_SERVER)
|
||||
add_subdirectory(server)
|
||||
endif()
|
||||
endif()
|
||||
|
|
|
|||
8
examples/server/CMakeLists.txt
Normal file
8
examples/server/CMakeLists.txt
Normal file
|
|
@ -0,0 +1,8 @@
|
|||
set(TARGET server)
|
||||
include_directories(${CMAKE_CURRENT_SOURCE_DIR})
|
||||
add_executable(${TARGET} server.cpp json.hpp httplib.h)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
if(TARGET BUILD_INFO)
|
||||
add_dependencies(${TARGET} BUILD_INFO)
|
||||
endif()
|
||||
311
examples/server/README.md
Normal file
311
examples/server/README.md
Normal file
|
|
@ -0,0 +1,311 @@
|
|||
# llama.cpp/example/server
|
||||
|
||||
This example allow you to have a llama.cpp http server to interact from a web page or consume the API.
|
||||
|
||||
## Table of Contents
|
||||
|
||||
1. [Quick Start](#quick-start)
|
||||
2. [Node JS Test](#node-js-test)
|
||||
3. [API Endpoints](#api-endpoints)
|
||||
4. [More examples](#more-examples)
|
||||
5. [Common Options](#common-options)
|
||||
6. [Performance Tuning and Memory Options](#performance-tuning-and-memory-options)
|
||||
|
||||
## Quick Start
|
||||
|
||||
To get started right away, run the following command, making sure to use the correct path for the model you have:
|
||||
|
||||
#### Unix-based systems (Linux, macOS, etc.):
|
||||
|
||||
```bash
|
||||
./server -m models/7B/ggml-model.bin --ctx_size 2048
|
||||
```
|
||||
|
||||
#### Windows:
|
||||
|
||||
```powershell
|
||||
server.exe -m models\7B\ggml-model.bin --ctx_size 2048
|
||||
```
|
||||
|
||||
That will start a server that by default listens on `127.0.0.1:8080`. You can consume the endpoints with Postman or NodeJS with axios library.
|
||||
|
||||
## Node JS Test
|
||||
|
||||
You need to have [Node.js](https://nodejs.org/en) installed.
|
||||
|
||||
```bash
|
||||
mkdir llama-client
|
||||
cd llama-client
|
||||
npm init
|
||||
npm install axios
|
||||
```
|
||||
|
||||
Create a index.js file and put inside this:
|
||||
|
||||
```javascript
|
||||
const axios = require("axios");
|
||||
|
||||
const prompt = `Building a website can be done in 10 simple steps:`;
|
||||
|
||||
async function Test() {
|
||||
let result = await axios.post("http://127.0.0.1:8080/completion", {
|
||||
prompt,
|
||||
batch_size: 128,
|
||||
n_predict: 512,
|
||||
});
|
||||
|
||||
// the response is received until completion finish
|
||||
console.log(result.data.content);
|
||||
}
|
||||
|
||||
Test();
|
||||
```
|
||||
|
||||
And run it:
|
||||
|
||||
```bash
|
||||
node .
|
||||
```
|
||||
|
||||
## API Endpoints
|
||||
|
||||
You can interact with this API Endpoints. This implementations just support chat style interaction.
|
||||
|
||||
- **POST** `hostname:port/completion`: Setting up the Llama Context to begin the completions tasks.
|
||||
|
||||
*Options:*
|
||||
|
||||
`batch_size`: Set the batch size for prompt processing (default: 512).
|
||||
|
||||
`temperature`: Adjust the randomness of the generated text (default: 0.8).
|
||||
|
||||
`top_k`: Limit the next token selection to the K most probable tokens (default: 40).
|
||||
|
||||
`top_p`: Limit the next token selection to a subset of tokens with a cumulative probability above a threshold P (default: 0.9).
|
||||
|
||||
`n_predict`: Set the number of tokens to predict when generating text (default: 128, -1 = infinity).
|
||||
|
||||
`threads`: Set the number of threads to use during computation.
|
||||
|
||||
`n_keep`: Specify the number of tokens from the initial prompt to retain when the model resets its internal context. By default, this value is set to 0 (meaning no tokens are kept). Use `-1` to retain all tokens from the initial prompt.
|
||||
|
||||
`as_loop`: It allows receiving each predicted token in real-time instead of waiting for the completion to finish. To enable this, set to `true`.
|
||||
|
||||
`interactive`: It allows interacting with the completion, and the completion stops as soon as it encounters a `stop word`. To enable this, set to `true`.
|
||||
|
||||
`prompt`: Provide a prompt. Internally, the prompt is compared, and it detects if a part has already been evaluated, and the remaining part will be evaluate.
|
||||
|
||||
`stop`: Specify the words or characters that indicate a stop. These words will not be included in the completion, so make sure to add them to the prompt for the next iteration.
|
||||
|
||||
`exclude`: Specify the words or characters you do not want to appear in the completion. These words will not be included in the completion, so make sure to add them to the prompt for the next iteration.
|
||||
|
||||
- **POST** `hostname:port/embedding`: Generate embedding of a given text
|
||||
|
||||
*Options:*
|
||||
|
||||
`content`: Set the text to get generate the embedding.
|
||||
|
||||
`threads`: Set the number of threads to use during computation.
|
||||
|
||||
To use this endpoint, you need to start the server with the `--embedding` option added.
