llama.cpp python library is a simple Python bindings for@ggerganovllama.cpp.

This package provides:

• Low-level access to C API via ctypes interface.
• High-level Python API for text completion
  • OpenAI-like API
  • LangChain compatibility
  • LlamaIndex compatibility
• OpenAI compatible web server
  • Local Copilot replacement
  • Function Calling support
  • Vision API support
  • Multiple Models

%pip install--upgrade--quiet  llama-cpp-python

from langchain_community.embeddingsimport LlamaCppEmbeddings

llama= LlamaCppEmbeddings(model_path="/path/to/model/ggml-model-q4_0.bin")

text="This is a test document."

query_result= llama.embed_query(text)

doc_result= llama.embed_documents([text])

Related​

• Embedding modelconceptual guide
• Embedding modelhow-to guides