mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-28 08:31:25 +00:00
server / ranking : add sorting and management of top_n (#16403)
* server / ranking : add sorting and management of top_n
* Make the retro compatible if no top_n will return
all results
here is a script to make some test
```script
URL=${1:-http://127.0.0.1:8181}
curl "$URL/v1/rerank" -H "Content-Type: application/json" \
-d '{ "model": "M", "query": "What is the recipe to make bread ?",
"return_text" : true,
"texts" : true,
"top_n": 6,
"documents": [
"voici la recette pour faire du pain, il faut de la farine de l eau et du levain et du sel",
"it is a bear",
"bread recipe : floor, water, yest, salt",
"The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.",
"here is the ingedients to bake bread : 500g floor, 350g water, 120g fresh refresh yest, 15g salt",
"recipe to make cookies : floor, eggs, water, chocolat",
"here is the recipe to make bread : 500g floor, 350g water, 120g fresh refresh yest, 15g salt",
"il fait tres beau aujourd hui",
"je n ai pas faim, je ne veux pas manger",
"je suis a paris"
] }' | jq
```
* use resize() instead for(...)
* simplify top_n init since no need to return error
result to test :
./tests.sh unit/test_rerank.py -v -x
==================================================== test session starts =====================================================
platform linux -- Python 3.12.3, pytest-8.3.5, pluggy-1.6.0 -- /home/yann/dev/yann/llama.cpp/tools/server/tests/test/bin/python3
cachedir: .pytest_cache
rootdir: /home/yann/dev/yann/llama.cpp/tools/server/tests
configfile: pytest.ini
plugins: anyio-4.11.0
collected 8 items
unit/test_rerank.py::test_rerank PASSED [ 12%]
unit/test_rerank.py::test_rerank_tei_format PASSED [ 25%]
unit/test_rerank.py::test_invalid_rerank_req[documents0] PASSED [ 37%]
unit/test_rerank.py::test_invalid_rerank_req[None] PASSED [ 50%]
unit/test_rerank.py::test_invalid_rerank_req[123] PASSED [ 62%]
unit/test_rerank.py::test_invalid_rerank_req[documents3] PASSED [ 75%]
unit/test_rerank.py::test_rerank_usage[Machine learning is-A machine-Learning is-19] PASSED [ 87%]
unit/test_rerank.py::test_rerank_usage[Which city?-Machine learning is -Paris, capitale de la-26] PASSED [100%]
===================================================== 8 passed in 4.31s ======================================================
* add rerank top_n unit test
here is the result :
./tests.sh unit/test_rerank.py -v -x
=================================================================== test session starts ===================================================================
platform linux -- Python 3.12.3, pytest-8.3.5, pluggy-1.6.0 -- /home/yann/dev/yann/llama.cpp/tools/server/tests/test/bin/python3
cachedir: .pytest_cache
rootdir: /home/yann/dev/yann/llama.cpp/tools/server/tests
configfile: pytest.ini
plugins: anyio-4.11.0
collected 16 items
unit/test_rerank.py::test_rerank PASSED [ 6%]
unit/test_rerank.py::test_rerank_tei_format PASSED [ 12%]
unit/test_rerank.py::test_invalid_rerank_req[documents0] PASSED [ 18%]
unit/test_rerank.py::test_invalid_rerank_req[None] PASSED [ 25%]
unit/test_rerank.py::test_invalid_rerank_req[123] PASSED [ 31%]
unit/test_rerank.py::test_invalid_rerank_req[documents3] PASSED [ 37%]
unit/test_rerank.py::test_rerank_usage[Machine learning is-A machine-Learning is-19] PASSED [ 43%]
unit/test_rerank.py::test_rerank_usage[Which city?-Machine learning is -Paris, capitale de la-26] PASSED [ 50%]
unit/test_rerank.py::test_rerank_top_n[None-4] PASSED [ 56%]
unit/test_rerank.py::test_rerank_top_n[2-2] PASSED [ 62%]
unit/test_rerank.py::test_rerank_top_n[4-4] PASSED [ 68%]
unit/test_rerank.py::test_rerank_top_n[99-4] PASSED [ 75%]
unit/test_rerank.py::test_rerank_tei_top_n[None-4] PASSED [ 81%]
unit/test_rerank.py::test_rerank_tei_top_n[2-2] PASSED [ 87%]
unit/test_rerank.py::test_rerank_tei_top_n[4-4] PASSED [ 93%]
unit/test_rerank.py::test_rerank_tei_top_n[99-4] PASSED [100%]
=================================================================== 16 passed in 8.84s ===================================================================
* editor config check fix
This commit is contained in:
@@ -5401,15 +5401,6 @@ int main(int argc, char ** argv) {
|
||||
|
||||
const json body = json::parse(req.body);
|
||||
|
||||
// TODO: implement
|
||||
//int top_n = 1;
|
||||
//if (body.count("top_n") != 1) {
|
||||
// top_n = body.at("top_n");
|
||||
//} else {
|
||||
// res_error(res, format_error_response("\"top_n\" must be provided", ERROR_TYPE_INVALID_REQUEST));
|
||||
// return;
|
||||
//}
|
||||
|
||||
// if true, use TEI API format, otherwise use Jina API format
|
||||
// Jina: https://jina.ai/reranker/
|
||||
// TEI: https://huggingface.github.io/text-embeddings-inference/#/Text%20Embeddings%20Inference/rerank
|
||||
@@ -5434,6 +5425,8 @@ int main(int argc, char ** argv) {
|
||||
return;
|
||||
}
|
||||
|
||||
int top_n = json_value(body, "top_n", (int)documents.size());
|
||||
|
||||
// create and queue the task
|
||||
json responses = json::array();
|
||||
bool error = false;
|
||||
@@ -5474,7 +5467,8 @@ int main(int argc, char ** argv) {
|
||||
body,
|
||||
responses,
|
||||
is_tei_format,
|
||||
documents);
|
||||
documents,
|
||||
top_n);
|
||||
|
||||
res_ok(res, root);
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user