|
||||
|
||||
- **POST** `hostname:port/tokenize`: Tokenize a given text
|
||||
|
||||
*Options:*
|
||||
|
||||
`content`: Set the text to tokenize.
|
||||
|
||||
- **GET** `hostname:port/next-token`: Receive the next token predicted, execute this request in a loop. Make sure set `as_loop` as `true` in the completion request.
|
||||
|
||||
*Options:*
|
||||
|
||||
`stop`: Set `hostname:port/next-token?stop=true` to stop the token generation.
|
||||
|
||||
## More examples
|
||||
|
||||
### Interactive mode
|
||||
|
||||
This mode allows interacting in a chat-like manner. It is recommended for models designed as assistants such as `Vicuna`, `WizardLM`, `Koala`, among others. Make sure to add the correct stop word for the corresponding model.
|
||||
|
||||
The prompt should be generated by you, according to the model's guidelines. You should keep adding the model's completions to the context as well.
|
||||
|
||||
This example works well for `Vicuna - version 1`.
|
||||
|
||||
```javascript
|
||||
const axios = require("axios");
|
||||
|
||||
let prompt = `A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.
|
||||
### 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.`;
|
||||
|
||||
async function ChatCompletion(answer) {
|
||||
// the user's next question to the prompt
|
||||
prompt += `\n### Human: ${answer}\n`
|
||||
|
||||
result = await axios.post("http://127.0.0.1:8080/completion", {
|
||||
prompt,
|
||||
batch_size: 128,
|
||||
temperature: 0.2,
|
||||
top_k: 40,
|
||||
top_p: 0.9,
|
||||
n_keep: -1,
|
||||
n_predict: 2048,
|
||||
stop: ["\n### Human:"], // when detect this, stop completion
|
||||
exclude: ["### Assistant:"], // no show in the completion
|
||||
threads: 8,
|
||||
as_loop: true, // use this to request the completion token by token
|
||||
interactive: true, // enable the detection of a stop word
|
||||
});
|
||||
|
||||
// create a loop to receive every token predicted
|
||||
// note: this operation is blocking, avoid use this in a ui thread
|
||||
|
||||
let message = "";
|
||||
while (true) {
|
||||
// you can stop the inference adding '?stop=true' like this http://127.0.0.1:8080/next-token?stop=true
|
||||
result = await axios.get("http://127.0.0.1:8080/next-token");
|
||||
process.stdout.write(result.data.content);
|
||||
message += result.data.content;
|
||||
|
||||
// to avoid an infinite loop
|
||||
if (result.data.stop) {
|
||||
console.log("Completed");
|
||||
// make sure to add the completion to the prompt.
|
||||
prompt += `### Assistant: ${message}`;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// This function should be called every time a question to the model is needed.
|
||||
async function Test() {
|
||||
// the server can't inference in paralell
|
||||
await ChatCompletion("Write a long story about a time magician in a fantasy world");
|
||||
await ChatCompletion("Summary the story");
|
||||
}
|
||||
|
||||
Test();
|
||||
```
|
||||
|
||||
### Alpaca example
|
||||
|
||||
**Temporaly note:** no tested, if you have the model, please test it and report me some issue
|
||||
|
||||
```javascript
|
||||
const axios = require("axios");
|
||||
|
||||
let prompt = `Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
||||
`;
|
||||
|
||||
async function DoInstruction(instruction) {
|
||||
prompt += `\n\n### Instruction:\n\n${instruction}\n\n### Response:\n\n`;
|
||||
result = await axios.post("http://127.0.0.1:8080/completion", {
|
||||
prompt,
|
||||
batch_size: 128,
|
||||
temperature: 0.2,
|
||||
top_k: 40,
|
||||
top_p: 0.9,
|
||||
n_keep: -1,
|
||||
n_predict: 2048,
|
||||
stop: ["### Instruction:\n\n"], // when detect this, stop completion
|
||||
exclude: [], // no show in the completion
|
||||
threads: 8,
|
||||
as_loop: true, // use this to request the completion token by token
|
||||
interactive: true, // enable the detection of a stop word
|
||||
});
|
||||
|
||||
// create a loop to receive every token predicted
|
||||
// note: this operation is blocking, avoid use this in a ui thread
|
||||
|
||||
let message = "";
|
||||
while (true) {
|
||||
result = await axios.get("http://127.0.0.1:8080/next-token");
|
||||
process.stdout.write(result.data.content);
|
||||
message += result.data.content;
|
||||
|
||||
// to avoid an infinite loop
|
||||
if (result.data.stop) {
|
||||
console.log("Completed");
|
||||
// make sure to add the completion and the user's next question to the prompt.
|
||||
prompt += message;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// This function should be called every time a instruction to the model is needed.
