Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

server : (embeddings) using same format for "input" and "content" #10872

Merged
merged 4 commits into from
Dec 18, 2024
Merged

server : (embeddings) using same format for "input" and "content" #10872

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d4e0bad
server : (embeddings) using same format for "input" and "content"
ngxson Dec 17, 2024
9a56680
fix test case
ngxson Dec 17, 2024
d4b9ec0
handle empty input case
ngxson Dec 17, 2024
101e772
fix test
ngxson Dec 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions examples/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3651,14 +3651,14 @@ int main(int argc, char ** argv) {
const json body = json::parse(req.body);
bool oaicompat = false;

// an input prompt can be a string or a list of tokens (integer)
// for the shape of input/content, see tokenize_input_prompts()
json prompt;
if (body.count("input") != 0) {
if (body.contains("input")) {
oaicompat = true;
prompt = body.at("input");
} else if (body.count("content") != 0) {
// with "content", we only support single prompt
prompt = std::vector<std::string>{body.at("content")};
} else if (body.contains("content")) {
oaicompat = false;
prompt = body.at("content");
} else {
res_error(res, format_error_response("\"input\" or \"content\" must be provided", ERROR_TYPE_INVALID_REQUEST));
return;
Expand Down
29 changes: 29 additions & 0 deletions examples/server/tests/unit/test_embedding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,35 @@ def test_embedding_multiple():
assert len(d['embedding']) > 1


@pytest.mark.parametrize(
"content,is_multi_prompt",
[
# single prompt
("string", False),
([12, 34, 56], False),
([12, 34, "string", 56, 78], False),
# multiple prompts
(["string1", "string2"], True),
(["string1", [12, 34, 56]], True),
([[12, 34, 56], [12, 34, 56]], True),
([[12, 34, 56], [12, "string", 34, 56]], True),
]
)
def test_embedding_mixed_input(content, is_multi_prompt: bool):
global server
server.start()
res = server.make_request("POST", "/embeddings", data={"content": content})
assert res.status_code == 200
if is_multi_prompt:
assert len(res.body) == len(content)
for d in res.body:
assert 'embedding' in d
assert len(d['embedding']) > 1
else:
assert 'embedding' in res.body
assert len(res.body['embedding']) > 1


def test_embedding_openai_library_single():
global server
server.start()
Expand Down
1 change: 1 addition & 0 deletions examples/server/utils.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,6 +138,7 @@ static llama_tokens tokenize_mixed(const llama_context * ctx, const json & json_
* and multiple prompts (multi-tasks):
* - "prompt": ["string1", "string2"]
* - "prompt": ["string1", [12, 34, 56]]
* - "prompt": [[12, 34, 56], [78, 90, 12]]
* - "prompt": [[12, 34, "string", 56, 78], [12, 34, 56]]
*/
static std::vector<llama_tokens> tokenize_input_prompts(llama_context * ctx, const json & json_prompt, bool add_special, bool parse_special) {
Expand Down
Loading