CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-05 09:36:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

embedding: add raw option for --embd-output-format (#16541)

Browse Source 
* Add --embd-output-format raw for plain numeric embedding output

This new option outputs embeddings as raw space-separated floats, without JSON or 'embedding N:' prefixes. Useful for downstream vector pipelines and scripting.

* Move raw output handling into format handling section

* Move raw output handling into else-if block with other format handlers

* Use LOG instead of printf for raw embedding output

* docs: document 'raw' embedding output format in arg.cpp and README
This commit is contained in:
Sam Malayek
2025-10-28 03:51:41 -07:00
committed by GitHub
parent 7a0e900e36
commit 1c1409e131
3 changed files with 27 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/arg.cpp
View File

@@ -3248,7 +3248,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_EMBEDDING}));
add_opt(common_arg(
{"--embd-output-format"}, "FORMAT",
"empty = default, \"array\" = [[],[]...], \"json\" = openai style, \"json+\" = same \"json\" + cosine similarity matrix",
"empty = default, \"array\" = [[],[]...], \"json\" = openai style, \"json+\" = same \"json\" + cosine similarity matrix, \"raw\" = plain whitespace-delimited output (one embedding per line)",
[](common_params & params, const std::string & value) {
params.embd_out = value;
}