|
||||
DoInstruction("Destroy the world"); // as joke
|
||||
```
|
||||
|
||||
### Embeddings
|
||||
|
||||
First, run the server with `--embedding` option:
|
||||
|
||||
```bash
|
||||
server -m models/7B/ggml-model.bin --ctx_size 2048 --embedding
|
||||
```
|
||||
|
||||
Run this code in NodeJS:
|
||||
|
||||
```javascript
|
||||
const axios = require('axios');
|
||||
|
||||
async function Test() {
|
||||
let result = await axios.post("http://127.0.0.1:8080/embedding", {
|
||||
content: `Hello`,
|
||||
threads: 5
|
||||
});
|
||||
// print the embedding array
|
||||
console.log(result.data.embedding);
|
||||
}
|
||||
|
||||
Test();
|
||||
```
|
||||
|
||||
### Tokenize
|
||||
|
||||
Run this code in NodeJS:
|
||||
|
||||
```javascript
|
||||
const axios = require('axios');
|
||||
|
||||
async function Test() {
|
||||
let result = await axios.post("http://127.0.0.1:8080/tokenize", {
|
||||
content: `Hello`
|
||||
});
|
||||
// print the embedding array
|
||||
console.log(result.data.tokens);
|
||||
}
|
||||
|
||||
Test();
|
||||
```
|
||||
|
||||
## Common Options
|
||||
|
||||
- `-m FNAME, --model FNAME`: Specify the path to the LLaMA model file (e.g., `models/7B/ggml-model.bin`).
|
||||
- `-c N, --ctx_size N`: Set the size of the prompt context. The default is 512, but LLaMA models were built with a context of 2048, which will provide better results for longer input/inference.
|
||||
- `--embedding`: Enable the embedding mode. **Completion function doesn't work in this mode**.
|
||||
- `--host`: Set the hostname or ip address to listen. Default `127.0.0.1`;
|
||||
- `--port`: Set the port to listen. Default: `8080`.
|
||||
|
||||
### RNG Seed
|
||||
|
||||
- `-s SEED, --seed SEED`: Set the random number generator (RNG) seed (default: -1, < 0 = random seed).
|
||||
|
||||
The RNG seed is used to initialize the random number generator that influences the text generation process. By setting a specific seed value, you can obtain consistent and reproducible results across multiple runs with the same input and settings. This can be helpful for testing, debugging, or comparing the effects of different options on the generated text to see when they diverge. If the seed is set to a value less than 0, a random seed will be used, which will result in different outputs on each run.
|
||||
|
||||
## Performance Tuning and Memory Options
|
||||
|
||||
### No Memory Mapping
|
||||
|
||||
- `--no-mmap`: Do not memory-map the model. By default, models are mapped into memory, which allows the system to load only the necessary parts of the model as needed. However, if the model is larger than your total amount of RAM or if your system is low on available memory, using mmap might increase the risk of pageouts, negatively impacting performance.
|
||||
|
||||
### Memory Float 32
|
||||
|
||||
- `--memory_f32`: Use 32-bit floats instead of 16-bit floats for memory key+value, allowing higher quality inference at the cost of higher memory usage.
|
||||
|
||||
## Limitations:
|
||||
|
||||
- The actual implementation of llama.cpp need a `llama-state` for handle multiple contexts and clients, but this could require more powerful hardware.
|
||||
8794
examples/server/httplib.h
Normal file
8794
examples/server/httplib.h
Normal file
File diff suppressed because it is too large
Load diff
24596
examples/server/json.hpp
Normal file
24596
examples/server/json.hpp
Normal file
File diff suppressed because it is too large
Load diff
721
examples/server/server.cpp
Normal file
721
examples/server/server.cpp
Normal file
|
|
@ -0,0 +1,721 @@
|
|||
#include <httplib.h>
|
||||
#include <json.hpp>
|
||||
#include "common.h"
|
||||
#include "llama.h"
|
||||
|
||||
struct server_params
|
||||
{
|
||||
std::string hostname = "127.0.0.1";
|
||||
int32_t port = 8080;
|
||||
};
|
||||
|
||||
struct llama_server_context
|
||||
{
|
||||
bool as_loop = false;
|
||||
bool has_next_token = false;
|
||||
std::string generated_text = "";
|
||||
|
||||
int32_t num_tokens_predicted = 0;
|
||||
int32_t n_past = 0;
|
||||
int32_t n_consumed = 0;
|
||||
int32_t n_session_consumed = 0;
|
||||
int32_t n_remain = 0;
|
||||
|
||||
std::vector<llama_token> embd;
|
||||
std::vector<llama_token> last_n_tokens;
|
||||
std::vector<llama_token> processed_tokens;
|
||||
std::vector<llama_token> llama_token_newline;
|
||||
std::vector<llama_token> embd_inp;
|
||||
std::vector<std::vector<llama_token>> no_show_words;
|
||||
std::vector<llama_token> tokens_predicted;
|
||||
|
||||
llama_context *ctx;
|
||||
gpt_params params;
|
||||
|
||||
void rewind() {
|
||||
as_loop = false;
|
||||
params.antiprompt.clear();
|
||||
no_show_words.clear();
|
||||
num_tokens_predicted = 0;
|
||||
generated_text = "";
|
||||
}
|
||||
|
||||
bool loadModel(gpt_params params_)
|
||||
{
|
||||
params = params_;
|
||||
ctx = llama_init_from_gpt_params(params);
|
||||
if (ctx == NULL)
|
||||
{
|
||||
fprintf(stderr, "%s: error: unable to load model\n", __func__);
|
||||
return false;
|
||||
}
|
||||
// determine newline token
|
||||
llama_token_newline = ::llama_tokenize(ctx, "\n", false);
|
||||
last_n_tokens.resize(params.n_ctx);
|
||||
std::fill(last_n_tokens.begin(), last_n_tokens.end(), 0);
|
||||
return true;
|
||||
}
|
||||
|
||||
bool loadPrompt() {
|
||||
params.prompt.insert(0, 1, ' '); // always add a first space
|
||||
std::vector<llama_token> prompt_tokens = ::llama_tokenize(ctx, params.prompt, true);
|
||||
// compare the evaluated prompt with the new prompt
|
||||
int new_prompt_len = 0;
|
||||
for (int i = 0;i < prompt_tokens.size(); i++) {
|
||||
if (i < processed_tokens.size() &&
|
||||
processed_tokens[i] == prompt_tokens[i])
|
||||
{
|
||||
continue;
|
||||
}
|
||||
else
|
||||
{
|
||||
embd_inp.push_back(prompt_tokens[i]);
|
||||
if(new_prompt_len == 0) {
|
||||
if(i - 1 < n_past) {
|
||||
processed_tokens.erase(processed_tokens.begin() + i, processed_tokens.end());
|
||||
}
|
||||
// Evaluate the new fragment prompt from the last token processed.
