Embedding Program¶
Program Identification¶
Author: Saul Emre Erdog
Maintainer: Saul Emre Erdog
Email: erdog@mbasesoftware.com
Name: mbase_embedding_simple
Version: v0.1.0
Type: Utility, Example
Network Usage: No
Lib Depends: mbase-std mbase-inference
Repo location: https://github.com/Emreerdog/mbase/tree/main/examples/embedding
Synopsis¶
mbase_embedding_simple model_path *[option [value]]
mbase_embedding_simple model.gguf -gl 80 -p 'What is life?'
mbase_embedding_simple model.gguf -gl 80 -pf prompt1.txt -pf prompt2.txt
Description¶
An example program for generating the embeddings of the given prompt or prompts.
The given implementation is stable and shows the basics of how to generate embeddings using MBASE embedder processor InfEmbedderProcessor
.
Options¶
- -h, --help¶
Print program information.
- -v, --version¶
Shows program version.
- -pf file_path, --prompt-file file_path¶
File containing prompt or prompts seperated by the seperator (default=’’). If prompt is given, prompt file will be ignored.
- -p string, --prompt string¶
Prompt or prompts seperated by the seperator (default=’’). This will be used even if the prompt file is supplied.
- -sp seperator, --seperator seperator¶
Prompt seperator (default=”<embd_sep>”).
- -t count, --thread-count count¶
Threads used to compute embeddings (default=16).
- -gl count, --gpu-layers count¶
Number of layers too offload to GPU. Ignored if there is no GPU is present. (default=999)
- -jout output_path, --json-output-path output_path¶
If the json output path is specified, result will be written there in file “openai_embeddings.json” (default=’’).