tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 20:05:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : add /detokenize endpoint (#2802)

Browse Source 
* Add a /detokenize endpoint to the example server

* remove trailing white-space
This commit is contained in:
Bruce MacDonald
2023-08-26 16:11:45 -07:00
committed by GitHub
parent 730d9c681e
commit c1ac54b77a
2 changed files with 27 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
examples/server/server.cpp
View File

@ -1104,6 +1104,12 @@ static json format_tokenizer_response(const std::vector<llama_token> &tokens)
{"tokens", tokens}};
}
static json format_detokenized_response(std::string content)
{
return json{
{"content", content}};
}
template <typename T>
static T json_value(const json &body, const std::string &key, const T &default_value)
{
@ -1501,6 +1507,21 @@ int main(int argc, char **argv)
const json data = format_tokenizer_response(tokens);
return res.set_content(data.dump(), "application/json"); });
svr.Post("/detokenize", [&llama](const Request &req, Response &res)
{
auto lock = llama.lock();
const json body = json::parse(req.body);
std::string content;
if (body.count("tokens") != 0)
{
const std::vector<llama_token> tokens = body["tokens"];
content = tokens_to_str(llama.ctx, tokens.cbegin(), tokens.cend());
}
const json data = format_detokenized_response(content);
return res.set_content(data.dump(), "application/json"); });
svr.Post("/embedding", [&llama](const Request &req, Response &res)
{
auto lock = llama.lock();