|
||||
n_past = processed_tokens.size();
|
||||
}
|
||||
new_prompt_len ++;
|
||||
}
|
||||
}
|
||||
if(n_past > 0 && params.interactive) {
|
||||
n_remain -= new_prompt_len;
|
||||
}
|
||||
if ((int)embd_inp.size() > params.n_ctx - 4)
|
||||
{
|
||||
return false;
|
||||
}
|
||||
has_next_token = true;
|
||||
return true;
|
||||
}
|
||||
|
||||
void beginCompletion()
|
||||
{
|
||||
if(n_remain == 0) {
|
||||
// number of tokens to keep when resetting context
|
||||
if (params.n_keep < 0 || params.n_keep > (int)embd_inp.size())
|
||||
{
|
||||
params.n_keep = (int)embd_inp.size();
|
||||
}
|
||||
}
|
||||
n_remain = params.n_predict;
|
||||
}
|
||||
|
||||
llama_token nextToken() {
|
||||
llama_token result = -1;
|
||||
if (embd.size() > 0)
|
||||
{
|
||||
if (n_past + (int)embd.size() > params.n_ctx)
|
||||
{
|
||||
// Reset context
|
||||
const int n_left = n_past - params.n_keep;
|
||||
n_past = std::max(1, params.n_keep);
|
||||
processed_tokens.erase(processed_tokens.begin() + n_past, processed_tokens.end());
|
||||
embd.insert(embd.begin(), last_n_tokens.begin() + params.n_ctx - n_left / 2 - embd.size(), last_n_tokens.end() - embd.size());
|
||||
}
|
||||
for (int i = 0; i < (int)embd.size(); i += params.n_batch)
|
||||
{
|
||||
int n_eval = (int)embd.size() - i;
|
||||
if (n_eval > params.n_batch)
|
||||
{
|
||||
n_eval = params.n_batch;
|
||||
}
|
||||
if (llama_eval(ctx, &embd[i], n_eval, n_past, params.n_threads))
|
||||
{
|
||||
fprintf(stderr, "%s : failed to eval\n", __func__);
|
||||
has_next_token = false;
|
||||
return result;
|
||||
}
|
||||
n_past += n_eval;
|
||||
}
|
||||
}
|
||||
embd.clear();
|
||||
if ((int)embd_inp.size() <= n_consumed && has_next_token)
|
||||
{
|
||||
// out of user input, sample next token
|
||||
const float temp = params.temp;
|
||||
const int32_t top_k = params.top_k <= 0 ? llama_n_vocab(ctx) : params.top_k;
|
||||
const float top_p = params.top_p;
|
||||
const float tfs_z = params.tfs_z;
|
||||
const float typical_p = params.typical_p;
|
||||
const int32_t repeat_last_n = params.repeat_last_n < 0 ? params.n_ctx : params.repeat_last_n;
|
||||
const float repeat_penalty = params.repeat_penalty;
|
||||
const float alpha_presence = params.presence_penalty;
|
||||
const float alpha_frequency = params.frequency_penalty;
|
||||
const int mirostat = params.mirostat;
|
||||
const float mirostat_tau = params.mirostat_tau;
|
||||
const float mirostat_eta = params.mirostat_eta;
|
||||
const bool penalize_nl = params.penalize_nl;
|
||||
llama_token id = 0;
|
||||
{
|
||||
auto logits = llama_get_logits(ctx);
|
||||
auto n_vocab = llama_n_vocab(ctx);
|
||||
|
||||
// Apply params.logit_bias map
|
||||
for (auto it = params.logit_bias.begin(); it != params.logit_bias.end(); it++)
|
||||
{
|
||||
logits[it->first] += it->second;
|
||||
}
|
||||
|
||||
std::vector<llama_token_data> candidates;
|
||||
candidates.reserve(n_vocab);
|
||||
for (llama_token token_id = 0; token_id < n_vocab; token_id++)
|
||||
{
|
||||
candidates.emplace_back(llama_token_data{token_id, logits[token_id], 0.0f});
|
||||
}
|
||||
|
||||
llama_token_data_array candidates_p = {candidates.data(), candidates.size(), false};
|
||||
|
||||
// Apply penalties
|
||||
float nl_logit = logits[llama_token_nl()];
|
||||
auto last_n_repeat = std::min(std::min((int)last_n_tokens.size(), repeat_last_n), params.n_ctx);
