0 Fork 0

mirror of https://github.com/langchain-ai/langchain.git synced 2026-10-06 01:45:27 +03:00

Files

T

Nothing major. The docs just give an error when you try to use
`embeddings` instead of `llama`.

2023-04-06 12:45:45 -07:00

Llama-cpp

This notebook goes over how to use Llama-cpp embeddings within LangChain

In [ ]:

!pip install llama-cpp-python

In [ ]:

from langchain.embeddings import LlamaCppEmbeddings

In [ ]:

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

In [ ]:

text = "This is a test document."

In [ ]:

query_result = llama.embed_query(text)

In [ ]:

doc_result = llama.embed_documents([text])