vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

tool-call: fix llama 3.x and functionary 3.2, play nice w/ pydantic_ai package, update readme (#11539)

Browse source 
* An empty tool_call_id is better than none!

* sync: minja (tool call name optional https://github.com/google/minja/pull/36)

* Force-disable parallel_tool_calls if template doesn't support it

* More debug logs

* Llama 3.x tools: accept / trigger on more varied spaced outputs

* Fix empty content for functionary v3.2 tool call

* Add proper tool call docs to server README

* readme: function calling *is* supported now

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Olivier Chafik 2025-01-31 14:15:25 +00:00 • committed by GitHub
parent b1bcd309fc
commit a83f528688
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 129 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/chat-template.hpp
View file

@ -283,10 +283,12 @@ class chat_template {
message["role"] = "user";
auto obj = json {
{"tool_response", {
{"tool", message.at("name")},
{"content", message.at("content")},
}},
};
if (message.contains("name")) {
obj["tool_response"]["name"] = message.at("name");
}
if (message.contains("tool_call_id")) {
obj["tool_response"]["tool_call_id"] = message.at("tool_call_id");
}