|
||||
llama_sample_repetition_penalty(ctx, &candidates_p,
|
||||
last_n_tokens.data() + last_n_tokens.size() - last_n_repeat,
|
||||
last_n_repeat, repeat_penalty);
|
||||
llama_sample_frequency_and_presence_penalties(ctx, &candidates_p,
|
||||
last_n_tokens.data() + last_n_tokens.size() - last_n_repeat,
|
||||
last_n_repeat, alpha_frequency, alpha_presence);
|
||||
if (!penalize_nl)
|
||||
{
|
||||
logits[llama_token_nl()] = nl_logit;
|
||||
}
|
||||
|
||||
if (temp <= 0)
|
||||
{
|
||||
// Greedy sampling
|
||||
id = llama_sample_token_greedy(ctx, &candidates_p);
|
||||
}
|
||||
else
|
||||
{
|
||||
if (mirostat == 1)
|
||||
{
|
||||
static float mirostat_mu = 2.0f * mirostat_tau;
|
||||
const int mirostat_m = 100;
|
||||
llama_sample_temperature(ctx, &candidates_p, temp);
|
||||
id = llama_sample_token_mirostat(ctx, &candidates_p, mirostat_tau, mirostat_eta, mirostat_m, &mirostat_mu);
|
||||
}
|
||||
else if (mirostat == 2)
|
||||
{
|
||||
static float mirostat_mu = 2.0f * mirostat_tau;
|
||||
llama_sample_temperature(ctx, &candidates_p, temp);
|
||||
id = llama_sample_token_mirostat_v2(ctx, &candidates_p, mirostat_tau, mirostat_eta, &mirostat_mu);
|
||||
}
|
||||
else
|
||||
{
|
||||
// Temperature sampling
|
||||
llama_sample_tail_free(ctx, &candidates_p, tfs_z, 1);
|
||||
llama_sample_typical(ctx, &candidates_p, typical_p, 1);
|
||||
llama_sample_top_p(ctx, &candidates_p, top_p, 1);
|
||||
llama_sample_temperature(ctx, &candidates_p, temp);
|
||||
id = llama_sample_token(ctx, &candidates_p);
|
||||
}
|
||||
}
|
||||
last_n_tokens.erase(last_n_tokens.begin());
|
||||
last_n_tokens.push_back(id);
|
||||
processed_tokens.push_back(id);
|
||||
num_tokens_predicted++;
|
||||
}
|
||||
|
||||
// replace end of text token with newline token when in interactive mode
|
||||
if (id == llama_token_eos() && params.interactive)
|
||||
{
|
||||
id = llama_token_newline.front();
|
||||
if (params.antiprompt.size() != 0)
|
||||
{
|
||||
// tokenize and inject first reverse prompt
|
||||
const auto first_antiprompt = ::llama_tokenize(ctx, params.antiprompt.front(), false);
|
||||
embd_inp.insert(embd_inp.end(), first_antiprompt.begin(), first_antiprompt.end());
|
||||
}
|
||||
}
|
||||
|
||||
// add it to the context
|
||||
embd.push_back(id);
|
||||
for (auto id : embd)
|
||||
{
|
||||
result = id;
|
||||
}
|
||||
// decrement remaining sampling budget
|
||||
--n_remain;
|
||||
}
|
||||
else
|
||||
{
|
||||
// some user input remains from prompt or interaction, forward it to processing
|
||||
while ((int)embd_inp.size() > n_consumed)
|
||||
{
|
||||
embd.push_back(embd_inp[n_consumed]);
|
||||
last_n_tokens.erase(last_n_tokens.begin());
|
||||
last_n_tokens.push_back(embd_inp[n_consumed]);
|
||||
processed_tokens.push_back(embd_inp[n_consumed]);
|
||||
++n_consumed;
|
||||
if ((int)embd.size() >= params.n_batch)
|
||||
{
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
if (params.interactive && (int)embd_inp.size() <= n_consumed)
|
||||
{
|
||||
// check for reverse prompt
|
||||
if (params.antiprompt.size())
|
||||
{
|
||||
std::string last_output;
|
||||
for (auto id : last_n_tokens)
|
||||
{
|
||||
last_output += llama_token_to_str(ctx, id);
|
||||
}
|
||||
has_next_token = true;
|
||||
// Check if each of the reverse prompts appears at the end of the output.
