CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : allow to generate multimodal embeddings (#4681)

Browse Source
This commit is contained in:
Karthik Sethuraman
2023-12-29 06:22:10 -08:00
committed by GitHub
parent 82d6eab224
commit b93edd22f5
2 changed files with 14 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/README.md
View File

@@ -166,7 +166,7 @@ node index.js
`n_probs`: If greater than 0, the response also contains the probabilities of top N tokens for each generated token (default: 0)
`image_data`: An array of objects to hold base64-encoded image `data` and its `id`s to be reference in `prompt`. You can determine the place of the image in the prompt as in the following: `USER:[img-12]Describe the image in detail.\nASSISTANT:` In this case, `[img-12]` will be replaced by the embeddings of the image id 12 in the following `image_data` array: `{..., "image_data": [{"data": "<BASE64_STRING>", "id": 12}]}`. Use `image_data` only with multimodal models, e.g., LLaVA.
`image_data`: An array of objects to hold base64-encoded image `data` and its `id`s to be reference in `prompt`. You can determine the place of the image in the prompt as in the following: `USER:[img-12]Describe the image in detail.\nASSISTANT:`. In this case, `[img-12]` will be replaced by the embeddings of the image with id `12` in the following `image_data` array: `{..., "image_data": [{"data": "<BASE64_STRING>", "id": 12}]}`. Use `image_data` only with multimodal models, e.g., LLaVA.
*Result JSON:*
@@ -224,6 +224,8 @@ node index.js
`content`: Set the text to process.
`image_data`: An array of objects to hold base64-encoded image `data` and its `id`s to be reference in `content`. You can determine the place of the image in the content as in the following: `Image: [img-21].\nCaption: This is a picture of a house`. In this case, `[img-21]` will be replaced by the embeddings of the image with id `21` in the following `image_data` array: `{..., "image_data": [{"data": "<BASE64_STRING>", "id": 21}]}`. Use `image_data` only with multimodal models, e.g., LLaVA.
- **POST** `/infill`: For code infilling. Takes a prefix and a suffix and returns the predicted completion as stream.
*Options:*

12
examples/server/server.cpp
View File

@@ -3077,7 +3077,17 @@ int main(int argc, char **argv)
{
prompt = "";
}
const int task_id = llama.request_completion({ {"prompt", prompt}, { "n_predict", 0} }, false, true, -1);
json image_data;
if (body.count("image_data") != 0) {
image_data = body["image_data"];
}
else
{
image_data = "";
}
const int task_id = llama.request_completion({ {"prompt", prompt}, { "n_predict", 0}, {"image_data", image_data} }, false, true, -1);
task_result result = llama.next_result(task_id);
return res.set_content(result.result_json.dump(), "application/json; charset=utf-8");
});