|
||||
for (std::string &antiprompt : params.antiprompt)
|
||||
{
|
||||
if (last_output.find(antiprompt.c_str(), last_output.length() - antiprompt.length(), antiprompt.length()) != std::string::npos)
|
||||
{
|
||||
has_next_token = false;
|
||||
return result;
|
||||
}
|
||||
}
|
||||
}
|
||||
if (n_past > 0)
|
||||
{
|
||||
has_next_token = true;
|
||||
}
|
||||
}
|
||||
|
||||
if (!embd.empty() && embd.back() == llama_token_eos()) {
|
||||
has_next_token = false;
|
||||
}
|
||||
|
||||
if (params.interactive && n_remain <= 0 && params.n_predict != -1)
|
||||
{
|
||||
n_remain = params.n_predict;
|
||||
}
|
||||
has_next_token = n_remain != 0;
|
||||
return result;
|
||||
}
|
||||
|
||||
std::string doCompletion()
|
||||
{
|
||||
llama_token token = nextToken();
|
||||
if (token == -1) {
|
||||
return "";
|
||||
}
|
||||
tokens_predicted.clear();
|
||||
tokens_predicted.push_back(token);
|
||||
|
||||
// Avoid add the no show words to the response
|
||||
for (std::vector<llama_token> word_tokens : no_show_words)
|
||||
{
|
||||
int match_token = 1;
|
||||
if (tokens_predicted.front() == word_tokens.front())
|
||||
{
|
||||
bool execute_matching = true;
|
||||
if (tokens_predicted.size() > 1) { // if previus tokens had been tested
|
||||
for (int i = 1; i < word_tokens.size(); i++)
|
||||
{
|
||||
if (i >= tokens_predicted.size()) {
|
||||
match_token = i;
|
||||
break;
|
||||
}
|
||||
if (tokens_predicted[i] == word_tokens[i])
|
||||
{
|
||||
continue;
|
||||
}
|
||||
else
|
||||
{
|
||||
execute_matching = false;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
while (execute_matching) {
|
||||
if (match_token == word_tokens.size()) {
|
||||
return "";
|
||||
}
|
||||
token = nextToken();
|
||||
tokens_predicted.push_back(token);
|
||||
if (token == word_tokens[match_token])
|
||||
{ // the token follow the sequence
|
||||
match_token++;
|
||||
}
|
||||
else if (match_token < word_tokens.size())
|
||||
{ // no complete all word sequence
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if(as_loop) {
|
||||
generated_text = "";
|
||||
}
|
||||
for (llama_token tkn : tokens_predicted)
|
||||
{
|
||||
generated_text += llama_token_to_str(ctx, tkn);
|
||||
}
|
||||
return generated_text;
|
||||
}
|
||||
|
||||
std::vector<float> embedding(std::string content, int threads) {
|
||||
content.insert(0, 1, ' ');
|
||||
std::vector<llama_token> tokens = ::llama_tokenize(ctx, content, true);
|
||||
if (tokens.size() > 0)
|
||||
{
|
||||
if (llama_eval(ctx, tokens.data(), tokens.size(), 0, threads))
|
||||
{
|
||||
fprintf(stderr, "%s : failed to eval\n", __func__);
|
||||
std::vector<float> embeddings_;
|
||||
return embeddings_;
|
||||
}
|
||||
}
|
||||
const int n_embd = llama_n_embd(ctx);
|
||||
const auto embeddings = llama_get_embeddings(ctx);
|
||||
std::vector<float> embeddings_(embeddings, embeddings + n_embd);
|
||||
return embeddings_;
|
||||
}
|
||||
};
|
||||
|
||||
using namespace httplib;
|
||||
|
||||
using json = nlohmann::json;
|
||||
|
||||
void server_print_usage(int /*argc*/, char **argv, const gpt_params ¶ms)
|
||||
{
|
||||
fprintf(stderr, "usage: %s [options]\n", argv[0]);
|
||||
fprintf(stderr, "\n");
|
||||
fprintf(stderr, "options:\n");
|
||||
fprintf(stderr, " -h, --help show this help message and exit\n");
|
||||
fprintf(stderr, " -s SEED, --seed SEED RNG seed (default: -1, use random seed for < 0)\n");
|
||||
fprintf(stderr, " --memory_f32 use f32 instead of f16 for memory key+value\n");
|
||||
fprintf(stderr, " --embedding enable embedding mode\n");
|
||||
fprintf(stderr, " --keep number of tokens to keep from the initial prompt (default: %d, -1 = all)\n", params.n_keep);
|
||||
if (llama_mlock_supported())
|
||||
{
|
||||
fprintf(stderr, " --mlock force system to keep model in RAM rather than swapping or compressing\n");
|
||||
}
|
||||
if (llama_mmap_supported())
|
||||
{
|
||||
fprintf(stderr, " --no-mmap do not memory-map model (slower load but may reduce pageouts if not using mlock)\n");
|
||||
}
|
||||
fprintf(stderr, " -ngl N, --n-gpu-layers N\n");
|
||||
fprintf(stderr, " number of layers to store in VRAM\n");
|
||||
fprintf(stderr, " -m FNAME, --model FNAME\n");
|
||||
fprintf(stderr, " model path (default: %s)\n", params.model.c_str());
|
||||
fprintf(stderr, " -host ip address to listen (default 127.0.0.1)\n");
|
||||
fprintf(stderr, " -port PORT port to listen (default 8080)\n");
|
||||
fprintf(stderr, "\n");
|
||||
}
|
||||
|
||||
bool server_params_parse(int argc, char **argv, server_params &sparams, gpt_params ¶ms)
|
||||
{
|
||||
gpt_params default_params;
|
||||
std::string arg;
|
||||
bool invalid_param = false;
|
||||
|
||||
for (int i = 1; i < argc; i++)
|
||||
{
|
||||
arg = argv[i];
|
||||
if (arg == "--port")
|
||||
{
|
||||
if (++i >= argc)
|
||||
{
|
||||
invalid_param = true;
|
||||
break;
|
||||
}
|
||||
sparams.port = std::stoi(argv[i]);
|
||||
}
|
||||
else if (arg == "--host")
|
||||
{
|
||||
if (++i >= argc)
|
||||
{
|
||||
invalid_param = true;
|
||||
break;
|
||||
}
|
||||
sparams.hostname = argv[i];
|
||||
}
|
||||
else if (arg == "-s" || arg == "--seed")
|
||||
{
|
||||
#if defined(GGML_USE_CUBLAS)
|
||||
fprintf(stderr, "WARNING: when using cuBLAS generation results are NOT guaranteed to be reproducible.\n");
|
||||
#endif
|
||||
if (++i >= argc)
|
||||
{
|
||||
invalid_param = true;
|
||||
break;
|
||||
}
|
||||
params.seed = std::stoi(argv[i]);
|
||||
}
|
||||
else if (arg == "-m" || arg == "--model")
|
||||
{
|
||||
if (++i >= argc)
|
||||
{
|
||||
invalid_param = true;
|
||||
break;
|
||||
}
|
||||
params.model = argv[i];
|
||||
}
|
||||
else if (arg == "--embedding")
|
||||
{
|
||||
params.embedding = true;
|
||||
}
|
||||
else if (arg == "-h" || arg == "--help")
|
||||
{
|
||||
server_print_usage(argc, argv, default_params);
|
||||
exit(0);
|
||||
}
|
||||
else if (arg == "-c" || arg == "--ctx_size")
|
||||
{
|
||||
if (++i >= argc)
|
||||
{
|
||||
invalid_param = true;
|
||||
break;
|
||||
}
|
||||
params.n_ctx = std::stoi(argv[i]);
|
||||
}
|
||||
else if (arg == "--memory_f32")
|
||||
{
|
||||
params.memory_f16 = false;
|
||||
}
|
||||
else if (arg == "--gpu-layers" || arg == "-ngl" || arg == "--n-gpu-layers")
|
||||
{
|
||||
if (++i >= argc)
|
||||
{
|
||||
invalid_param = true;
|
||||
break;
|
||||
}
|
||||
params.n_gpu_layers = std::stoi(argv[i]);
|
||||
}
|
||||
else
|
||||
{
|
||||
fprintf(stderr, "error: unknown argument: %s\n", arg.c_str());
|
||||
server_print_usage(argc, argv, default_params);
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
|
||||
if (invalid_param)
|
||||
{
|
||||
fprintf(stderr, "error: invalid parameter for argument: %s\n", arg.c_str());
|
||||
server_print_usage(argc, argv, default_params);
|
||||
exit(1);
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
bool parse_options_completion(json body, llama_server_context& llama, Response &res) {
|
||||
if (!body["threads"].is_null())
|
||||
{
|
||||
llama.params.n_threads = body["threads"].get<int>();
|
||||
}
|
||||
if (!body["n_predict"].is_null())
|
||||
{
|
||||
llama.params.n_predict = body["n_predict"].get<int>();
|
||||
}
|
||||
if (!body["top_k"].is_null())
|
||||
{
|
||||
llama.params.top_k = body["top_k"].get<int>();
|
||||
}
|
||||
if (!body["top_p"].is_null())
|
||||
{
|
||||
llama.params.top_p = body["top_p"].get<float>();
|
||||
}
|
||||
if (!body["temperature"].is_null())
|
||||
{
|
||||
llama.params.temp = body["temperature"].get<float>();
|
||||
}
|
||||
if (!body["batch_size"].is_null())
|
||||
{
|
||||
llama.params.n_batch = body["batch_size"].get<int>();
|
||||
}
|
||||
if (!body["n_keep"].is_null())
|
||||
{
|
||||
llama.params.n_keep = body["n_keep"].get<int>();
|
||||
}
|
||||
if (!body["as_loop"].is_null())
|
||||
{
|
||||
llama.as_loop = body["as_loop"].get<bool>();
|
||||
}
|
||||
if (!body["interactive"].is_null())
|
||||
{
|
||||
llama.params.interactive = body["interactive"].get<bool>();
|
||||
}
|
||||
if (!body["prompt"].is_null())
|
||||
{
|
||||
llama.params.prompt = body["prompt"].get<std::string>();
|
||||
}
|
||||
else
|
||||
{
|
||||
json data = {
|
||||
{"status", "error"},
|
||||
{"reason", "You need to pass the prompt"}};
|
||||
res.set_content(data.dump(), "application/json");
|
||||
res.status = 400;
|
||||
return false;
|
||||
}
|
||||
if (!body["stop"].is_null())
|
||||
{
|
||||
std::vector<std::string> stop_words = body["stop"].get<std::vector<std::string>>();
|
||||
for (std::string stop_word : stop_words)
|
||||
{
|
||||
llama.params.antiprompt.push_back(stop_word);
|
||||
llama.no_show_words.push_back(::llama_tokenize(llama.ctx, stop_word, false));
|
||||
}
|
||||
}
|
||||
if (!body["exclude"].is_null())
|
||||
{
|
||||
std::vector<std::string> no_show_words = body["exclude"].get<std::vector<std::string>>();
|
||||
for (std::string no_show : no_show_words)
|
||||
{
|
||||
llama.no_show_words.push_back(::llama_tokenize(llama.ctx, no_show, false));
|
||||
}
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
int main(int argc, char **argv)
|
||||
{
|
||||
// own arguments required by this example
|
||||
gpt_params params;
|
||||
server_params sparams;
|
||||
|
||||
// struct that contains llama context and inference
|
||||
llama_server_context llama;
|
||||
params.model = "ggml-model.bin";
|
||||
|
||||
if (server_params_parse(argc, argv, sparams, params) == false)
|
||||
{
|
||||
return 1;
|
||||
}
|
||||
|
||||
if (params.seed <= 0)
|
||||
{
|
||||
params.seed = time(NULL);
|
||||
}
|
||||
|
||||
fprintf(stderr, "%s: seed = %d\n", __func__, params.seed);
|
||||
|
||||
// load the model
|
||||
if (!llama.loadModel(params))
|
||||
{
|
||||
return 1;
|
||||
}
|
||||
|
||||
Server svr;
|
||||
|
||||
svr.Get("/", [](const Request &req, Response &res)
|
||||
{ res.set_content("<h1>llama.cpp server works</h1>", "text/html"); });
|
||||
|
||||
svr.Post("/completion", [&llama](const Request &req, Response &res)
|
||||
{
|
||||
if(llama.params.embedding) {
|
||||
json data = {
|
||||
{"status", "error"},
|
||||
{"reason", "To use completion function disable embedding mode"}};
|
||||
res.set_content(data.dump(), "application/json");
|
||||
res.status = 400;
|
||||
return;
|
||||
}
|
||||
|
||||
llama.rewind();
|
||||
|
||||
if(parse_options_completion(json::parse(req.body), llama, res) == false){
|
||||
return;
|
||||
}
|
||||
|
||||
if (!llama.loadPrompt())
|
||||
{
|
||||
json data = {
|
||||
{"status", "error"},
|
||||
{"reason", "Context too long, please be more specific"}};
|
||||
res.set_content(data.dump(), "application/json");
|
||||
res.status = 400;
|
||||
return;
|
||||
}
|
||||
|
||||
llama.beginCompletion();
|
||||
if(llama.as_loop) {
|
||||
json data = {
|
||||
{"status", "done" } };
|
||||
return res.set_content(data.dump(), "application/json");
|
||||
} else {
|
||||
// loop inference until finish completion
|
||||
while (llama.has_next_token)
|
||||
{
|
||||
llama.doCompletion();
|
||||
}
|
||||
try
|
||||
{
|
||||
json data = {
|
||||
{"content", llama.generated_text },
|
||||
{"tokens_predicted", llama.num_tokens_predicted}};
|
||||
return res.set_content(data.dump(), "application/json");
|
||||
}
|
||||
catch (json::exception e)
|
||||
{
|
||||
// Some tokens have bad UTF-8 strings, the json parser is very sensitive
|
||||
json data = {
|
||||
{"content", "Bad encoding token"},
|
||||
{"tokens_predicted", 0}};
|
||||
return res.set_content(data.dump(), "application/json");
|
||||
}
|
||||
} });
|
||||
|
||||
svr.Post("/tokenize", [&llama](const Request &req, Response &res)
|
||||
{
|
||||
json body = json::parse(req.body);
|
||||
json data = {
|
||||
{"tokens", ::llama_tokenize(llama.ctx, body["content"].get<std::string>(), false) } };
|
||||
return res.set_content(data.dump(), "application/json");
|
||||
});
|
||||
|
||||
svr.Post("/embedding", [&llama](const Request &req, Response &res)
|
||||
{
|
||||
if(!llama.params.embedding) {
|
||||
std::vector<float> empty;
|
||||
json data = {
|
||||
{"embedding", empty}};
|
||||
fprintf(stderr, "[llama-server] : You need enable embedding mode adding: --embedding option\n");
|
||||
return res.set_content(data.dump(), "application/json");
|
||||
}
|
||||
json body = json::parse(req.body);
|
||||
std::string content = body["content"].get<std::string>();
|
||||
int threads = body["threads"].get<int>();
|
||||
json data = {
|
||||
{"embedding", llama.embedding(content, threads) } };
|
||||
return res.set_content(data.dump(), "application/json");
|
||||
});
|
||||
|
||||
svr.Get("/next-token", [&llama](const Request &req, Response &res)
|
||||
{
|
||||
if(llama.params.embedding) {
|
||||
res.set_content("{}", "application/json");
|
||||
return;
|
||||
}
|
||||
std::string result = "";
|
||||
if (req.has_param("stop")) {
|
||||
llama.has_next_token = false;
|
||||
} else {
|
||||
result = llama.doCompletion(); // inference next token
|
||||
}
|
||||
try {
|
||||
json data = {
|
||||
{"content", result },
|
||||
{"stop", !llama.has_next_token }};
|
||||
return res.set_content(data.dump(), "application/json");
|
||||
} catch (json::exception e) {
|
||||
// Some tokens have bad UTF-8 strings, the json parser is very sensitive
|
||||
json data = {
|
||||
{"content", "" },
|
||||
{"stop", !llama.has_next_token }};
|
||||
return res.set_content(data.dump(), "application/json");
|
||||
}
|
||||
});
|
||||
|
||||
fprintf(stderr, "%s: http server Listening at http://%s:%i\n", __func__, sparams.hostname.c_str(), sparams.port);
|
||||
|
||||
if(params.embedding) {
|
||||
fprintf(stderr, "NOTE: Mode embedding enabled. Completion function doesn't work in this mode.\n");
|
||||
}
|
||||
|
||||
// change hostname and port
|
||||
svr.listen(sparams.hostname, sparams.port);
|
||||
}
|
||||
Loading…
Reference in a new issue